Forthcoming and Online First Articles

International Journal of Computational Science and Engineering

International Journal of Computational Science and Engineering (IJCSE)

Forthcoming articles have been peer-reviewed and accepted for publication but are pending final changes, are not yet published and may not appear here in their final order of publication until they are assigned to issues. Therefore, the content conforms to our standards but the presentation (e.g. typesetting and proof-reading) is not necessarily up to the Inderscience standard. Additionally, titles, authors, abstracts and keywords may change before publication. Articles will not be published until the final proofs are validated by their authors.

Forthcoming articles must be purchased for the purposes of research, teaching and private study only. These articles can be cited using the expression "in press". For example: Smith, J. (in press). Article Title. Journal Title.

Articles marked with this shopping trolley icon are available for purchase - click on the icon to send an email request to purchase.

Online First articles are published online here, before they appear in a journal issue. Online First articles are fully citeable, complete with a DOI. They can be cited, read, and downloaded. Online First articles are published as Open Access (OA) articles to make the latest research available as early as possible.

Open AccessArticles marked with this Open Access icon are Online First articles. They are freely available and openly accessible to all without any restriction except the ones stated in their respective CC licenses.

Register for our alerting service, which notifies you by email when new issues are published online.

We also offer which provide timely updates of tables of contents, newly published articles and calls for papers.

International Journal of Computational Science and Engineering (89 papers in press)

Regular Issues

  • Empowerment of cluster and grid load-balancing algorithms to support distributed exascale computing systems with high compatibility   Order a copy of this article
    by Faezeh Mollasalehi, Shirin Shahrabi, Elham Adibi, Ehsan Mousavi Khaneghah 
    Abstract: The occurrence of dynamic and interactive events in processes leads to changes in the state of their necessities and in the state of computing elements of the system, leading to changes in the state of the load balancer. This impact may render the load balancer unable to manage the load balancing of the system. On the other hand, the nature of the scientific applications that need to be distributed exascale systems means that both traditional and distributed exascale systems programs are required. As a result, not only does the load balancer support traditional patterns and mechanisms, but also these mechanisms should be empowered to support the states caused by the occurrence of events with a dynamic and interactive nature. In this paper, in addition to the examination of events with dynamic and interactive nature, a mathematical model is presented to examine the impact of this concept on the load balancer. This mathematical model examines the traditional load balancer that is used in cluster and grid computing systems and should support which characteristics to manage the dynamic and interactive nature in processes and execution in distributed exascale computing systems. Based on the model and definition of global activity, mechanisms that are used in cluster and grid systems in distributed exascale systems are examined. In cluster and grid systems that can support the specified characteristics in this article, in 60% of the cases, the load balancer can manage events with a dynamic and interactive nature and use the mathematical model as the load-balancing mechanism in the distributed exascale system.
    Keywords: distributed exascale computing; load balancing; events of dynamic and interactive nature; load-balancing algorithms; cluster computing; grid computing.

  • An improved method for K-means clustering based on internal validity indexes and inter-cluster variance   Order a copy of this article
    by Guangli Zhu, Xiaoqing Li, Shunxiang Zhang, Xin Xu, Biao Zhang 
    Abstract: The traditional internal validity indexes of k-means clustering algorithm are sometimes difficult to get the best cluster number. Therefore, a good clustering result cannot be obtained generally. To solve this problem, this paper proposes an improved method for k-means clustering based on internal validity indexes and inter-cluster variance. This method firstly sets different initial cluster numbers, which are all integers selected from the interval. Then the same data set is clustered under each selected cluster number to obtain the clustering results. Secondly, the obtained clustering results are evaluated by the internal validity indexes. Finally, if the internal validity values are similar, the inter-cluster variances among clustering numbers are compared to get the best clustering result. Experimental results show that the new improved method can obtain a better clustering result under a certain condition.
    Keywords: K-means clustering; internal validity indexes; inter-cluster variance.

  • Recommendation Service for hotel applications on blockchain   Order a copy of this article
    by Meng-Yen Hsieh, Pei-Wei Wang, Chih-Hong Kao 
    Abstract: Adopting recommendation mechanisms to process users data is available on cloud computing to enhance the performance of modelling user preference. Using recommendation APIs available in cloud computing, our work focuses on developing hotel or lodging web applications with a trust-based recommendation service. The recommendation service accompanying trust relationship among users is advanced further to reduce the problem of cold-start users and data-rating sparsity. Additionally, a blockchain service is assisted with an online room-booking service. We suggest that the architecture for hotel or lodging applications is incorporated with a number of requested modules. A prototype is built by the proposed modules over a cluster platform and a blockchain net. The experimental results show that the trust-based recommender of the prototype contains more improved accuracy than general recommenders only with explicit rating data. A smart contract in a blockchain test net for the online room-booking service is implemented, executed, and evaluated.
    Keywords: recommendation; booking; trust; blockchain.

  • Human interactive behaviour recognition method based on multi-feature fusion   Order a copy of this article
    by Qing Ye, Rui Li, Hang Yang, Xinran Guo 
    Abstract: Recently, the selection of the overall and individual characteristics in interactive actions and the high-dimensional complexity of features are still important factors affecting the recognition accuracy. In this paper, we propose a human interactive behaviour recognition method based on multi-feature fusion, which includes two parts, feature extraction and behaviour recognition. Firstly, we use histogram feature descriptors to form a three-dimensional gradient histogram of local space-time feature (3D-HOG) and a histogram of global optical flow feature (HOF). Then the bag-of-words model is used to reduce the dimensions, and the classification matrix is obtained through multilayer perceptron (MLP) classifiers. In the second part, we use recurrent neural network (RNN) to get connections in time. Considering the information of interactive behaviour will be different at different stages, an improved Gauss neural network is proposed for interactive behaviour recognition. The experimental results show that the algorithm can effectively improve the accuracy in the UT-interaction dataset.
    Keywords: multi-feature fusion; bag-of-words model; multilayer perceptron classifiers; an improved Gauss neural network; interactive behavior recognition.

  • Optimised implementation of AVR system using particle swarm optimisation (PSO)   Order a copy of this article
    by Amin Jarrah, Mohammad Zaitoun 
    Abstract: Several techniques have been developed to improve the control quality and deliver optimised products in many industrial process domains. This work aims to propose an optimised automatic voltage regulator (AVR) system implementation by applying a nature-inspired algorithm called Particle Swarm Optimization (PSO) to design a proportional-integrator-derivative (PID) controller for the AVR system. The proposed system consists of two controllers to deal with both the transient state and the time response. Various parallelisation and optimisation techniques, such as loop unrolling, loop pipelining, dataflow, and loop flattening, were adopted and applied to investigate the opportunities of creating a much more effective design. The proposed system achieves better results for the settling time and the overshoot, which makes the proposed system a suitable choice for zero overshoot industry applications.
    Keywords: optimisation techniques; particle swarm optimisation; PID controller; AVR system; time response; optimal control.

  • A secure hash function based on sponge construction and chaotic maps   Order a copy of this article
    by Amine Zellagui, Naima Hadj-said, Adda Ali Pacha 
    Abstract: This work introduces a new hash function based on the sponge structure and two chaotic maps. It aims to avoid the major problems of Merkle-Damg
    Keywords: PWLCM; hash function; chaotic maps; sponge construction; cloud computing; collision; password.

  • A Bayesian network correlation-based classifier chain algorithm for multilabel learning   Order a copy of this article
    by Hao Zhang, Kai-Biao Lin, Wei Weng, Juan Wen, Chin-Ling Chen 
    Abstract: In recent years, researchers have proposed many multilabel classification algorithms to solve the problem of multilabel classification. Among them, the classifier chain (CC) algorithm is widely studied because it fully considers the correlation between labels, the model size is linear with the number of labels, and the training steps can be executed in parallel. However, the chain label sequence of the CC algorithm is random; if the prediction results of the labels in front of the chain are not correct, the impact will spread throughout the rest of the chain, which will greatly affect the performance of the CC algorithm. To solve this problem, we propose a new multilabel learning method, the Bayesian network correlation-based CC (BNCC) algorithm, to decrease the uncertainty in the label order from the CC algorithm. It uses a neural network constructed in TensorFlow as the classifier of all labels and calculates the corresponding error function, which is used to eliminate the influence of the feature set on all labels. A directed acyclic graph (DAG) Bayesian network is constructed by using the error function to identify the correlations between the labels. The optimal correlation label is identified via topological sorting. Finally, the sorted sequence is used as the chain order of the CC. The experimental results demonstrate that the proposed method is superior to the unordered CC model and other multilabel learning algorithms on several benchmark datasets.
    Keywords: multilabel learning; Bayesian network; classifier chain; label relationship.
    DOI: 10.1504/IJCSE.2021.10042448
     
  • A multi-objective computation offloading algorithm in MEC environments   Order a copy of this article
    by Li Liu, Xuemei Lei, Qian Wang 
    Abstract: Mobile Edge Computing (MEC) is able to provide cloud computing capabilities at network edges by offloading computation tasks to MEC servers deployed in the proximity of edge nodes. Therefore, how to make offloading decision for mobile users has become a critical issue. In this paper, we propose a multi-objective computation offloading algorithm combining Multi-Objective Evolutionary Algorithm based on Decomposition (MOEA/D) with Invasive Weed Optimisation (IWO) and Differential Evolution (DE). Considering that IWO is a numerical stochastic optimisation method imitating weeds' behaviour in nature and enjoys great robustness, we further improve its searching abilities. In order to reduce computing time, single-object problems can be clustered into several groups in which only one problem can be optimised by IWO and others are optimised by DE. Experimental results show the competitive performance of our proposed algorithm for computation offloading in MEC environments.
    Keywords: mobile edge computing; computation offloading; MOEA/D; invasive weed optimisation; offloading decision.

  • An improved motion estimation criterion for temporal coding of video   Order a copy of this article
    by Awanish Mishra, Narendra Kohli 
    Abstract: The size of video data is growing exponentially worldwide and hence there is need for better video coding standards. There are many video coding standards given by MPEG and H.26X. The latest and effective video coding standards are AVC, HEVC and AV1. MPEG and H.26X use block matching techniques for the temporal coding and these block matching techniques mostly use mean absolute difference (MAD) as the block matching criterion. MAD is very simple and there is much less complexity in its implementation, but sometimes MAD results in spurious selection of matched block owing to different transformations in sequential images and the noise introduced in the frame. To overcome this problem there have been many matching criteria, such as vector matching criteria (VMC), smooth constrained mean absolute error (SC-MAE) and scaled value criterion (SVC). Criteria defined up till now do not consider the noise introduced in the frame and hence are still producing incorrect selection or rejection of the blocks. In this paper, a new motion estimation criterion is suggested and compared with four existing criteria in terms of PSNR, average number of evaluated search points per block, and average MAD per pixel. The MAD per pixel improves by nearly 70% for the proposed matching criterion.
    Keywords: motion estimation; matching criterion; block matching; search window; source block.

  • Cyberbullying detection: an ensemble learning approach   Order a copy of this article
    by Pradeep Kumar Roy, Ashish Singh, Asis Kumar Tripathy, Tapan Kumar Das 
    Abstract: Online social networking platforms have become a common choice for people to communicate with friends, relatives, or business partners. This allows sharing life achievement, success, and much more. In parallel, it also invited hidden issues such as web-spamming, cyberbullying, cybercrime, and others. This paper addresses the issue of cyberbullying using an ensemble machine learning model. The complete experiment works in two phases: firstly, k-nearest neighbour, logistic regression and decision tree classifiers are used to detect the bullying post. Secondly, the prediction outcomes of these classifiers are passed to a voting-based ensemble learning model for the predictions. The experimental outcomes confirmed that the ensemble model is detecting bullying posts with good accuracy.
    Keywords: cyberbullying; Twitter; social network; ensemble learning; classification.

  • T-PdM: tripartite predictive maintenance framework using machine learning algorithms   Order a copy of this article
    by Ozlem Ece Yurek, Derya Birant, Alp Kut 
    Abstract: The purpose of this paper is to propose a new predictive maintenance (PdM) framework that has three aspects: (i) estimating the remaining useful life (RUL) of a machine, (ii) classifying machine health status (failure/non-failure), and (iii) discovering the relationship between the errors and component failures of machines by using machine learning (ML) techniques. This is the first PdM framework that integrates three ML paradigms (regression, classification, and association rule mining) in a single platform. It compares six different ML algorithms. The results indicate that the proposed framework can be successfully used to get valuable knowledge about machines and to build a consistent maintenance strategy to improve machine usage in the industry sector. The existing PdM studies usually use only one ML paradigm, which is insufficient for prediction. To overcome this limitation and improve prediction accuracy, a novel tripartite predictive maintenance framework (T-PdM) is proposed in this study.
    Keywords: predictive maintenance; machine learning; classification; regression; association rule mining.

  • Automated network intrusion detection using multimodal networks   Order a copy of this article
    by Subhash Pingale, Sanjay R. Sutar 
    Abstract: Intrusion detection requires accurate and timely detection of any bad connection that intends to exploit network vulnerabilities. Previous approaches have focused on deriving statistical features based on domain knowledge, followed by primitive machine learning and ensemble techniques. Grouping all the parameters as a single input to a model may not always be effective. In this paper, we propose using multimodal networks for network intrusion detection. The input logs are segregated into multiple subgroups trained differently. Their intermediate representations are combined to produce the final prediction. This approach handles the strengths of individual features better than normalization. The system is evaluated on the NSL-KDD dataset and is compared with standard methods across multiple performance metrics. The proposed system achieves an accuracy of 83.5, the highest compared with other approaches. Channeling inputs for richer feature extraction is fast gaining traction, and we extend the same in cybersecurity.
    Keywords: intrusion detection system; multimodal networks; NSL-KDD dataset; cybersecurity.
    DOI: 10.1504/IJCSE.2022.10044448
     
  • A hybrid of local and global atmospheric scattering models for depth prediction via the cross Bayesian model   Order a copy of this article
    by Qianjin Zhao, Haitao Zhang, Jianhua Cui, Yanguang Sun, Songsong Duan, Chenxing Xia 
    Abstract: Monocular depth estimation is a fascinating and challenging problem in virtual vision. However, the training of networks based on deep learning largely depends on the training data. This paper proposes a depth prediction method based on the depth cue: atmospheric light scattering, which can effectively predict the depth in different atmospheric light scenarios. But the assumption of global atmospheric light constancy produces unavoidable error. Especially for complex scenes, the complex reflected light of the scene leads to uneven distribution of atmospheric light. This paper proposes a new local atmospheric light estimation method, which can more effectively simulate the real distribution of atmospheric light scattering in the air. The experiment found that the two models are complementary. In order to fuse the intrinsic real information of the two models, this paper adopts the fusion strategy based on the cross Bayesian model, and edge preserving filtering is used to preserve the detailed information.
    Keywords: depth estimation; global atmospheric light; local atmospheric light; cross Bayesian model.
    DOI: 10.1504/IJCSE.2021.10043067
     
  • Research on online emotion of COVID-19 based on text sentiment analysis   Order a copy of this article
    by Zhenyu Gu, Yao Lin, Yonghui Dai, Chenxiao Niu 
    Abstract: The growth of internet users and the convenience of internet communication provide a foundation for the formation of internet emotions. As the internet and real-life interactions become closer, the influence of internet emotions on society is increasing. Therefore, taking the spread of COVID-19 in Xinjiang in 2020 as an example, 43,111 related micro-blog texts were collected. After a series of operations, such as Chinese word segmentation, POS tagging, data cleaning, text representation, feature extraction and so on, thematic extraction and text sentiment analysis were carried out to get people's comment themes, emotional tendencies and COVID-19's network emotional situation. The results show that the public will have a better understanding of the cause of COVID-19 disease and its infectiousness, preventive measures and cure as time goes on. The research of this paper can help the relevant government departments to perceive and guide the network emotional situation.
    Keywords: COVID-19; text sentiment analysis; web sentiment; feature extraction; topic mining.

  • A named entity recognition method towards product reviews based on BiLSTM-Attention-CRF   Order a copy of this article
    by Shunxiang Zhang, Haiyang Zhu, Hanqing Xu, Guangli Zhu 
    Abstract: Named Entity Recognition (NER) towards product review is intended to identify domain-dependent named entities (e.g., organisation name, product name, etc.) from product reviews. Owing to the fragmentation and non-construction of product reviews, traditional methods are difficult to capture the domain feature information and dependencies precisely. To solve the problem, we propose an NER method towards product reviews based on BiLSTM-Attention-CRF. Firstly, three kinds of feature (characters, words and parts of speech) are integrated into the feature representation of texts. The final feature vector is obtained through training, mapping and linking the selected features. Then, the BiLSTM network is built to extract text features, and the Attention Mechanism is adopted to strengthen the capture of local features. Finally, CRF is applied to annotate and identify the entity. Compared with existing models, it is demonstrated that the proposed method can effectively recognise named entities from product reviews.
    Keywords: NER; product reviews; BiLSTM; Attention Mechanism; CRF.

  • Efficient and non-interactive ciphertext range query based on differential privacy   Order a copy of this article
    by Peirou Feng, Qitian Sheng, Jianfeng Wang 
    Abstract: Differential private range query schemes satisfy differential privacy by adding or deleting records during the process of creating the index, which suffers from the weakness of data loss in query results owing to the negative noise. Recently, Sahin et al. proposed a differential private index with overflow arrays in ICDE 2018, which ensures the integrity of query results. However, this scheme suffers from two drawbacks: (i) some private information (e.g., query requests or frequency) may be leaked because of querying over plaintext index; (ii) the overflow arrays bring extra storage overhead. To this end, we present a non-interactive ciphertext range query based on differential privacy and comparable encryption. Our scheme can protect the query privacy since the query is performed over ciphertext based on comparable encryption. The experiment results show that our proposed scheme can save the storage overhead.
    Keywords: range query; differential privacy; short comparable encryption.

  • Joint training with the edge detection network for salient object detection   Order a copy of this article
    by Zongyun Gu, Junling Kan, Chun Ma, Wang Qing, Fangfang Li 
    Abstract: The U-shaped network has great advantages in object detection tasks. However, most of the previous salient object detection studies suffered from inaccurate predictions affected by unclear object boundaries. Considering the complementarity of the information between salient object and salient edge, we designed a new kind of network to effectively perform the joint training with edge detection tasks in three steps. Firstly, we added a prediction branch on the bottom-up pathway for capturing the edge of salient objects. Secondly, salient object features, global context, integrated low-level details, and high-level semantic information are extracted by the method of progressive fusion. Finally, the feature of the salient edge is concatenated with that of the salient object on the last layer in the top-down pathway. Since the salient edge feature contains much information about edge and location, the feature fusion can locate salient objects more accurately. The results of experiments on five benchmark datasets demonstrate that the proposed approach achieves competitive performance.
    Keywords: deep learning; salient object detection; U-shape architecture; edge detection; feature pyramid network.
    DOI: 10.1504/IJCSE.2022.10045026
     
  • Application of a deep learning approach for recognition of voiced Odia digits   Order a copy of this article
    by Prithviraj Mohanty, Jyoti Prakash Sahoo, Ajit Kumar Nayak 
    Abstract: Automatic speech recognition in a regional language such as Odia is a challenging field of research. Voiced Odia digit recognition helps in designing automatic voice dialler systems. In this study, a deep learning approach is used for the recognition of voiced Odia digits. The spectrogram representation of voiced samples is given as the input to the deep learning models after considering the feature extraction using MFCC. Various performance metrics are obtained by considering several experiments with different epoch sizes and variation in the dataset, using the train-validate-test ratio. Experimental outcomes reveal that the CNN model provides improved accuracy of 91.72% in epoch size of 500 with a split ratio of 80-10-10 as compared with the other two models that use VSL and DNN. The reported outcome reveals that the proposed CNN model has better average recognition accuracy than contemporary models such as HMM and SVM.
    Keywords: ASR; CNN; DNN; MFCC; HMM; SVM; spectrogram.

  • Service recommendation through graph attention network in heterogeneous information networks   Order a copy of this article
    by Fenfang Xie, Yangjun Xu, Angyu Zheng, Liang Chen, Zibin Zheng 
    Abstract: Recommending suitable services to users autonomously has become the key to solve the problem of service information overload. Existing recommendation algorithms have some limitations, either discarding the side information of the node, or ignoring the information of the intermediate node, or omitting the feature information of the neighbour nodes, or not modelling the pairwise attentive interaction between users and services. To solve the above-mentioned limitations, this paper proposes a service recommendation approach by leveraging the graph attention network (GAT) and co-attention mechanism in heterogeneous information networks (HINs). Specifically, different types of meta-path are first constructed, and a feature expression is learned for each node in HINs. Then, the feature information of mashups/services are aggregated by the co-attention mechanism. Finally, the multi-layer perceptron (MLP) is applied to recommend suitable services for users. Experiments on a real-world dataset illustrate that the proposed method outperforms other state-of-the-art comparison methods.
    Keywords: service recommendation; graph attention network; co-attention mechanism; heterogeneous information network.

  • Machine learning-based land usage identification using Haralick texture features of aerial images with Kekres LUV colour space   Order a copy of this article
    by Sudeep Thepade, Shalakha Bang, Rik Das, Zahid Akhtar 
    Abstract: Study of gathering some useful insights from our planet Earth its natural, man-made, physical, and biological structures is quite engrossing. Earth observation, despite being intuitive, also helps in mitigating the adverse impacts of human civilisation on our mother Earth. Multiple techniques that help in observing the Earths surface include Earth Surveying Techniques, Remote Sensing technology, etc. The properties which are measured using Remote-sensing technology stimulate the study of Land Usage Identification which refers to the purpose the land is used for. The rapid increase in population, immense growth in infrastructure and technology have led to massive urbanisation posing a great number of challenges. The knowledge of Land Use Identification will help in developing strategies to drive off issues related to the depletion of forest areas, urban encroachment, monitoring of natural disasters, etc. This paper attempts to give a more robust approach towards Land Usage Identification that extracts Haralick texture features from input aerial images of the earth by considering their representation in two different color spaces namely RGB and Kekre-LUV. Comparing the results obtained by using different machine learning classification algorithms, it is found that an ensemble of simple logistic and random forest classifiers outputs maximum classification accuracy.
    Keywords: grey level co-occurrence matrix; random forest; simple logistic regression; land usage identification; remote sensing.
    DOI: 10.1504/IJCSE.2022.10045551
     
  • Constrained-based power management algorithm for green cloud computing   Order a copy of this article
    by Sanjib Kumar Nayak, Sanjaya Kumar Panda, Satyabrata Das 
    Abstract: In green cloud computing (GCC), power management provides many advantages, such as reducing costs, saving the environment and improving system efficiency. It is adopted in various facilities, like datacenters, which are backed by non-renewable energy (NRE) sources. These sources are not only costly, but also drastically impact the environment. This paper introduces a constrained-based power management algorithm, which considers four NRE and RE power supplies of the datacenters, grid, photovoltaics (PV), wind and battery, to fulfill the cumulative load power demand of submitted user requests (URs). The URs are fulfilled in the order of PV, wind and battery, and grid, respectively. The simulation is carried out by taking NRE sources, RE sources and both, and ten instances. The simulation results are compared using overall cost, UR assigned to NRE and UR assigned to RE to show the performance in three scenarios of the proposed algorithm.
    Keywords: green cloud computing; power management; non-renewable energy; renewable energy; fossil fuel; solar energy; wind energy; load balancing.

  • Optimisations of four imputation frameworks for performance exploring based on decision tree algorithms in big data analysis problems   Order a copy of this article
    by Jale Bektas, Turgay Ibrikci 
    Abstract: The phenomenon of how to treat missing values is a problem confronted in big data analysis. Therefore, various applications have been developed on imputation strategies. This study focused on four imputation frameworks proposing novel perspectives based on expectation-maximization (EM), self-organising map (SOM), K-means, and multilayer perceptron (MLP). Initially, several transformation steps such as normalized, standardised, interquartile range, and wavelet were applied. Then, imputed datasets were analysed using decision tree algorithms (DTAs) by optimising their parameters. These analyses showed that DTAs had not been strikingly affected by any data transformation techniques except interquartile range. Even though the dataset contains a missing value ratio of 33.73%, the EM imputation framework provided a performance increase of 0.42% to 3.14%. DTAs based on C4.5 and NBTree algorithms have been more stable in analysing all big imputed datasets. Furthermore, realistic performance measurement of any preprocessing experiment with a classification algorithm based on C4.5 can be proposed to avoid time complexity.
    Keywords: preprocessing; data mining; multiple imputation,decision tree classifier; machine- learning; big data analytics.

  • A new approach based on generalised multiquadric and compactly supported radial basis functions for solving two-dimensional Volterra-Fredholm integral equations   Order a copy of this article
    by Dalila Takouk 
    Abstract: This article describes a numerical scheme to solve two-dimensional nonlinear VolterraFredholm integral equations (IEs). The method estimates the solution by compactly supported radial basis functions and compared with the approximation of the solution by generalised multiquadric radial basis function with the optimal strategy for the exponent . Integrals appearing in the procedure of the solution are approximated using shifted LegendreGaussLobatto nodes and weights. The method is mathematically simple and truly meshless. It can be used for high-dimensional problems because it does not require any cell structures. Finally, numerical experiments are given to show and test the applicability of the presented approach and confirm the theoretical analysis.
    Keywords: Volterra-Fredholm integral equations; two-dimensional integral equations; generalized multiquadric radial basis functions; compactly supported radial basis functions; interpolation method; shifted Legendre-Gauss-Lobatto nodes and weights .

  • KH-FC: krill herd-based fractional calculus algorithm for text document clustering using MapReduce structure   Order a copy of this article
    by Priyanka Shivaprasad More, Dr. Baljit Singh Saini 
    Abstract: In this paper, Krill Herd-based Fractional Calculus (KH-FC) using MapReduce framework is proposed for effective text document clustering. Here, the stop word removal and stemming model is applied in the pre-processing step, helps to remove redundant information and hence the size of the information is reduced, which further enhances the clustering accuracy. Furthermore, Term Frequency (TF) and Inverse Document Frequency (IDF) are employed for extracting significant features. Finally, the developed KH-FC model is used for clustering the text documents. The developed KH-FC algorithm is developed by combining the FC concept into the KH technique. In this method, pre-processing and feature extraction is performed in the mapper phase, whereas the clustering process is executed in the reducer phase. The performance of the developed approach is evaluated based on performance metrics, such as accuracy, Jaccard coefficient, and F-measure. The developed KH-FC approach obtained better performance in terms of accuracy, Jaccard coefficient, and F-measure is 0.983, 0.936 and 0.967, respectively.
    Keywords: text document clustering; fractional calculus; krill herd algorithm; term frequency–inverse document frequency; Jaccard similarity.

  • A comprehensive understanding of popular machine translation evaluation metrics   Order a copy of this article
    by Md. Adnanul Islam, Md. Saddam Hossain Mukta 
    Abstract: Machine translation is one of the pioneer applications of natural language processing and artificial intelligence. Automatic evaluation of the translation performance of the machine translators is one of the most challenging tasks, as manual evaluation of large volumes of document translations is infeasible in practice. Thus, to facilitate the evaluation of translation performance automatically, several metrics have been introduced and used widely. Although these translation performance evaluation metrics cannot match the efficiency level of human evaluation, they are popularly employed in automatic evaluation of translation quality of texts across multifarious application domains. This article discusses three such widely used evaluation metrics BLEU, METEOR, and TER, with relevant details by demonstrating step-by-step calculations. The main novelty of this article lies in the consideration of several example translations to present and clarify the calculation process of these three popular evaluation metrics for measuring the performance or quality of machine translation. Moreover, the article presents a comparative analysis among these three metrics using two different datasets to reveal their similarities and distinctions in terms of behaviour.
    Keywords: evaluation metrics; translation performance; BLEU; METEOR; TER; machine translation.
    DOI: 10.1504/IJCSE.2021.10044073
     
  • Intelligent recommendation of personalised tourist routes based on improved discrete particle swarm   Order a copy of this article
    by Jie Luo, Xilian Duan 
    Abstract: In order to overcome the problems of low accuracy and long time consuming in traditional personalised travel route recommendation methods, this paper proposes an intelligent recommendation of personalized tourist routes based on improved discrete particle swarm. This method analyses the key problems of tourism recommendation according to the personalised tourism characteristics, collects the information of tourists' interest, and establishes the model of tourists' interest. On this basis, the discrete particle swarm optimisation algorithm is improved, and the improved discrete particle swarm optimisation algorithm is used to select the personalised travel route, and the selection results are recommended to the passengers, so as to realise the personalised travel route intelligent recommendation. The experimental results show that the recommendation accuracy of this method is between 82.5% and 96.9%, and the recommendation time is always less than 0.5 s, which can realise the accurate and rapid recommendation of personalised tourist routes.
    Keywords: discrete particle swarm; personalised travel route; intelligent recommendation; passenger interest.

  • Web API service recommendation for mashup creation   Order a copy of this article
    by Gejing Xu, Sixian Lian, Mingdong Tang 
    Abstract: Mashup refers to a sort of Web application developed by reusing or combining Web API services, which are very popular software components for building various applications. As the number of open Web APIs increases, to find suitable Web APIs for mashup creation, however, becomes a challenging issue. To address this issue, a number of Web API service recommendation methods have been proposed. Content-based methods rely on the description of the service candidates and the users request to make recommendations. Collaborative filtering-based methods use the invocation records of a set of services generated by a set of users to make recommendations. There are also some studies employing both the description and invocation records of services to make recommendations. In this paper, we survey the state-of-the-art Web API service recommendation methods, and discuss their characteristics and differences. We also present some possible future research directions.
    Keywords: web service; recommendation; collaborative filtering; mashup creation.

  • A novel dual-fusion algorithm of single image dehazing based on anisotropic diffusion and Gaussian filter   Order a copy of this article
    by Kaihan Xiao, Qingshan Tang, Si Liu, Sijie Li, Jiayi Huang, Tao Huang 
    Abstract: Dark channel prior (DCP) is a widely used method in single image dehazing technology. Here, we propose a novel dual-fusion algorithm of single image dehazing based on anisotropic diffusion and Gaussian filter to suppress the halo effect or colour distortion in traditional DCP algorithms. Anisotropic diffusion is used for edge-preserving smooth images and a Gaussian filter is used to smooth the local white objects. A dual-fusion strategy is conducted to optimise the atmospheric veil. Besides, the fast explicit diffusion (FED) scheme is used to accelerate the numerical solution of the anisotropic diffusion to reduce time consumption. The subjective and objective evaluation of the experiment shows that the proposed algorithm can effectively suppress the halo effect and colour distortion, and has good dehazing performance on evaluation metrics. The proposed algorithm also reduces the time consumption by 54.2% compared with DCP with guided filter. This study provides an effective solution for single image dehazing.
    Keywords: image dehazing; dark channel prior; anisotropic diffusion; fast explicit diffusion; image fusion.

  • Robust pedestrian detection using scale and illumination invariant mask R-CNN   Order a copy of this article
    by Ujwalla Gawande, Kamal Hajari, Yogesh Golhar 
    Abstract: In this paper, we address the challenging difficulty of detecting pedestrians with variation in scale and the illumination of the images. Occurrences of pedestrians with such variations exhibit diverse features. Therefore, it intensely affects the performance of recent pedestrian detection methods. We propose a new robust approach for overcoming the antecedent challenges. We proposed a Scale and Illumination invariant Mask R-CNN (SII Mask-RCNN) framework. The first phase of the proposed framework wields illumination variations by performing a logarithmic transformation and adaptive illumination enhancement. In addition, the non-subsampled contourlet transform used to decompose the image into multi-resolution components. Finally, we convolved the image with the multi-scale masks to find corresponding points that are illumination and scale-invariant. Extensive evaluations on pedestrian benchmark databases illustrate the effectiveness and robustness of the proposed framework. The experimental results contribute the notable performance improvements in pedestrian detection compared with the state-of-the-art approaches.
    Keywords: deep learning; pedestrian detection; computer vision; neural network; CNN.
    DOI: 10.1504/IJCSE.2022.10045688
     
  • Spam email classification and sentiment analysis based on semantic similarity methods   Order a copy of this article
    by Ulligaddala Srinivasarao, Aakanksha Sharaff 
    Abstract: Electronic mail is widely used for communication purposes, and the spam filter is required in the email to save storage and protect from security issues. Various techniques based on NLP methods are used to increase spam detection efficiency. Spam detection cannot handle the unbalanced classes and lower efficiency owing to irrelevant feature extraction in existing approaches. In this research, sentiment analysis-based semantic FE and hybrid FS techniques were used to increase the spam and non-spam detection efficiency in email. The sentiment analysis is carried out in this proposed method with semantic feature extraction and hybrid FS. The sentiment analysis measures the polarity of the input text and used for email spam classification. Different semantic similarity feature extraction methods are used in this proposed method. The TF-IDF, Information Gain, and Gini Index were used. The proposed semantic similarity and hybrid FS were evaluated with various classifiers. The experimental analysis shows that the Gini index FS technique, word2vec FE, and SVM classifier show the higher performance of 95.17% and RF with Gini index and word2vec methods has 93.3% accuracy in email spam detection.
    Keywords: artificial neural network; hybrid feature selection; semantic similarity; SVM; TF-IDF.

  • An efficient algorithm for maximum cliques problem on IoT devices   Order a copy of this article
    by Bouneb Zine El Abidine 
    Abstract: This work describes how the maximum clique problem (MCP) algorithm can be performed on microcontrollers in a dynamic environment. In practice, many problems can be formalised using MCP and graphs where our problem is considered in the context of a dynamic environment. MCP is, however, a tricky problem NP-Complete, for which suitable solutions must be designed for microcontrollers. Microcontrollers are built for specific purposes and optimised to meet different constraints, such as timing, nested recursion depth limitation, or no recursion at all due to recursion stack limitation, power, and RAM limitation. On another side, graph representation and all the algorithms mentioned in the literature to solve the MCP, which is recursive, consume memory and are designed specifically for computers rather than a microcontroller.
    Keywords: MCE; MCP; microcontrollers ; IoT; agent coalition; symbolic computation; n queens completion problem ; MicroPython.

  • A new resource-sharing protocol in the light of a token-based strategy for distributed systems   Order a copy of this article
    by Ashish Singh Parihar, Swarnendu Chakraborty 
    Abstract: One of the highly researched areas in distributed systems is mutual exclusion. To avoid any inconsistent state of a system, more than one process executing on different processors are not allowed to invoke their critical sections simultaneously for the purpose of resource sharing. As a solution to such resource allocation issues, a token-based strategy for distributed mutual exclusion algorithms as a prime classification of solutions is one of the most popular and significant ways to handle mutual exclusion in this field. Through this research article, we propose a novel token-based distributed mutual exclusion algorithm. The proposed solution is scalable and has better results in terms of message complexity compared with existing solutions. In this proposed method, the numbers of messages exchanged per critical section invocation are 3(?log? N?-1), 3?(?log?(N+1) ?-1)/2? and 6[?log?(N+1)?+2(2^(-?log?(N+1)?)-1)] in the cases of light load, medium load and high load situations, respectively.
    Keywords: distributed system; mutual exclusion; critical section; token-based; resource allocation.

  • Cybersecurity threats and vulnerabilities in 4G/5G network enabled systems   Order a copy of this article
    by Shailendra Mishra 
    Abstract: Radio access networks, core networks, transport networks, and interconnect networks of 4G and 5G networks are exposed to threats. In 4G and 5G technology, the security system consists of standardisation, network policy, network arrangement, and network placement and approach. The study aims to examine the challenges associated with cybersecurity threats and vulnerabilities within 4G/5G networks and how they affect the use of these networks. From the analysis of the primary data, it appears that 4G and 5G telecommunications networks face some significant cybersecurity issues that require regulatory intervention. The simulation results show that the proposed intrusion detection and defence system has better QoS. The security solutions are fast and effective in detecting and mitigating cyber-attacks. In terms of cyber-attack detection and mitigation, the solutions are fast and effective.
    Keywords: 4G and 5G enabled networks; cybersecurity; threats; vulnerabilities; IDS.

  • Low-loss data compression using deep learnong framework with attention-based autoencoder   Order a copy of this article
    by S. Sriram, P. Chitra, V.V. Sankar, S. Abirami, S.j. Rethina Durai 
    Abstract: With the rapid development of media, representation and compression of data plays a vital role for efficient data storage and data transmission. Deep learning can help the research objective of compression by exploring its technical avenues to overcome the challenges faced by the traditional Windows archiver. The proposed work is an experimental effort to employ deep learning for data compression to achieve high compression rate with reduced loss. Initially, the work explored multilayer autoencoder models that obtained efficient data compression with higher compression ratio than the traditional Windows archiver. However, the autoencoders suffered from reconstruction loss. Therefore, an added attention mechanism in the autoencoder is proposed for reducing the reconstruction loss. The objective of the attention mechanism is to reduce the difference between the latent representation of an input at the encoder with its corresponding representation in the decoder along with the difference between the original input and its corresponding reconstructed output. This attention layer introduced in a multilayer autoencoder that capably compresses the data with improved compression ratio and reduced reconstruction loss. The proposed attention-based autoencoder is extensively evaluated on the atmospheric and oceanic data obtained from the Centre for Development of Advanced Computing. The validation shows that the proposed attention-based autoencoder could proficiently compress the data with around 89.7% improved compression rate compared with the traditional Windows archiver. Also, the results demonstrate that the proposed attention mechanism reduces the reconstruction loss by up to 25% more than the multilayer autoencoder
    Keywords: deep learning; multilayer autoencoder; compression ratio; attention; reconstruction loss.

  • Cross-modal correlation feature extraction with orthogonality redundancy reduce and discriminant structure constraint   Order a copy of this article
    by Qianjin Zhao, Xinrui Ping, Shuzhi Su 
    Abstract: Canonical Correlation Analysis (CCA) is a classic feature extraction method that widely used in the field of pattern recognition. Its goal is to learn correlation projection directions to maximize the correlation between the two sets of variables, but it does not consider the class label information among samples and the within-modal redundancy information from the correlation projection directions. To this end, this paper proposes a class label embedded orthogonal correlation feature extraction method. This method embeds label-guide discriminant structure information into correlation analysis theories for improving discrimination of correlation features, and within-modal orthogonality constraints are added to further reduce the projection redundancy of correlation features. Experiments on multiple image databases show that this method is an effective feature extraction method. This method provides a new solution to pattern recognition.
    Keywords: feature extraction; correlation analysis theory; discriminative subspace learning; orthogonality redundancy reduce.

  • Hurst exponent estimation using neural network   Order a copy of this article
    by Somenath Mukherjee, Bikash Sadhukhan, Arghya Kusum Das, Abhra Chaudhuri 
    Abstract: The Hurst exponent is used to identify the autocorrelation structure of a stochastic time series, which allows for detecting persistence in time series data. Traditional signal processing techniques work reasonably well in determining the Hurst exponent of a stochastic time series. However, a notable drawback of these methods is their speed of computation. On the other hand, neural networks have repeatedly proven their ability to learn very complex input-output mappings, even in very high dimensional vector spaces. Therefore, an endeavour has been undertaken to employ neural networks to determine the Hurst exponent of a stochastic time series. Unlike previous attempts to solve such problems using neural networks, the proposed architecture can be recognised as the universal estimator of the Hurst exponent for short-range and long-range dependent stochastic time series. Experiments demonstrate that, if sufficiently trained, a neural network can predict the Hurst exponent of any stochastic time series at least 15 times faster than standard signal processing approaches.
    Keywords: neural network; regression; Hurst exponent estimation; stochastic time series.
    DOI: 10.1504/IJCSE.2022.10045166
     
  • Enhancement of classification and prediction accuracy for breast cancer detection using fast convolution neural network with ensemble algorithm   Order a copy of this article
    by Naga Deepti Ponnaganti, Raju Anitha 
    Abstract: Breast cancer is a leading cancer found mostly in women across the world and are more in number in the developing countries where they are not diagnosed in the early stages. The recent works have compared machine learning algorithms using various techniques, such as ensemble methods and classification. Hence, the requirement now is to develop a technique that gives minimum error to increase accuracy. So, this paper proposes the neural network where classifying and predicting breast cancer are enhanced with maximum accuracy. The novel technique of fast convolution neural network (FCNN) has been used for enhancing the classification and for improving the prediction accuracy ensemble algorithm of gradient boosting and adaptive boosting. By this proposed technique with ensemble algorithm, the huge data has been taken and predicted for detecting the cancer, and this combined boosting algorithm will reduce the misclassification and will improve the binary classification. The training and testing of the dataset has been done with FCNN where the numerous datasets can be classified for earlier detection of cancer. The simulation result shows the improved accuracy, prediction class, precision and F-1 score.
    Keywords: breast cancer; machine learning algorithms; classification; prediction accuracy; fast convolution neural network; gradient boosting and adaptive boosting.
    DOI: 10.1504/IJCSE.2022.10045291
     
  • Combining DNA sequences and chaotic maps to improve robustness of RGB image encryption   Order a copy of this article
    by Onkar Thorat, Ramchandra Mangrulkar 
    Abstract: In todays world, colour images are generated and stored for a variety of purposes by organisations. Standard encryption schemes, such as AES or DES, are not well suited for encryption of multimedia data owing to their pattern appearance and high computational cost. Many methods are being proposed for the encryption of greyscale images. However, there are only a few methods proposed in the literature specifically for encrypting colour images. This paper presents a new method, called RGB Image Encryption Scheme (RGBIES), for encrypting colour images based on chaotic maps and DNA sequences. RGBIES has three major stages. Stages 1 and 3 propose a powerful scrambling algorithm based on a chaotic logistic map. The intermediate step uses a chaotic Lorenz map, the keys of which are obtained using DNA sequences. Various visual and quantitative analyses are performed that prove the resistance of the method against modern-day attacks.
    Keywords: image encryption; image security; chaotic maps; deoxyribonucleic acid sequences; security analysis; cryptography; diffusion.

  • Improved class-specific vector for biomedical question type Classification   Order a copy of this article
    by Tanu Gupta, Ela Kumar 
    Abstract: Polysemy words in questions are problematic in labelling questions correctly. This paper proposes two word embedding based approaches for tackling the polysemy problem in biomedical question type classification. In the first approach, the label-independent class vector is drawn using a statistical score of the word for classifying multi-class questions dataset, unlike previous work where the class vector is label-dependent. Secondly, the sense vector of a word interpreted using a context group discrimination algorithm is concatenated with class-specific word embedding to increase the discriminative property of the word. Besides this, a survey dataset Covid-S is introduced in this paper, which is a collection of public queries, myths, and doubts about novel Covid-19 diseases. The efficacy of our introduced approach for question classification is evaluated for BioASQ8b and Covid-S datasets with three well-known evaluation measures: accuracy, micro-average and Hamming loss.
    Keywords: class vector; polysemy; biomedical question classification; sense embedding; Covid-S.

  • Research on big data access control mechanism   Order a copy of this article
    by Yinxia Zhuang, Yapeng Sun, Han Deng, Jun Guo 
    Abstract: The increasing amount of data provides an excellent opportunity for the analysis of big data. But when we consider the convenience provided by big data, we should also consider the security issues involved behind it. In recent years, the leakage of data resources has become a troublesome problem in the field of big data. The emergence of access control technology adds a barrier to the access of data resources, avoids some illegal users' access to resources, and reduces the problem of resource leakage to a certain extent. This paper summarises the development of some access control technologies in the field of big data access control, including discretionary access control technology, role-based access control technology, attribution-based access control technology, blockchain-based access control technology, etc. Then it summarises the application characteristics of access control technology in the field of big data, and finally looks forward to the development prospect of access control.
    Keywords: big data; Access control; Security.

  • Combining machine learning and effective feature selection for real-time stock trading in variable time-frames   Order a copy of this article
    by A. K. M. Amanat Ullah, Fahim Imtiaz, Miftah Uddin Md Ihsan, Md. Golam Rabiul Alam, Mahbub Majumdar 
    Abstract: The unpredictability and volatility of the stock market render it challenging to make a substantial profit using any generalised scheme. Many previous studies tried different techniques to build a machine learning model, which can make a significant profit in the US stock market by performing live trading. However, very few studies have focused on the importance of finding the best features for a particular period for trading. Our top approach used the performance to narrow down the features from a total of 148 to about 30. Furthermore, the top 25 features were dynamically selected before each time training our machine learning model. It uses ensemble learning with four classifiers: Gaussian Naive Bayes, Decision Tree, Logistic Regression with L1 regularization, and Stochastic Gradient Descent, to decide whether to go long or short on a particular stock. Our best model performed daily trade between July 2011 and January 2019, generating 54.35% profit. Finally, our work showcased that mixtures of weighted classifiers perform better than any individual predictor about making trading decisions in the stock market.
    Keywords: feature selection; feature extraction; stock trading; ensemble learning.
    DOI: 10.1504/IJCSE.2022.10046373
     
  • Privacy-preserving global user profile construction through federated learning   Order a copy of this article
    by Zheng Huo, Teng Wang, Yilin Fan, Ping He 
    Abstract: User profiles are derived from big data left on the internet through machine learning algorithms. However, threats of data privacy leakages restrict access to the sources of data in centralised machine learning. Federated learning can avoid privacy leakage during the data collection phase. In this study, we propose an algorithm for constructing a privacy-preserving global user profile through federated learning in a vertical data-segmentation scenario. Each participant has some of the characteristics of user data, they train the local clusters on their data using the CLIQUE algorithm, and carefully encrypt the cluster parameters using Paillier encryption to protect the cluster parameters from the untrusted aggregator. The aggregator then makes intersections over the cluster parameters without decryption to construct a global user profile. Finally, we conduct experiments on real datasets, and the results verify that the algorithm shows good performance in terms of precision and effectiveness.
    Keywords: differential privacy; federated learning; CLIQUE algorithm; encryption.

  • Parameter-free marginal Fisher analysis based on L2,1-norm regularisation for face recognition   Order a copy of this article
    by Yu'e Lin, Zhiyuan Ren, Xingzhu Liang, Shunxiang Zhang 
    Abstract: Marginal Fisher analysis is an effective feature extraction algorithm for face recognition, but the algorithm is sensitive to the influence of the neighbourhood parameter setting, and does not have the function of feature selection. In order to solve the above problems, this paper proposes a parameter-free marginal discriminant analysis based on L2,1-norm regularisation (PFMDA/L2,1). The algorithm calculates the weights using the cosine distance between samples and dynamically determines neighbours of each data point so that it doesn't set any parameters. In order to enable both feature extraction and feature selection to proceed simultaneously, two optimisation models with the L2,1-norm constraint are presented and then the complete solution for PFMDA/L2,1 is given. The experimental results on the ORL, YaleB and AR face databases show that the proposed method is feasible and effective.
    Keywords: marginal Fisher analysis; feature extraction; feature selection; parameter-free; L2,1-norm regularisation; cosine distance.

  • Research on credit risk evaluation of B2B platform supply chain financing enterprises based on improved TOPSIS   Order a copy of this article
    by Hong Zhang, Yuan Chen, Xiyue Yan, Han Deng 
    Abstract: This paper establishes a credit evaluation index system for B2B platform supply chain financing enterprises, which consists of four levels: B2B platform, supply chain financing enterprises, core enterprises and supply chain collaboration. Taking 24 samples of supply chain financing enterprises listed on GEM from six well-known B2B platforms in China as the research objects, the credit risk of supply chain financing enterprises on B2B platform is dynamically evaluated by using the improved TOPSIS method incorporating time dimension. The research shows that the strong comprehensive strength of core enterprises, close supply chain collaboration and good credit status of enterprises themselves have a favourable impact on the credit evaluation of supply chain financing of enterprises. A high-quality B2B platform is beneficial for enterprises to carry out supply chain financing and attract more high-quality supply chain enterprises to cooperate.
    Keywords: improved TOPSIS method; TOPSIS; B2B platform; supply chain financing; credit risk.

  • BITSAT: an efficient approach to modern image cryptography   Order a copy of this article
    by Sheel Sanghvi, Ramchandra Mangrulkar 
    Abstract: This paper proposes a new approach towards efficient image cryptography that works using the concepts of bit-plane decomposition and bit-level scrambling. This method does not require the involvement of additional or extra images. Users have the flexibility of choosing (1) any bit-plane decomposition method; (2) logic that runs the key generation block; (3) customisation in the bit-level permutations performed during scrambling. The implementation of the method is simple and free of heavily complex steps and operations. This makes the algorithm applicable in a real-world scenario. The BITSAT algorithm is applied to a variety of images and, consequently, the encrypted images generated showcase a high level of encryption. The analysis and evaluation of the algorithm and its security aspects are performed and described in detail. The paper also presents the application domains of the method. Overall, the results and analysis indicate a positive working scope and suitability for real-life applications.
    Keywords: hybrid image encryption; image cryptography; novel image encryption scheme; bit-level scrambling; bit-plane decomposition.

  • A GRU-based hybrid global stock price index forecasting model with group decision-making   Order a copy of this article
    by Jincheng Hu, Qingqing Chang, Siyu Yan 
    Abstract: To predict the global stock price index daily more effectively, this study develops a new filtering gate recurrent unit group-based decision-making (FiGRU_G) model that combines GRU group network and group decision-making strategy. This proposed FiGRU_G model can effectively overcome the shortcoming of traditional neural network algorithms that the random initialisation of network weights may cause worse performance to some extent. The experimental results indicate visually that the proposed FiGRU_G framework outperforms other competing methods in terms of prediction accuracy and robustness for both Chinese and international stock markets. In the short-term prediction scenario, the FiGRU_G framework achieves 20% and 19% performance improvements on evaluation criteria MAPE and SDAPE, respectively, compared with the GRU model in the Chinese stock market. For the international markets, this FiGRU_G framework also achieves 23% and 22% performance improvements, respectively, compared with the GRU model.
    Keywords: stock closing price prediction; deep learning; GRU model; group decision-making.
    DOI: 10.1504/IJCSE.2022.10047524
     
  • Patient reviews analysis using machine learning   Order a copy of this article
    by Bijayalaxmi Panda, Chhabi Rani Panigrahi, Bibudhendu Pati 
    Abstract: In the present situation, web technologies provide opportunities for online communication. Health-related tweets are available in online forums. Doctors and patients share their views in discussion forums that help other people seeking similar information. An investigation was performed on patient reviews collected from different forums regarding different diseases. These are unstructured to identify positive and negative tweets. The dataset collected from figshare identified several features from the text provided by patients into numerical forms. Specific features are selected from the dataset and machine learning classification algorithms, such as Support Vector Machine (SVM), Gaussian na
    Keywords: classification; support vector machine; Gaussian naïve Bayes; random forest; feature selection.

  • Parameter identification and SOC estimation for power battery based on multi-timescale double Kalman filter algorithm   Order a copy of this article
    by Likun Xing, Mingrui Zhan, Min Guo, Liuyi Ling 
    Abstract: Accurate modelling and state of charge (SOC) estimation are great significance to improve efficiency and extend service life of power batteries. A joint extended Kalman filter (EKF)-unscented Kalman filter (UKF) algorithm for online identification of battery model parameters and SOC estimation is proposed, in order to solve the problems of time-varying internal parameters resulting in inaccurate SOC estimation. Based on the second-order RC equivalent circuit model, UKF is used for online parameter identification at the macroscopic time scale, and EKF is used for estimating the lithium battery SOC at the microscopic time scale. The experimental results show that the mean absolute error (MAE) and root mean square error (RMSE) of SOC estimated are significantly reduced by the proposed method, respectively, compared with the conventional SOC estimation method which the parameters are identified off-line. The SOC estimation results demonstrate the accuracy and robustness of the joint EKF-UKF algorithm.
    Keywords: state of charge; multi-timescale; online parameter identification; double Kalman filter algorithm.

  • Multiple correlation based decision tree model for classification of software requirements   Order a copy of this article
    by Pratvina Talele, Rashmi Phalnikar 
    Abstract: Recent research in Requirements Engineering (RE) includes requirements classification, and use of Machine Learning (ML) algorithms to solve RE problems. The limitation of existing techniques is that they consider only one feature at a time to map the requirements without considering the correlation of two features and are biased. To understand these limitations, our study compares and extends the ML algorithms to classify requirements in terms of precision and accuracy. Our literature survey shows that decision tree (DT) algorithm can identify different requirements and outperforms existing ML algorithms. As the number of features increases, the accuracy using the DT is improved by 1.65%. To overcome the limitations of DT, we propose a Multiple Correlation Coefficient based DT algorithm. When compared with existing ML approaches, the results showed that the proposed algorithm can improve classification performance. The accuracy of the proposed algorithm is improved by 5.49% compared with the DT algorithm.
    Keywords: machine learning; requirements engineering; decision tree; multiple correlation coefficient.

  • Improved performance on tomato pest classification via transfer learning based deep convolutional neural network with regularisation techniques   Order a copy of this article
    by Gayatri Pattnaik, Vimal K. Shrivastava, K. Parvathi 
    Abstract: Insect pests are major threat to the quality and quantity of crop yield. Hence, early detection of pests using a fast, reliable and non-chemical method is essential to control the infestations. Hence, we have focused on tomato pest classification using pre-trained deep convolutional neural network (CNN) in this paper. Four models (VGG16, DenseNet121, DenseNet169, and Xception) were explored with transfer learning approach. In addition, we have adopted two regularization techniques viz. early stopping and data augmentation to prevent the model from overfitting and improve its generalization ability. Among four models, the DenseNet169 achieved highest classification accuracy of 95.23%. The promising result shows that the DenseNet169 model with transfer learning and regularization techniques can be used in agricultural for pest management.
    Keywords: agriculture; convolutional neural network; data augmentation; early stopping; pest; regularisation; tomato plants.

  • A collaborative filtering recommendation algorithm based on DeepWalk and self-attention   Order a copy of this article
    by Jiaming Guo, Hong Wen, Weihong Huang, Ce Yang 
    Abstract: Graph embedding is one of the vital technologies in solving the problem of information overload in recommendation systems. It can simplify the vector representations of items and accelerates the calculation process. Unfortunately, the recommendation system using graph embedding technology does not consider the deep relationships between items when it learns embedding vectors. In order to solve this problem, we propose a collaborative filtering recommendation algorithm based on DeepWalk and self-attention in this paper. This algorithm can enhance the accuracy in measuring the similarity between items and obtain more accurate embedding vectors. Chronological order and mutual information are used to construct a weighted directed relationship graph. Self-attention and DeepWalk are used to generate embedding vectors. Then item-based collaborative filtering is used to obtain recommended lists. The results of the relative experiments and evaluations on three public datasets show that our algorithm is better than the existing ones.
    Keywords: DeepWalk; self-attention; mutual information; collaborative filtering; recommendation algorithm.

  • A proxy signcryption scheme for secure sharing of industrial IoT data in fog environment   Order a copy of this article
    by Rachana Patil, Yogesh Patil 
    Abstract: Rapid technical advancements have transformed the industrial segment. The IIoT and Industry 4.0 comprise a complete instrumentation system that has sensors, positioners, actuators, instruments and processes. Owing to various delays and safety concerns, the industrial process necessitates that specified data be transferred across the internet. Considering this, fog computing is potentially helpful as a mediator, as it performs localised processing of data, so that may be applied to a variety of industrial applications. Furthermore, industrial big data is often required to be shared among different applications. Here, we proposed an ECC-based Proxy Signcryption for IIoT (ECC-PSC-IIoT) in a fog computing environment. The proposed scheme provides the features of signature and encryption in a single cycle. The ECC-PSC-IIoT system is proven to be secure by using the AVISPA tool. Moreover, extensive performance assessment indicates the competency of the proposed scheme with respect to computation and communication time.
    Keywords: IIoT; elliptic curve cryptography; signcryption; fog computing; proxy signature.

  • An aeronautic X-ray image security inspection network for rotation and occlusion   Order a copy of this article
    by Bingshan Su, Shiyong An, Xuezhuan Zhao, Jiguang Chen, Xiaoyu Li, Yuantao He 
    Abstract: Aviation security inspection needs lots of time and human labour. In this paper, we establish a new network for detecting prohibited objects in aeronautic security inspection X-ray images. Objects in the X-ray image often present rotated shapes and overlap heavily with each other. In order to solve the rotation and occlusion in X-ray image detection, we construct the De-rotation-and-occlusion Module (DROM), an efficient module that can be embedded into most deep learning detectors. Our DROM leverages the edge, colour and Oriented Fast and Rotated BRIEF (ORB) features to generate an integrated feature map, while the ORB features could be extracted quickly and diminish the deviation produced by rotation effectively. Finally, we evaluate DROM on the OPIXRay dataset; compared with several latest approaches, the experimental results certify that our module promotes the performance of Single Shot MultiBox Detector (SSD) and obtains higher accuracy, which proves the modules application value in practical security inspection.
    Keywords: X-ray image detection; de-rotation-and-occlusion; deep learning; ORB; SSD.

  • ReFIGG: retinal fundus image generation using generative adversarial networks   Order a copy of this article
    by Sharika Sasidharan Nair, M.S. Meharban 
    Abstract: The effective training of deep architectures mainly depends on a large number of well-explained data. This is a problem in the medical field where it is hard and costly to gain such images. The tiny blood-vessels of the retina are the only part of the human structure that can be directly and nonintrusively foreseen within the living person. Hence, it can be easily obtained and examined by automatic tools. Fundus imaging is a basic check-up process in ophthalmology that provides essential data to make it easier for doctors to detect various eye-related diseases at early stages. Fundus image generation is a challenging process to carry out by constructing composite models of the eye structure. In this paper, we overcome the issue of unavailability of medical fundus datasets by synthesising them artificially through an encoder-decoder generator model to the existing MCML method of generative adversarial networks for easier, quicker, and early analysis.
    Keywords: fundus image; generative adversarial networks; encoder-decoder model; image synthesis; deep learning.

  • CBSOACH: design of an efficient consortium blockchain-based selective ownership and access control model with vulnerability resistance using hybrid decision engine   Order a copy of this article
    by Kalyani Pampattiwar, Pallavi Vijay Chavan 
    Abstract: Cloud deployments are prone to vulnerabilities and attacks, mitigated via security patches. However, these patches increase the computational complexity of the deployments, thus reducing their quality-of-service performance. To overcome this limitation and maintain high-security levels, this text proposes the design of the CBSOACH model, which is a novel Consortium Blockchain-based Selective Ownership and Access Control model with vulnerability resistance using a Hybrid decision engine. The model introduces header-level pattern analysis, which processes all incoming traffic using a light-weight rule-based method. Header-level pattern analysis is backed by a consortium blockchain model that allows for efficient ownership control with minimum overheads. Owing to a combination of header-level pattern analysis with consortium blockchain, the model can maintain traceability, trustability, immutability, and distributed computing capabilities. The model can reduce attack probability while maintaining lower delay and high-efficiency ownership transfer. This increases the scalability and usability of the model for large-scale deployments.
    Keywords: cloud; ownership; blockchain; authentication; access control; consortium; attacks; accuracy; delay.

  • Blockchain-based secure deduplication against duplicate-faking attack in decentralized storage   Order a copy of this article
    by Jingkai Zhou, Guohua Tian, Jianghong Wei 
    Abstract: Secure client-side deduplication enables cloud server to efficiently save storage space and communication bandwidth without compromising privacy. However, the potential duplicate-faking attack (DFA) may cause data users to lose their outsourced data. Existing solutions can either only detect DFA and fail to avoid data loss, or have high storage costs. In this paper, we propose a blockchain-based secure deduplication scheme against DFA in decentralised storage. Specifically, we firstly proposed a client-side deduplication protocol, in which server does not need to store additional metadata to check subsequent uploaders, who only need to encrypt the challenged partial blocks instead of the entire file. Besides, we design a battle mechanism based on smart contract to protect users from losing data. When an uploader detects a DFA, he can apply for a battle with the previous uploader to achieve an effective punishment. Finally, security and performance analysis indicate the practicality of the proposed scheme.
    Keywords: secure data deduplication; duplicate-faking attack; proof of ownership; blockchain; smart contract.

  • Blockchain-based collaborative intrusion detection scheme   Order a copy of this article
    by Tianran Dang, Guohua Tian, Jianghong Wei, Shuqin Liu 
    Abstract: The collaborative intrusion detection technique is an effective solution to protect users from various cyber-attacks, among which the large-scale trusted sharing and real-time updating of attack instances are the main challenges. However, the existing collaborative intrusion detection systems (CIDS) either can only achieve real-time instance sharing in a centralised setting or implement large-scale instance sharing through blockchain. In this paper, we propose a novel blockchain-based CIDS scheme. Specifically, we present a reputation-based consensus protocol, which incentives service providers (SP) to evaluate the attack instances collected from collectors and punishes the malicious evaluators. Then, only trusted attack instances will be published on the blockchain to provide large-scale trusted intrusion detection services. Furthermore, we introduce a redactable blockchain technique to achieve dynamic instances update, which enables our scheme to provide a real-time intrusion detection service. Finally, we demonstrate the practicality of the proposed scheme through security analysis, theoretical analysis and performance evaluation.
    Keywords: collaborative intrusion detection; blockchain; reputation-based consensus; redactable blockchain.

  • Application of bagging and particle swarm optimisation techniques to predict technology sector stock prices in the era of the Covid-19 pandemic using the support vector regression method   Order a copy of this article
    by Heni Sulastri, Sheila Maulida Intani, Rianto Rianto 
    Abstract: The increase in positive cases of Covid-19 not only affects the health and lifestyle, but also the economy and the stock market. Tech and digital sector stocks can be predicted to be one of the most profitable. Therefore, the prediction of the stock price is required to be able to see how the prospects of investment in the future. In this study, the prediction of the stock prices of Multipolar Technologies Ltd (MLPT) was carried out using the Support Vector Regression (SVR) method with Bootstrap Aggregation (Bagging) Technique and Particle Swarm Optimisation (PSO) as SVR optimisation. From the results of the prediction process, it is shown that the application of bagging and PSO techniques in predicting stock prices in the technological sector can reduce the Root Mean Squared Error (RMSE) value on the SVR, the RMSE value from 22.142 to 21.833. Although it does not have a big impact, it is better to apply a combination of bagging and PSO techniques to SVR than one of them (SVR / SVR - PSO / SVR-bagging).
    Keywords: bootstraps aggregation; bagging; Covid-19; particle swarm optimisation; prediction; share prices; support vector regression.

  • Kidney diseases classification based on SONN and MLP-GA in ultrasound radiography images   Order a copy of this article
    by Anuradha Laishram, Khelchandra Thongam 
    Abstract: A strategy for robust classification of renal ultrasound images for the identification of three kidney disorders, renal calculus, cortical cyst, and hydronephrosis, has been attempted. Features were retrieved using the Intensity Histogram (IH), grey level co-occurrence matrices (GLCM), and grey level run length matrices (GLRLM) techniques. Using the extracted features, input samples are created and then fed to a hybrid model which is a combination of self-organising neural network (SONN) and multilayer perceptron (MLP) trained with a genetic algorithm (GA). Self-Organising Neural Network (SONN) is used to cluster the input patterns into four groups or clusters and finally, MLP using genetic algorithm is employed on each cluster to classify the input patterns. The proposed hybrid method using SONN and MLP-GA has more potential to classify the ultrasound images by achieving a precision of 93.9%, recall of 93.0%, F1 score of 93.0%, and overall accuracy of 96.8%.
    Keywords: genetic algorithm; grey level co-occurrence matrix; grey level run length matrix; intensity histogram; multilayer perceptron; self-organising neural network; ultrasound images.

  • LightNet: pruned sparsed convolutional neural network for image classification   Order a copy of this article
    by Edna Too 
    Abstract: Deep learning has become a most sought after approach in the area of Artificial intelligence (AI). However, deep learning models pose some challenges in the learning process. It is computationally intensive to train deep learning networks and also resource intensive. Therefore, it cannot be applied in limited resource devices. Limited research is being done on implementation of efficient approaches for real world problems. This study tries bridge the gaps towards an applicable system in real world, especially in the agricultural sector for plant disease management and fruit classification. We introduce a novel architecture called LightNet. LighNet is an architecture that employs two strategies to achieve sparsity of DenseNet: the skip connections and pruning strategy. The resultant is a small network with reduced parameters and model size. Experimental evaluation reveal that LightNet is more efficient that the DenseNet architecture. The model is evaluated on real world datasets PlantsVillage and Fruits-360.
    Keywords: image classification; deep learning; convolution neural network; LightNet; ConvNet.

  • Predicting possible antiviral drugs against COVID-19 based on Laplacian regularised least squares and similarity kernel fusion   Order a copy of this article
    by Xiaojun Zhang, Lan Yang, Hongbo Zhou 
    Abstract: COVID-19 has produced a severe impact on global health and wealth. Drug repurposing strategies provide effective ways for inhibiting COVID-19. In this manuscript, a drug repositioning-based virus-drug association prediction method, VDA-LRLSSKF, was developed to screen potential antiviral compounds against COVID-19. First, association profile similarity matrices of viruses and drugs are computed. Second, similarity kernel fusion model is presented to combine biological similarity and association profile similarity from viruses and drugs. Finally, a Laplacian regularised least squares method is used to compute the probability of association between each virus-drug pair. We compared VDA-LRLSSKF with four of the best VDA prediction methods. The experimental results and analysis demonstrate that VDA-LRLSSKF calculated better AUCs of 0.8286, 0.8404, 0.8882 on three datasets, respectively. VDA-LRLSSKF predicted that ribavirin and remdesivir could be underlying therapeutic clues for inhibiting COVID-19 and need further experimental validation.
    Keywords: SARS-CoV-2; VDA-LRLSSKF; drug repurposing; Laplacian regularised least squares; similarity kernel fusion.

  • A modified Brown and Gibson model for cloud service selection   Order a copy of this article
    by Munmun Saha, Sanjaya Kumar Panda, Suvasini Panigrahi 
    Abstract: Cloud computing has been widely accepted in the information technology (IT) industry as it provides on-demand services, lower operational and investment costs, scalability, and many more. Nowadays, small and medium enterprises (SMEs) use the cloud infrastructure for building their applications, which makes their business more agile by using elastic and flexible cloud services. Many cloud service providers (CSPs) have offered numerous services to their customers. However, owing to the vast availability of cloud services and the wide range of CSPs, decision-making for cloud selection or adopting cloud services is not consistently straightforward. This paper proposes a modified Brown and Gibson model (M-BGM) to select the best CSP. We consider both the subjective and objective criteria for the non-quantifiable and quantifiable values, respectively. Here, various decision-makers can express their views about the alternatives. We compare M-BGM with multi-attribute group decision-making (MAGDM) approach and perform a sensitivity analysis to show the robustness.
    Keywords: cloud computing; multi-criteria decision-making; quality of service; cloud service provider; Brown and Gibson model; analytic hierarchy process; Delphi method; decision maker.

  • Short-term load forecasting with bidirectional LSTM-attention based on the sparrow search optimisation algorithm   Order a copy of this article
    by Jiahao Wen, Zhijian Wang 
    Abstract: Short-term power load forecasting has always been a complex problem for distribution networks due to their insufficient accuracy and poor training effects. To solve this problem, a bidirectional long short-term memory (BILSTM) prediction model based on attention was proposed to process collected data, and the different observed data characteristics were divided through a pretreatment unit to obtain a training set and test set. The BILSTM layer was used for modelling to learn historical load data and daily feature data, enabling the extraction of the internal dynamic change rules of features. An attention mechanism was used to give different weights to the implied BILSTM states through mapping, weighting and parameter matrix learning, which reduced the loss of historical information and enhanced the influence of important information. The sparrow search (SS) algorithm was used to optimise the hyperparameter selection process of the model. The test results showed that the performance of the proposed method was better than that of the traditional prediction model, and the root mean square errors decreased by (1.18, 1.09, 0.60, 0.54) and (2.11, 0.45, 0.21, 0.11) on different datasets.
    Keywords: short-term load prediction; sparrow search algorithm; neural network; weight assignment; attention mechanism.

  • 3DL-PS: an image encryption technique using a 3D logistic map, hashing functions and pixel scrambling techniques   Order a copy of this article
    by Parth Kalkotwar, Rahil Kadakia, Ramchandra Mangrulkar 
    Abstract: With the advancement in technology over the years, the security of data transferred over the internet is a major concern. In this paper, a robust and efficient image encryption scheme has been implemented using a 3D logistic map, SHA-512, and pixel scrambling. A good image encryption scheme should be able to produce two drastically different encrypted images for two original images with minute differences. Chaotic systems have proved to be highly efficient in providing this property, mainly because of their high randomness and volatility depending on the initial conditions. A 3D logistic map can be preferred over a 1D Logistic map owing to its increased encryption complexity, enhanced security, and better chaotic properties. To start the process, two secret keys are generated using two different user-provided keys and the input image, which makes it resistant to classical attacks such as the chosen-plaintext attack and chosen ciphertext attack. Further, it is necessary to change the pixel values of the original image so that it becomes difficult to trace back the original image from the encrypted image. Pixels of the images are altered using the values obtained upon the iteration of the 3D logistic map. In addition to this, two different pixel scrambling techniques are employed to enhance security. Firstly, different fragments of varying sizes are swapped depending on the secret keys generated earlier. Finally, a jumbling technique is used to mix the pixels horizontally and vertically in a completely dynamic way depending on the secret keys. The keyspace of the algorithm is found to be large enough to resist brute force attacks. The encrypted image has been observed and analysed against several attacks such as classical attacks, statistical attacks, and noise resistance. Key sensitivity analysis has also been performed. The results prove that the 3DL-PS algorithm is found to be resistant to several well-known attacks, providing an efficient image encryption scheme that can be used in various real-time applications.
    Keywords: image cryptography; chaotic systems; pixel scrambling; SHA-512; security analysis; classical attacks; 3D logistic map; noise resistance.

  • Hybrid grasshopper and ant lion algorithms to improve imperceptibility, robustness and convergence rate for the video steganography   Order a copy of this article
    by Sahil Gupta, Naresh Kumar Garg 
    Abstract: The need for securing multimedia content from being intercepted is a prominent research issue. This work proposes an optimised video steganography model that improves imperceptibility and robustness by extracting keyframes and calculating the optimal scaling factor. The Squirrel Search Algorithm (SSA) is used to extract keyframes since it ensures distinct position updation processes through Levy flying and predator features, whilst the grasshopper optimisation and ant lion optimisation algorithms are hybridised to compute the optimal value of the scaling factor. In terms of imperceptibility and robustness, the simulation results suggest that the proposed approach outperforms existing data-hiding models. It also discovers the optimal scaling factor in under 10 iterations, indicating that the fastest convergence rate is possible.
    Keywords: ant-lion optimisation; grasshopper optimisation; SVD; video steganography; impercepbility; robustness; PSNR; MSE.

  • Human behaviour analysis based on spatio-temporal dual-stream heterogeneous convolutional neural network   Order a copy of this article
    by Qing Ye, Yuqi Zhao, Haoxin Zhong 
    Abstract: At present, there are still many problems to be solved in human behaviour analysis, such as insufficient use of behaviour characteristic information and slow operation rate. We propose a human behaviour analysis algorithm based on spatio-temporal dual-stream heterogeneous convolutional neural network (STDNet). The algorithm improves on the basic structure of the traditional dual-stream network. When extracting spatial information, the DenseNet uses a hierarchical connection method to construct a dense network to extract the spatial feature of the video RGB image. When extracting motion information, BNInception is used to extract temporal features of video optical flow images. Finally, feature fusion is carried out by multi-layer perceptron and sent to Softmax classifier for classification. Experimental results on the UCF101 data set show that the algorithm can effectively use the spatio-temporal feature information in video, reduce the amount of calculation of the network model, and greatly improve the ability to distinguish similar actions.
    Keywords: human behaviour analysis; STDNet; optical flow; feature extraction; dual-stream network.

  • High-volume transaction processing in bitcoin lightning network on blockchains   Order a copy of this article
    by Rashmi P. Sarode, Divij Singh, Yutaka Watanobe, Subhash Bhalla 
    Abstract: Transactions on e-commerce platforms using blockchain technology are required to face a high volume of executing transactions. These systems are required to be scalable. Bitcoin Lightning Network (BLN) can execute high volumes of transactions and is scalable due to few hops in the network. It is an off-chain payment channel built on top of a blockchain which speeds up the transactions. In this paper, we discuss BLN along with its transaction processing in detail, its benefits and applications. Additionally, we discuss alternative networks for payments. We also propose a secure model on BLN that can be used for any e-commerce platform and compare it with existing applications such as that of Ethereum and Stellar.
    Keywords: lightning network; bitcoin; cryptocurrency; blockchain; Ethereum.

  • Data augmentation using fast converging CIELAB-GAN for efficient deep learning dataset generation   Order a copy of this article
    by Amin Fadaeddini, Babak Majidi, Alireza Souri, Mohammad Eshghi 
    Abstract: The commercial deep learning applications require large training datasets with many samples from different classes. The Generative Adversarial Networks (GAN) are able to create new data samples for training these machine learning models. However, the low speed of training these GANs in image and multimedia applications is a major constraint. In order to address this problem, in this paper a fast converging GAN called CIELAB-GAN for synthesizing new data samples for image data augmentation is proposed. The CIELAB-GAN simplifies the training process of GANs by transforming the images to the CIELAB colour space with fewer parameters. Then, the CIELAB-GAN translates the generated greyscale images into colourized samples using an autoencoder. The experimental results show that the CIELAB-GAN has lower computational complexity of 20% compared to the state of the art GAN models and is able to be trained substantially faster. The proposed CIELAB-GAN can be used for generating new image samples for various deep learning applications.
    Keywords: generative adversarial networks; deep learning; data augmentation; image processing.

  • Aerial remote sensing image registration based on dense residual network of asymmetric convolution   Order a copy of this article
    by Ying Chen, Wencheng Zhang, Wei Wang, Jiahao Wang, Xianjing Li, Qi Zhang, Yanjiao Shi 
    Abstract: The existing image registration frameworks pay less attention to important local feature information and part of global feature information, resulting in low registration accuracy. However, asymmetric convolution and dense connection can pay more attention to the key information and shallow information of the image. Therefore, this paper propose a novel feature extraction module to improve the feature extraction ability and registration accuracy of the model. Asymmetric convolution and dense connection are used to improve the residual structure to focus on both local and global information in the feature extraction stage. In the feature matching stage, bidirectional matching is used to alleviate asymmetric matching results by fusing two outcomes. Furthermore, a secondary affine transformation is proposed to estimate the real transformation between two images adequately. In contrast with several popular algorithms, the proposed method has a better registration effect on two public datasets, which has practical significance.
    Keywords: remote sensing image registration; residual network; asymmetric convolution; dense connection; transfer learning; regularization; affine transformation.

  • Non-parametric combination forecasting methods with application to GDP forecasting   Order a copy of this article
    by Wei Li, Yunyan Wang 
    Abstract: This work is devoted to constructing non-parametric combination prediction method, which can improve the forecasting effect and accuracy to some extent. In this paper, in order to forecast the regional gross domestic product, non-parametric autoregressive method is introduced into the autoregressive integrated moving average model, and a combined method of ARIMA model and non-parametric autoregressive model is established based on the residual correction. Furthermore, the specific prediction steps are proposed. The empirical results show that the new proposed combined model outperforms both the ARIMA model and the non-parametric autoregressive model in terms of regression effect and forecasting accuracy. The combination of parametric model and non-parametric model not only provides a method with better applicability and prediction effect for the establishment of GDP prediction model, but also provides a theoretical basis for the prediction of relevant economic data in the future. The prediction results show that during the Chinas 14th Five-Year Plan period, the gross domestic product of Jiangxi Province will increase by 7.01% annually.
    Keywords: GDP; ARIMA model; non-parametric autoregressive model; residual correction; combined model.

  • Comparative study of point matching method with spectral method on numerical solution electromagnetic problems   Order a copy of this article
    by Mahmoud Behroozifar 
    Abstract: The present study focuses on comparing the point matching method and spectral method for solving the integral equations arising in the electromagnetic domain. The point matching method, which is a traditional method, was based on basis functions which most of the time results in a singular and ill-posed system of nonlinear equations. In order to prevent these inconveniences, the physical structure of the object must be altered in some cases this yields a high error in the results and requires high CPU time and memory usage. Also in most cases, this method converges slowly and leads a singular and ill-posed system. Consequently, applying the point matching method for this problem causes to obtain an approximate solution with low accuracy and high computation volume. As an alternative, we present the spectral method based on Bernstein polynomials (BPs) as a robust nominee. Employing the BPs reduces the problem to an algebraic equations system. The other merits of the presented method are faster convergence and avoidance of occurring a singular system.
    Keywords: Bernstein polynomials; electrostatic; micro strip; point matching method; spectral method.

  • RCRE: radical-aware causal relationship extraction model oriented in the medical field   Order a copy of this article
    by Xiaoqing Li, Guangli Zhu, Zhongliang Wei, Shunxiang Zhang 
    Abstract: In the massive medical texts, the accuracy of causal relationship extraction is relatively low because of its special characteristic, a high correlation between semantics and radicals. To improve the extraction accuracy, this paper proposes a radical-aware causal relationship extraction model, which is oriented to the medical field. The BERT pre-training model is used to extract character-level features, which contain rich context information. To further deeply capture the semantics of characters, the Word2Vec model is used to extract radical features. Finally, the above two features are concatenated and passed into the extraction model to obtain the extraction results. Experimental results show that the proposed model can improve the accuracy of causal relationship extraction in medical texts.
    Keywords: causal relationship extraction; the medical field; radical features; BERT model; Word2Vec model.

Special Issue on: CCPI'20 Smart Cloud Applications, Services and Technologies

  • A big data and cloud computing model architecture for a multi-class travel demand estimation through traffic measures: a real case application in Italy   Order a copy of this article
    by Armando Cartenì, Ilaria Henke, Assunta Errico, Marida Di Bartolomeo 
    Abstract: The big data and cloud computing are an extraordinary opportunity to implement multipurpose smart applications for the management and the control of transport systems. The aim of this paper is to propose a big data and cloud computing model architecture for a multi-class origin-destination demand estimation based on the application of a bi-level transport algorithm using traffic counts on a congested network, also to propose sustainable policies at urban scale. The proposed methodology has been applied to a real case study in terms of travel demand estimation within the city of Naples (Italy), also aiming to verify the effectiveness of a sustainable policy in term of reducing traffic congestion by about 20% through en-route travel information. The obtained results, although preliminary, suggest the usefulness of the proposed methodology in terms of ability in real time/pre-fixed time periods to estimate traffic demand.
    Keywords: cloud computing; big data; virtualisation; smart city; internet of things; transportation planning; demand estimation; sustainable mobility; simulation model.

  • A methodology for introducing an energy-efficient component within the rail infrastructure access charges in Italy   Order a copy of this article
    by Marilisa Botte, Ilaria Tufano, Luca D'Acierno 
    Abstract: After the separation of rail infrastructure managers from rail service operators occurred within the European Union in 1991, the necessity of defining an access charge framework for ensuring non-discriminatory access to the rail market arose. Basically, it has to guarantee an economic balance for infrastructure manager accounts. Currently, in the Italian context, access charge schemes neglect the actual energy-consumption of rail operators and related costs of energy traction for infrastructure managers. Therefore, we propose a methodology, integrating cloud-based tasks and simulation tools, for including such an aspect within the infrastructure toll, thus making the system more sustainable. Finally, to show the feasibility of the proposed approach, it has been applied to an Italian real rail context, i.e. the Rome-Naples high-speed railway line. Results have shown that customising the tool access charges, by considering the power supply required, may generate a virtuous loop with an increase in energy-efficiency of rail systems.
    Keywords: cloud-based applications; rail infrastructure access charges; environmental component; energy-saving policies.

  • Edge analytics on resource-constrained devices   Order a copy of this article
    by Sean Savitz, Charith Perera, Omer Rana 
    Abstract: Video and image cameras have become an important type of sensor within the Internet of Things (IoT) sensing ecosystem. Camera sensors can measure our environment at high precision, providing the basis for detecting more complex phenomena in comparison with other sensors e.g. temperature or humidity. This comes at a high computational cost on the CPU, memory and storage resources, and requires consideration of various deployment constraints, such as lighting and height of camera placement. Using benchmarks, this work evaluates object classification on resource-constrained devices, focusing on video feeds from IoT cameras. The models that have been used in this research include MobileNetV1, MobileNetV2 and Faster R-CNN, which can be combined with regression models for precise object localisation. We compare the models by using their accuracy for classifying objects and the demand they impose on the computational resources of a Raspberry Pi.
    Keywords: internet of things; edge computing; edge analytics; resource-constrained devices; camera sensing; deep learning; object detection.

  • Traffic control strategies based on internet of vehicles architectures for smart traffic management: centralised vs decentralised approach   Order a copy of this article
    by Houda Oulha, Roberta Di Pace, Rachid Ouafi, Stefano De Luca 
    Abstract: In order to reduce traffic congestion, real-time traffic control is one of the most widely adopted strategies. However, the effectiveness of this approach is constrained not only by the adopted framework but also by data. Indeed, the computational complexity may significantly affect this kind of application, thus the trade-off between the effectiveness and the efficiency must be analysed. In this context, the most appropriate traffic control strategy to be adopted must be accurately evaluated. In general, there are three main control approaches in the literature: centralised control, decentralised control and distributed control, which is an intermediate approach. In this paper, the effectiveness of a centralised and a decentralised approach is compared and applied to two network layouts. The results, evaluated not only in terms of performance index with reference to the network total delay but also in terms of emissions and fuel consumption, highlight that the considered centralised approach outperforms the adopted decentralised one and this is particularly evident in the case of more complex layouts.
    Keywords: cloud computing; internet of vehicles; transportation; centralised control; decentralised control; emissions; fuel consumption.

  • ACSmI: a solution to address the challenges of cloud services federation and monitoring towards the cloud continuum   Order a copy of this article
    by Juncal Alonso, Maider Huarte, Leire Orue-Echevarria 
    Abstract: The evolution of cloud computing has changed the way in which cloud service providers offer their services and how cloud customers consume them, moving towards the usage of multiple cloud services, in what is called multi-cloud. Multi-cloud is gaining interest by the expansion of IoT, edge computing and the cloud continuum, where distributed cloud federation models are necessary for effective application deployment and operation. This work presents ACSmI (Advanced Cloud Service Meta-Intermediator), a solution that implements a cloud federation, supporting the seamless brokerage of cloud services. Technical details addressing the discovered shortcomings are presented, including a proof of concept built on JHipster, Java, InfluxD, Telegraf and Grafana. ACSmI contributes to relevant elements of the European Gaia-X initiative, specifically to the federated catalogue, continuous monitoring, and certification of services. The experiments show that the proposed solution effectively saves up to 75% of the DevOps teams effort to discover, contract and monitor cloud services.
    Keywords: cloud service broker; cloud services federation; cloud services brokerage; cloud services intermediation; hybrid cloud; cloud service monitoring; multi-cloud; DevOps; cloud service level agreement; cloud service discovery; multi-cloud service management; cloud continuum.

  • User perception and economic analysis of an e-mobility service: development of an electric bus service in Naples, Italy   Order a copy of this article
    by Ilaria Henke, Assunta Errico, Luigi Di Francesco 
    Abstract: Among the sustainable mobility policies, electric mobility seems to be one of the best choices to reach sustainable goals, but it has limits that could be partially exceeded in the local public transport. This research presents a methodology to design a new sustainable public transport service that meets users needs by analysing economic feasibility. This methodology is then applied to a real case study: renewing an 'old' bus fleet with an electric one charged by a photovoltaic system in the city of Naples (Southern Italy). Its effects on users' mobility choices were assessed through a mobility survey. The bus line and the photovoltaic system were designed. Finally, the economic feasibility of the project was assessed through a cost-benefit analysis. This research is placed in the field of smart mobility and new technologies that increasingly need to store, manage, and process large amounts of data typical of cloud computing and big data applications
    Keywords: e-mobility; electric bus services; cloud computing; user perception; economic analysis; cost-benefit analysis; photovoltaic system; sustainable mobility policies; sustainable goals; new technologies; local emissions; environmental impacts.

Special Issue on: Intelligent Self-Learning Algorithms with Deep Embedded Clustering

  • Application of virtual numerical control technology in cam processing   Order a copy of this article
    by Linjun Li 
    Abstract: Numerical control (NC) machining is an important processing method in the machinery manufacturing industry. In most cases, as the final processing procedure, NC machining directly determines the quality of the finished product. As the key components needed in many industries such as automobile, internal combustion engine, national defense and so on, the precision and efficiency of the cam processing have a direct impact on the quality, life and energy saving standard of the engine and related products. This paper takes the cam NC grinding machining as the research object, takes the optimisation and intelligentisation of processing technology as the goal and uses the virtual NC technology to develop a process intelligent optimisation and NC machining software platform specifically for cam NC grinding machining. The software platform has machine tool library, grinding wheel library, material library, coolant reservoir library, process accessory library and other basic technology libraries, and it also has process example library, meta-knowledge rule library, forecast model library and other process intelligent libraries. With the support of database, the software platform can realise intelligent optimisation and automatic NC machining programming of cam grinding process plan. Because the software platform involves many research contents, this paper mainly focuses on the modelling of the motion process of the NC machining process system, the architecture of the intelligent platform software of the cam NC machining, and the virtual NC machining simulation of the process system. Therefore, the study of this paper is of great significance.
    Keywords: cam grinding; numerical control grinding; intelligent platform software; process problems; virtual grinding.

  • Research on oil painting effect based on image edge numerical analysis   Order a copy of this article
    by Yansong Zhang 
    Abstract: With the continuous development of the technology of non-photorealistic rendering, the effect of oil painting on image is increasing. The traditional oil painting effect is not satisfactory enough to satisfy people's needs. Therefore, this paper puts forward the research of oil painting effect based on image edge numerical analysis, and constructs a corresponding algorithm for image edge numerical analysis and detection. Through the comparison experiment with traditional algorithm oil painting results, the conclusion is drawn that the algorithm proposed in this paper can accurately analyse and detect the image edge, and the final rendering effect is more natural and more smooth than the traditional algorithm oil painting effect.
    Keywords: image; edge value; analysis; oil painting effect.

  • Research on multimedia and interactive teaching model of college English   Order a copy of this article
    by Zhang Juan 
    Abstract: Since the current higher education focuses on cultivating comprehensive practical ability rather than simply inculcating theoretical ideas, English should be adopted from the aspects of teaching purpose, teaching content and teaching strategy. A multiple interactive English teaching model is constructed to improve the information of a constructed method. Spatial reconstruction is used to extract and retrieve the information of multiple teaching resources, optimise and control the allocation of resources under the condition of load balance, and construct the data-mining model of College English teaching resources in the environment of information technology. With the result of information processing, optimised to maximise enthusiasm and creativity of the teachers and students, to continue the development of multimedia network resources and create a multiple interactive teaching environment, so as to create a platform for students.
    Keywords: information technology environment; college English; multiple interactive teaching mode;.

  • Design and application of system platform in piano teaching based on feature comparison   Order a copy of this article
    by Tingting Rao 
    Abstract: Traditional piano teaching is managed mainly by hand, but there are low management efficiency, management confusion and other problems, seriously restricting the development of piano teaching activities. In order to make up for the limitations of piano music teaching materials and the shortage of music teachers in some areas, the automatic score of computer is introduced into music learning, and a set of piano music singing and singing system based on characteristic comparison is developed. The difference between the score system and the existing commercial music scoring system on the internet lies in the educational orientation of the system, which is mainly reflected in the design and implementation of the feedback evaluation module. The system uses melody feature extraction, similarity comparison and pitch data analysis to perform the automatic singing score, locate the error position, estimate the cause of the error and give the learners detailed feedback and guidance suggestions. The application case study shows that the system has practical application value.
    Keywords: piano music teaching material; similarity comparison; learning feedback.

Special Issue on: SIRS'20 Intelligent Recognition Techniques and Applications

  • A deep learning approach for detecting the behaviour of people having personality disorders towards Covid-19 from Twitter   Order a copy of this article
    by Mourad Ellouze, Seifeddine Mechti, Moez Krichen, Vinayakumar Ravi, Lamia Hadrich Belguith 
    Abstract: This paper proposes an architecture taking advantage of artificial intelligence and text mining techniques in order to: (i) detect paranoid people by classifying their set of tweets into two classes (paranoid/not-paranoid), (ii) ensure the surveillance of these people by classifying their tweets about Covid-19 into two classes (person with normal behaviour/person with inappropriate behaviour). These objectives are achieved using an approach that takes advantage of different information related to the textual part, user and tweets for feature selection task and deep neural network for the classification task. We obtained an F-score rate of 70% for the detection of paranoid people and 73% for the detection of the behaviour of these people towards Covid-19. The obtained results are motivating and encouraging researchers to improve them given the interest and the importance of this research axis.
    Keywords: Covid-19; personality disorder; text mining; natural language processing; deep learning; Twitter.

  • A content-based image retrieval scheme with object detection and quantised colour histogram   Order a copy of this article
    by Yuvaraj Tankala, Joseph K. Paul, Manikandan V M 
    Abstract: Content-based image retrieval (CBIR) is an active area of research due to its wide applications. Most of the existing CBIR schemes are concentrated to do the searching of the images based on the texture, colour, or shape features extracted from the query image. In this manuscript, we propose an object detection based CBIR scheme with quantised colour histograms. In the proposed scheme, the meaningful objects will be identified from the query image by using you only look once (YOLO) object detection techniques and the quantised histograms of each of the object categories. The object lists, their count, and the area covered by the objects along with quantised colour histograms will be used during feature matching to retrieve the related images from the large image pool. The experiment of the proposed scheme is performed on the Corel 1K and Caltech image dataset. We have observed an average precision of 0.96 during the experimental study, which is quite high compared with the precision from the well-known existing schemes.
    Keywords: content-based image retrieval; object detection; colour histogram; you look only once; feature extraction;.

  • Offline Arabic handwritten character recognition: from conventional machine learning system to deep learning approaches   Order a copy of this article
    by Soumia Faouci, Djamel Gaceb 
    Abstract: Researchers have made great strides in the area of Arabic handwritten character recognition in the last decades, especially with the fast development of deep learning algorithms. The characteristics of Arabic manuscript text pose several problems for a recognition system. This paper presents a conventional machine learning system based on the extraction of a set of preselected features and an SVM classifier. In the second part, a simplified Convolutional Neural Network (CNN) model is proposed, which is compared with six other CNN models based on the pre-trained architectures. The suggested methods were tested using three databases: two versions of the OIHACDB dataset and the AIA9K dataset. The experimental results show that the proposed CNN model obtained promising results, as it is able to recognise 94.7%, 98.3%, and 95.6% of the test set of the three databases OIHACDB-28, OIHACDB-40, and AIA9K, respectively.
    Keywords: deep learning; convolutional neural network; Arabic handwritten character recognition; machine learning; support vector machine; transfer learning; features extractor; fine tuning.

  • Understanding the nonlinear dynamics of seizure and sleep EEG patterns generated using hierarchical chaotic neuronal network   Order a copy of this article
    by Sunitha Ramachandran, A. Sreedevi 
    Abstract: The purpose of this article is to describe how a chaotic biological neural network based on a mammalian olfactory system can be used to generate EEG patterns during seizures, REM and NREM sleep. The parameters governing the connection between each node at each layer of an olfactory system's K3 topology have been tuned to replicate low and high dimensional activities as well as periodic bursts matching to distinct brain states. The chaotic qualities of the simulated time series are evaluated against practical recordings of EEG patterns generated during distinct brain states by computing Hurst exponent, fractal dimension, and detrended fluctuation analysis. Our findings contribute to a better understanding of the complex cognitive tasks involved in various functional stages of the brain, as well as to the modelling of these activities using a biologically plausible hierarchical network of neurons.
    Keywords: mammalian olfactory system; chaotic biological neuronal network; EEG; epilepsy; REM; NREM; power spectrum; fractal dimension; Hurst exponent; detrended fluctuation analysis.
    DOI: 10.1504/IJCSE.2022.10045460
     
  • Analysis of the dynamics of the olfactory evoked EEG responses generated by the brain and E-nose under natural and synthetic odorant stimulations   Order a copy of this article
    by R. Sunitha, Suma Sri Sravya Chandu, A. Sreedevi 
    Abstract: Aroma and taste have a disproportionately strong effect on the human brain in comparison to the other senses. However, this effect is mostly unappreciated. The capacity for olfaction to perceive, identify and distinguish a vast number of chemicals present in the air is the consequence of complicated interactions between receptors, smell molecules, and the brain. The purpose of this article is to investigate and comprehend those complex interactions through the analysis of EEG signals recorded in response to a variety of natural and synthetic odorants administered to the mammalian olfactory system. Additionally, a prototype of a portable electronic nose (E-nose) was built, which consists of a sensor array and an Arduino microcontroller running an implementation of Freeman's KIII olfactory model. The sensor array's output is sent to the microcontroller, which generates EEG signals specific to the odorant stimuli applied. The EEG signal generated by the E-nose is then compared with EEG signals gathered from humans in terms of multiscale entropy and fractal dimension, highlighting the E-nose model's efficiency.
    Keywords: brain; electroencephalograph; E-nose; KIII model; olfaction; multiscale entropy; fractal dimension.
    DOI: 10.1504/IJCSE.2022.10045290
     
  • Coordinated control of PI-type PSS and MISO PI-type SSSC based damping controller design using improved grasshopper optimisation algorithm (IGOA)   Order a copy of this article
    by Sangram Mohapatra, Asit Patra 
    Abstract: This article presents the coordinated control of proportional integral type power system stabiliser (PI type-PSS) and the newly proposed multi-input single output based (MISO) damping controller using SSSC-based PI type lead lag controller for transient stability analysis. The Improved Grasshopper Optimisation Algorithm (IGOA) is employed in the coordinated controller design problem to find out the optimal controller parameters of single machine infinite bus (SMIB) and multi machine bus power system. A PI-type PSS with the proposed SSSC controller is analysed to show that the IGOA has satisfactory performance for optimisation problems compared with Grasshopper Optimization Algorithm (GOA), Differential Evolution (DE), Particle Swarm Optimization (PSO) techniques. The anticipated design approach of dynamic simulation results is analysed to explain the effectiveness and robustness of the power system. It is verified that a coordinated control of PI-type PSS with SSSC-based PI-type MISO controller has superior damping performance compared with individual remote speed deviation and line active power-based input signal-based PI-type PSS with PI-type SSSC controller in single and multi-machine power systems.
    Keywords: transient stability; improved grasshopper optimisation algorithm; static synchronous series compensator; PI-type MISO controller; PI-type PSS; multi machine power system.

  • Prediction of heart disease using hybrid optimisation techniques in data clustering   Order a copy of this article
    by Amolkumar N. Jadhav, Mukund B. Wagh, N. Gomathi 
    Abstract: The disease diagnosis in the medical field enhances better medical service to patients and also leads to a decrease in their mortality rate. The prediction of the survival rate of the patients purely depends on the accurate diagnosis of the diseases, but still, it is a major challenge to the physicians as well as to medical domains. Besides, several researchers have experimented related to the prediction and classification of heart diseases, but they are ineffective in providing accurate results. In this research, the performance analysis of the optimal clustering algorithm-based real-world heart dataset is carried out with the developed clustering methods. Here, three developed methods, such as kernel-based exponential grey wolf optimisation, enhanced kernel-based exponential grey wolf optimisation, and whale grey clustering algorithm obtained better performance and provide accurate results about the diagnosis of diseases. Moreover, the performance analysis is done by considering the evaluation metrics such as the Jaccard coefficient, F-measure, MSE, and Rand coefficient.
    Keywords: data clustering; disease diagnosis; medical image processing; grey wolf optimisation; kernel-based grey wolf optimiser.