Forthcoming and Online First Articles

International Journal of Computer Applications in Technology

International Journal of Computer Applications in Technology (IJCAT)

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 Articles will not be published until the final proofs are validated by their authors.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 Computer Applications in Technology (21 papers in press)

Regular Issues

  • FPGA implementation and Multisim simulation of a new four-dimensional two-scroll hyperchaotic system with coexisting attractors   Order a copy of this article
    by Sundarapandian Vaidyanathan, Esteban Tlelo-Cuautle, Khaled Benkouider, Aceng Sambas, Ciro Fabian Bermudez-Marquez, Samy Abdelwahab Safaan 
    Abstract: Field-programmable gate array (FPGA) design of a new four-dimensional two-scroll hyperchaotic system is investigated in this work. A detailed system modelling of the new system with a hyperchaotic attractor begins this work with phase plots, which is followed by a bifurcation study of the new system. Special dynamic properties such as multistability and symmetry are also investigated for the new system. Using Multisim software, a circuit model is designed and simulated for the new hyperchaotic system. FPGA design and Multisim simulation of the new system enable practical applications in science and engineering. The implementation of the FPGA design in this work is carried out by applying two numerical schemes, viz. Forward Euler and Trapezoidal methods. Experimental attractors observed in the oscilloscope show good match with the Matlab signal plots.The FPGA hardware resources are detailed for both numerical methods.
    Keywords: hyperchaos; bifurcation; symmetry; phase plots; hyperchaotic system;rnparameters; stability; multistability; circuit model; FPGA implementation.

  • Improving hybrid-layer convolutional neural network system for lung cancer nodule classification using enhanced weight optimisation algorithm   Order a copy of this article
    by Vikul Pawar, P. Premchand 
    Abstract: In recent times, lung cancer is evolving as a highly life-threatening disease for human beings. According to the WHO, lung cancer disease is the second largest cause of deaths as compared to all other types of cancer. The prevailing available technology is striving to get more exposure in the field of medical science using Computer Assisted Diagnosis (CAD), where image processing is playing a crucial role for detecting the cancerous nodules in computer tomographic images. Augmenting the machine learning techniques with image processing algorithms is becoming a more comprehensive examination of cancer disease in proposed CAD systems. This paper is describes a heuristic approach for lung cancer nodule detection, and the proposed model predominantly consists of the following tasks, which are image enhancement, segmenting ROI (Region of Interest), features extraction, and nodule classification. In pre-processing, primarily the Adaptive Median Filter (AMF) filtering method is applied to eliminate the speckle noise from input CT images of Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): in the LIDC-IDRI dataset, the quality of input image is improved by applying Histogram Equalization (HE) technique with Contrast-Limited Adaptive (CLA) approach. Secondly, in the successive stage the Improved Level-Set (ILS) algorithm is used to segment the ROI. Furthermore, the third step of the projected work is applied to extract the definite learnable texture features and statistical features from the segmented ROI. The extracted features in the subsequent stage of classification are applied to Hybrid-Layer Convolutional Neural Network (HL-CNN) architecture to classify the lung cancer nodule as either benign or malignant. Principally this research is carried out by contributing to each stage of it, where the novel concept of the improved Hybrid-Layer Convolutional Neural Network (HL-CNN) is employed by optimising and selecting the optimal weight using the Enhanced Cat Swarm Optimisation (ECSO) algorithm. The experimental result of the proposed HL-CNN using the weight optimisation algorithm ECSO is achieved an accuracy of 93%, which is comparatively efficient with respect to existing models such as DBN, SVM, CNN, WOA, MFO, and CSO. Moreover, the proposed model conclusively gives a decision on the detected nodule as either benign or malignant.
    Keywords: Computer Assisted Diagnosis (CAD); Computer Vision; Cancer Diagnosis; Image Classification; Image Enhancement; Image Segmentation; Feature Extraction.

  • Prediction model for total amount of coke oven gas generation based on FCM-RBF   Order a copy of this article
    by Lili Feng, Jun Peng, Zhaojun Huang 
    Abstract: The rational use of Coke Oven Gas (COG) is of great significance to improve the economic efficiency of enterprises. In this paper, a COG generation prediction model based on fuzzy C-mean clustering (FCM) and radial basis function (RBF) neural network is proposed to address the problems such as the difficulty of accurate modelling of COG generation process and the difficulty of real-time flow prediction. Firstly, the coke oven production process is analysed and correlation analysis is used to select the influencing factors. Secondly, the FCM is used to classify the working conditions of the coke oven, and the appropriate number of working conditions is selected through experiments. Finally, the prediction models under different working conditions are established separately by using RBF. The experiments were carried out using actual industrial production data, and the experimental results showed that the model could provide guidance reference for the dispatchers.
    Keywords: coking oven process; fuzzy C-means clustering; prediction model; radial basis function neural network.

  • Intelligent traffic congestion discrimination method based on wireless sensor network front-end data acquisition   Order a copy of this article
    by Maokai Lai 
    Abstract: Conventional intelligent traffic congestion discrimination methods mainly use GPS terminals to collect traffic congestion data, which is vulnerable to the influence of vehicle time distribution, resulting in poor final discrimination effect. Necessary to design a new intelligent traffic congestion discrimination method based on wireless sensor network front-end data collection. That is to use the front-end data acquisition technology of wireless sensor network to generate a front-end data acquisition platform to obtain intelligent traffic congestion data, and then design an intelligent traffic congestion discrimination algorithm based on traffic congestion rules so as to achieve intelligent traffic congestion discrimination. The experimental results show that the intelligent traffic congestion discrimination method designed based on the front-end data collection of wireless sensor network has good discrimination effect, the obtained discrimination data is more accurate, effective, and has certain application value, which has made certain contributions to reducing the frequency of urban traffic accidents.
    Keywords: wireless sensor network; front-end; Data acquisition; transportation; intelligence; traffic jam; traffic congestion data.
    DOI: 10.1504/IJCAT.2023.10059521
     
  • Unsupervised VAD method based on short time energy and spectral centroid in Arabic speech case   Order a copy of this article
    by Hind Ait Mait, Noureddine Aboutabit 
    Abstract: Voice Activity Detection (VAD) distinguishes speech segments from noise or silence areas. An efficient and noise-robust VAD system can be widely used for emerging speech technologies such as wireless communication and speech recognition. In this paper, we propose two versions of an unsupervised Arabic VAD method based on the combination of the Short-Time Energy (STE) and the Spectral Centroid (SC) features for formulating a typical threshold to detect the speech areas. The first version compares only the STE feature to the threshold (STE-VAD). In contrast, the second compares the SC vector and the threshold (SC-VAD). The two versions of our VAD method were tested on 770 sentences of the Arabphone corpus, which were recorded in clean and noisy environments and evaluated under different values of Signal-to-Noise-Ratio. The experiments demonstrated the robustness of the STE-VAD in terms of accuracy and Mean Square Error.
    Keywords: VAD; Arabic speech; voiced segment; unvoiced segment; STE; SC; MSE; Accuracy.
    DOI: 10.1504/IJCAT.2023.10061438
     
  • Bi-LSTM GRU-based deep learning architecture for export trade forecasting   Order a copy of this article
    by Vaishali Gupta 
    Abstract: To assess a country's economic outlook and achieve higher economic growth, econometric models and prediction techniques are significant tools. Policymakers are always concerned with the correct future estimates of economic variables to take the right economic decisions, design better policies and effectively implement them. Therefore, there is a need to improve the predictive accuracy of the existing models and to use more sophisticated and superior algorithms for accurate forecasting. Deep learning models like recurrent neural networks are considered superior for forecasting as they provide better predictive results as compared to many of the econometric models. Against this backdrop, this paper presents the feasibility of using different deep-learning neural network architectures for trade forecasting. It predicts export trade using different recurrent neural architectures such as “vanilla recurrent neural network (VRNN)”, “bi-directional long short-term memory network (Bi-LSTM)”, “bi-directional gated recurrent unit (Bi-GRU)” and a hybrid “bi-directional LSTM and GRU neural network”.
    Keywords: Bi-LSTM; GRU; economic forecasting; international trade; recurrent neural network.
    DOI: 10.1504/IJCAT.2024.10061555
     
  • Retrieval method for English teaching resources based on decision tree algorithm   Order a copy of this article
    by Jinyan Du 
    Abstract: A decision tree algorithm based English teaching resource retrieval method is proposed to address the issues of low recall, low precision, and long retrieval time in current resource retrieval methods. Firstly, the word frequency statistical method is used to extract the features of teaching resources. Then, the C4.5 algorithm in the decision tree algorithm is applied to complete the classification of English teaching resources based on information gain. Finally, select the Sussan concept similarity algorithm to calculate the similarity between the retrieved content and the database content, sort the similarity values from high to low, and select the teaching resource with the highest similarity value as the optimal English teaching resource retrieval result. The experiment shows that the recall of the studied method remains between 98.0% and 99.0%, and the precision is controlled above 98.00%. The shortest retrieval time is only 8.15 s.
    Keywords: decision tree algorithm; English teaching resources; feature extraction; semantic similarity; resource retrieval.
    DOI: 10.1504/IJCAT.2024.10061989
     
  • Personalised push of English online and offline mixed teaching resources   Order a copy of this article
    by Baomei Huang 
    Abstract: In order to improve the quality of English teaching and recommend English teaching resources that are suitable for students' needs, a personalized push method is proposed, combined with a mixed online and offline teaching mode. Firstly, by analysing the relationship between students and learning resources and combining interest models, we aim to explore students' interest in English learning resources. Next, based on the mining results of learning interests, a rating matrix is established to describe students' English learning behavior. Finally, using the results of resource scoring similarity, push English teaching resources that are highly similar to students' preferences. The experimental results show that compared to existing teaching resource push methods, our method has higher efficiency in extracting teaching resources and can achieve personalized teaching resource push within 3s, thereby helping to improve the quality of students' English learning.
    Keywords: English teaching; online and offline; mixed teaching mode; teaching resources; personalised push.
    DOI: 10.1504/IJCAT.2024.10061990
     
  • Research on automatic annotation of English pronunciation errors based on deep transfer learning   Order a copy of this article
    by Fengjuan Zhang 
    Abstract: In order to overcome the problems of low accuracy and long time of traditional English pronunciation error labeling methods, this paper proposes an automatic English pronunciation error labeling method based on deep transfer learning. Firstly, construct an English phonetic corpus to extract English pronunciation features; Then, a hidden Markov model is used to map the pronunciation phoneme sequence; Finally, through deep Transfer learning, the pronunciation error annotation function is constructed, and the automatic annotation of English pronunciation errors is realized through iterative training, and the final annotation results are output to realize the automatic annotation of English pronunciation errors. The results show that the accuracy of the proposed method for annotation can reach 99.8%, and the automatic annotation time does not exceed 16 minutes, effectively improving the effectiveness of automatic annotation for English pronunciation errors
    Keywords: speech corpus; phoneme sequence; end-to-end model; deep transfer learning; linear prediction coefficient.
    DOI: 10.1504/IJCAT.2024.10061991
     
  • Study on personalised search of English teaching resources database based on semantic association mining   Order a copy of this article
    by Xiujuan Wang, Tao Wei 
    Abstract: A personalised search method based on semantic association mining is proposed to address the issue of low recall and accuracy in personalised search of teaching resource databases. First, classify the resources in the English teaching resource database, extract the semantic features of the resources, then mine the user data, build the user interest model and solve it. Finally, according to the user interest model and the semantic features of the resource database text, determine the keywords most relevant to the user interest, and complete the personalised search of the English teaching resource database information. The experimental results show that the accuracy of personalised search in English teaching resource databases is higher than 98.2%, and the recall rate reaches 99.6%, indicating that the application of this method can effectively improve the effectiveness of personalised search in English teaching resource databases
    Keywords: semantic association mining; genetic algorithm; differential privacy; user interest model; personalised search.
    DOI: 10.1504/IJCAT.2024.10061992
     
  • An English translation syntax error recognition based on improved transformer model   Order a copy of this article
    by Wenjuan Che 
    Abstract: In order to overcome the problems of low recognition rate, high error rate and long processing time of traditional English translation syntax error recognition methods, an English translation syntax error recognition method based on improved Transformer model was proposed. The Kneser-Ney method is used to smooth processing the English translation text, and the hidden Markov model is used to label the smoothed English translation sequence to extract the character features, part of speech features, and part of speech features of the English translation sequence. The Transformer model is improved through the global location of entities, and the improved Transformer model and syntax error feature tags are used to recognition syntax error in English translation. The experimental results show that the maximum recognition rate of method of this paper is 97.1%, the minimum error recognition rate is 3.2%, and the average processing time is 0.72 s
    Keywords: improved Transformer model; English translation; syntax error recognition; smooth processing; hidden Markov model; feature tags.
    DOI: 10.1504/IJCAT.2024.10061993
     
  • A method for sharing online assisted teaching resources based on mobile social networks   Order a copy of this article
    by Weiwen Feng, YuTong Sun 
    Abstract: In order to solve the problems of high latency and average routing hops in existing teaching resource sharing methods, a new online assisted teaching resource sharing method based on mobile social networks is proposed. Firstly, combining temporal similarity with regional similarity, calculate the total similarity between learners. Secondly, for mobile social networks, the Similarity Louvain algorithm is used to construct communities based on the total similarity between learning. Finally, for learners in the community, sharing online auxiliary teaching resources through a direct meeting mechanism; For learners in the community, use improved ant colony algorithm to select the best advanced service provider and share online auxiliary teaching resources. Experimental results show that under different signal-to-noise ratios, the average number of route hops for resource sharing in our method is relatively low, with the highest average number of route hops around 3, and the sharing delay is effectively reduced.
    Keywords: mobile social network; online assisted teaching; resource sharing; attribute differences; request historical differences; similarity Louvain algorithm.
    DOI: 10.1504/IJCAT.2024.10062302
     
  • Dynamic classification of English teaching resources based on frequent itemset mining   Order a copy of this article
    by Xiuling Shi, Meiping Peng 
    Abstract: In order to solve the problems of poor resource classification accuracy and poor teaching resource classification performance in English teaching resource classification methods, this paper proposes a dynamic classification method for English teaching resources based on frequent itemset mining. Obtain English teaching resource data through frequent itemset mining methods, and perform word removal processing on the mined data; Design a TextRank keyword extraction model for English teaching resources based on network graph extraction method, and calculate the importance of keywords; By improving the TextRank keyword extraction method through frequent itemset mining, dynamic classification results of English teaching resources are obtained. The experimental results show that the English teaching resource classification method proposed in this paper takes only 15s, with a resource classification accuracy of 99.6%, and an AUC value consistently changing around 1, indicating better performance in English teaching resource classification
    Keywords: frequent itemsets mining; teaching resources; resource classification; TextRank keyword extraction model; network diagram.
    DOI: 10.1504/IJCAT.2024.10062303
     
  • A sharing method of English book resources in regional teaching consortium based on XDS technology   Order a copy of this article
    by Yawei Liu 
    Abstract: There are issues with low security coefficients in the sharing of English book resources in regional teaching consortia. Therefore, this article designs a method for sharing English book resources in regional teaching consortia based on XDS technology. Firstly, the graph clustering algorithm is used to abstract the English book resource data of the regional teaching consortium into a mathematical problem, and the clustered English book resources are divided into cluster families to achieve resource data collection; Then, the decision tree algorithm is used to classify the collected English book resource data, and the naive Bayesian algorithm is used to fill in the data after classification. Finally, use XDS technology to construct a framework for English book resource sharing in regional teaching consortia, and achieve research on resource security sharing. Test results show that the proposed method can improve the security of shared resource data and has a good effect.
    Keywords: XDS technology; Regional Teaching Consortium; English book resources; sharing methods; graph clustering.
    DOI: 10.1504/IJCAT.2024.10062304
     
  • Student privacy data encryption in network teaching platform based on dynamic key   Order a copy of this article
    by Peng Qu, Dahui Li 
    Abstract: In order to improve the integrity and security of student privacy data on online teaching platforms, a dynamic key based encryption method for student privacy data on online teaching platforms is proposed. Firstly, analyze the content of student privacy data on online teaching platforms, and use univariate feature extraction mining to mine student privacy data. Secondly, discrete wavelet transform is used to denoise the mined student privacy data to improve the quality of student privacy data. Finally, according to the dynamic key authentication process, complete the encryption of student privacy data. The experimental results show that in different privacy databases, the encryption time of our method is significantly shortened, and the encryption integrity is effectively improved, with an average integrity of 96.23%.
    Keywords: Dynamic key; Online teaching platform; Student privacy data; data encryption.
    DOI: 10.1504/IJCAT.2024.10062305
     
  • Data classification mining of university mental health education resources based on global search algorithm   Order a copy of this article
    by Jing Fang, Daoxun Wang 
    Abstract: To solve the problems of low accuracy and recall rate, as well as long classification mining time in traditional methods, a university mental health education resource data classification mining method based on global search algorithm is proposed. Collect data on university mental health education resources, identify abnormal data using isolated forests, and perform correction processing. Extract resource data features using Fisher discriminant criteria and select data features. Build a data classification mining model for university mental health education resources, and use the particle swarm optimization algorithm in the global search algorithm to construct an optimization objective function for classification mining. Input the data to be processed into the optimized model to obtain relevant classification mining results. The experimental results show that the proposed method has a mean classification mining accuracy of 98.1%, a mean recall rate of 97.3%, and a classification mining time of less than 1.28 s.
    Keywords: global search algorithm; university mental health education; resources; classification mining; isolation forests; Fisher's discriminant criterion; particle swarm optimisation algorithm.
    DOI: 10.1504/IJCAT.2024.10062306
     
  • Identifying student behavioural states in business English listening classroom based on SSD algorithm   Order a copy of this article
    by Xuewei Gao, Juan Xin 
    Abstract: By analysing students' behavioral states, one can evaluate their level of participation, engagement, and focus in learning activities. Therefore, this study designs a method for identifying student behavior states in business English listening classes based on the SSD algorithm. The behaviour state features are input into the improved SSD algorithm model, and the features are extracted step by step through operations such as convolution and pooling, and the classification and identification results of students' behavior states are output. In the experimental results, the kappa coefficient of the identification results obtained by this method can reach 0.974, and the global minimum and maximum values of the Matthews correlation coefficient are 0.80 and 0.95, indicating that the identification results of this method are effective.
    Keywords: business English listening class; student behaviour status; state identification; SSD algorithm; image enhancement; feature extraction.
    DOI: 10.1504/IJCAT.2024.10062307
     
  • Anomaly identification of English online learning data based on local outlier factor   Order a copy of this article
    by Yuying Liu 
    Abstract: In order to solve the problems of low recognition accuracy, low recall rate and low absolute value of F1 score in traditional online English learning data anomaly identification methods, a new anomaly identification of English online learning data based on local outlier factor is proposed. English online learning data resources are utilized to be mined using K-nearest neighbors and local reachability density, and a unified dataset is created by integrating data from different sources and formats. The information source model of the dataset is abstracted as a tuple, and English online learning data anomaly identification is achieved by implementing the local outlier factor threshold in the tuple. The experimental results indicate that the identification accuracy of the researched method is high, with an accuracy rate of over 90%. The recall rate and absolute value of the F1 score are also high, demonstrating good identification effectiveness.
    Keywords: local outlier factor; English online learning; data anomaly identification; K-nearest neighbours; information source model.
    DOI: 10.1504/IJCAT.2024.10062308
     
  • Balanced allocation of teaching information resources based on discrete particle swarm optimisation algorithm   Order a copy of this article
    by Hui Wang  
    Abstract: To overcome the problems of low resource use, low resource coverage, and long allocation time in traditional methods, a balanced allocation method of teaching information resources based on discrete particle swarm optimisation algorithm is proposed. Teaching information resources are collected and preprocessed through data cleaning, stop word removal, and label processing. The objective function for balancing teaching information resources is constructed, and the discrete particle swarm optimisation algorithm solves the objective function by determining the encoding method, initialising the particle swarm, and calculating the fitness, etc. The optimal solution includes optimal resource weights, optimal resource allocation methods, optimal resource allocation proportions, etc. The obtained parameters are used to determine the optimal allocation scheme. The experimental results show that the resource use rate of proposed method can reach 99.8%, the coverage rate of teaching resources varies from 96.2% to 99.5%, and the allocation time does not exceed 3.2 s.
    Keywords: Discrete particle swarm optimization; Teaching information resources; Balanced allocation; Optimal resource weights; Allocation proportions.
    DOI: 10.1504/IJCAT.2024.10062309
     
  • A knowledge sharing method for virtual academic community based on social network analysis   Order a copy of this article
    by Xiaolin Zhang, Miao Wang 
    Abstract: Studying knowledge sharing in virtual academic community is meaningful for a deep understanding of knowledge dissemination and sharing mechanisms, as well as for enhancing the knowledge level within these communities. To overcome the low success rate, long response time, and low satisfaction of traditional methods, a knowledge sharing method for virtual academic community based on social network analysis is proposed. The method analyzes the social network of knowledge exchange among users in virtual academic community, achieves knowledge discovery within these communities, and aggregation processing the knowledge. The knowledge sharing model is built using the state space modeling approach to realize knowledge sharing within the community. Experimental results demonstrate that the proposed method achieves a maximum success rate of 98.2% for knowledge sharing, a maximum response time of 0.51 s, and an average satisfaction level of 96.6.
    Keywords: social network analysis; virtual academic community; knowledge sharing; aggregation processing; state space modeling; knowledge sharing model.
    DOI: 10.1504/IJCAT.2024.10062310
     
  • Online learning effectiveness evaluation for college students based on social network data mining   Order a copy of this article
    by Die Meng, Beibei Ma, Mengting Liu, Shiying Li 
    Abstract: To solve the problems of low information collection accuracy, recall, and evaluation accuracy in traditional methods, an evaluation method of online learning effectiveness for college students based on social network data mining is proposed. A web crawler architecture is utilized to mine social network data and collect information on university student network learning.Linear regression models are employed to filter indicator data and establish an index system for evaluating learning effectiveness.The weights of indicators are determined using the analytic hierarchy process, and fuzzy evaluation vectors are obtained by combining membership degree functions. An evaluation model is constructed using fuzzy evaluation vectors and fuzzy judgment method, and evaluation indicator data are input into the model to obtain scores for learning effectiveness. Experimental results demonstrate that the maximum accuracy of information collection for the proposed method is 98.1%, the maximum recall rate is 97.9%, the mean precision is 97.67%.
    Keywords: social network data mining; college students; online learning; effectiveness; evaluation; web crawler; index system; fuzzy evaluation vectors and fuzzy judgment method.
    DOI: 10.1504/IJCAT.2024.10062311