International Journal of Computer Applications in Technology (48 papers in press)
Non-linear modified equation modeling in dynamical systems (Case Study research on Long Jump patterns)
by Farzad Sharifat
Improving Arabic Text Categorization using FA Words with K-Nearest Neighbor and Centroid-Based classification algorithms
by El-Sayed Atlam, M.E. Abd El-Monsef, O. El-Barbary
3D Scanning Machine and Additive Manufacturing: Concurrent Product and Process Development
by Ismet P. Ilyas
Simulation and visualisation approach for accidents in chemical plants
by Feng Ting-Fan, Tan Jing, Liu Jin, Deng Wensheng
Abstract: A new general approach to lay the foundation for building a more effective and real-time evacuation system for accidents in chemical plants is presented. In this work, we build the mathematical models and realise automatic grid generating based on the physical models stored in advance with several algorithms in jMonkeyEngine environment. Meanwhile, the results of the simulation data through finite difference method (FDM) are visualised coupling with the physical models. Taking fire as an example, including fire with single and multiple ignition sources, shows the feasibility of the presented approach. Furthermore, a coarse alarm and evacuation system from fire have been developed with a multiple SceneNode and roam system, which also includes the making and importing of the physical models. However, to improve the accuracy of the mathematical models, adaptability and refinement of the grids and universality of the evacuation system is the direction of efforts.
Keywords: simulation; chemical accidents; alarm and evacuation system; jMonkeyEngine.
Detecting occluded faces in unconstrained crowd digital pictures
by Chandana Withana, S. Janahiram, Abeer Alsadoon, A.M.S. Rahma
Abstract: Face detection and recognition mechanisms, a concept known as face detection, are widely used in various multimedia and security devices. There are significant numbers of studies into face recognition, particularly for image processing and computer vision. However, there remain significant challenges in existing systems owing to limitations behind algorithms. Viola Jones and Cascade Classifier are considered the best algorithms from existing systems. They can detect faces in an unconstrained crowd scene with half and full face detection methods. However, limitations of these systems are affecting accuracy and processing time. This project proposes a solution called Viola Jones and Cascade (VJaC), based on the study of current systems, features and limitations. This system considered three main factors: processing time, accuracy and training. These factors are tested on different sample images, and compared with current systems.
Keywords: face detection; unconstrained crowd digital pictures; face recognition.
Ensuring the correctness of adaptive business processes: a systematic literature review
by Fairouz Fakhfakh, Hatem Hadj Kacem, Ahmed Hadj Kacem
Abstract: Adaptability in process management systems is gaining an increasing attentionrnto satisfy the variable enterprise requirements. This concept has been recognized by the process community for a long time and various approaches in this area have been developed so far. In this context, one of the most difficult challenge is to ensure that change operations are applied correctly and do not cause any inconsistencies. This paper presents a survey that examines the existing studies ensuring the correctness of process changes.rnOur survey follows the guidelines of systematic literature reviews (SLR). It provides a comparison of the existing approaches based on some criteria such as verified properties, modeling languages and verification tools. Finally, we highlight some recommendations and possible future researches which need further investigations. So, throughout this present paper, we provide information for researchers and developers to understand the contributions and challenges of the current studies to pave the way for improving theirrnsolution.
Keywords: Process; adaptability; correctness; systematic literature review; challenges.
Developing a biotech scheme using fuzzy logic model to predict occurrence of diseases using a person's functional state
by Riad Taha Al-kasasbeh, Nikolay Korenevskiy, Altyn Amanzholovna Aikeyeva, Sofia Nikolaevna Rodionova, Ashraf Shaqadan, Maksim Ilyash
Abstract: The work deals with the issues of the synthesis of combined fuzzy decision rules for classification and evaluation of the level of functional states on two blocks of heterogeneous characteristics: the subjective test questionnaires and indicators describing the human attention.
Keywords: level of functional reserve; psycho emotional pressure; intellectual exhaustion; physical exhaustion; heterogeneous fuzzy models.
Improved XGBoost model Based on Genetic Algorithm
by Feng Zhao, Jinxiang Chen, Yanguang Sun, Yilan Yin
Abstract: An optimised XGBoost model based on genetic algorithm to search for optimal parameter combinations be proposed in this paper. It was proved that the improved algorithm has better classification effect through the liver disease data set Liver Disorders Data Set in the UCI Machine Learning Repository. In recent years, there have been many excellent intelligent algorithms in the field of machine learning and XGBoost is one of them. However, when using the XGBoost algorithm, it usually involves the adjustment of various parameters in the XGBoost model, and the selection of different parameter combinations has a greater impact on the classification performance of the model. In this paper, after encoding the XGBoost model parameters optimized by genetic algorithm, the global approximate optimal solution is obtained through operations such as selection, crossover and mutation, which greatly improves the performance of the model.
Keywords: XGBoost; parameter optimisation; genetic algorithm.
Mining expertise of developers from software repositories
by Maen Hammad, Haneen Hijazi, Mustafa Hammad, Ahmed Otoom
Abstract: This paper presents a technique to mine the developers contributions to explore their expertise in open source projects. The proposed technique is based on analyzing archived code changes, committed by developers, to identify their expertise. The technique analyses the keywords that appear in the textual content of commits. It is a lightweight technique since the text in commits is analyzed without making any syntactic code differencing. Each developer is linked with a list of keywords, with their frequencies, that appeared in his commits. Based on these keywords, three types of expertise are defined; unique, common and frequent. Unique expertise reflects topics exclusively handled by developers. Common expertise reflects shared topics while frequent expertise reflects frequent topics handled by each developer. The identified expertise can help in identifying topics or issues that are handled by specific or group of developers. A tool is developed to automatically mine and analyze committed code changes to support expertise identification. A case study is presented on three open source projects to investigate three research questions and to show how the proposed techniques can be applied. The main observations and conclusions of the study showed that frequent terms provide useful and variant information about developers expertise.
Keywords: software maintenance and evolution; mining software repositories; expertise mining.
Reliability-Aware Fixed Priority energy management with Shared resources in Real -time System
by Yiwen Zhang, Huizhen Zhang, Weixian Jiang
Abstract: In this paper, we focus on preemptive rate monotonic scheduling and comprehensively consider energy consumption and system reliability about scheduling periodic tasks with shared resources. Firstly, a static scheme for fixed priority periodic tasks with shared resources is proposed, which executes with a uniform speed and ignores the system reliability. Secondly, the problem of energy consumption and system reliability for scheduling fixed priority periodic tasks with shared resources is proved to be NP-hard and a maximum execution time first (MF) algorithm is proposed. Finally, a dynamic scheme for fixed priority periodic tasks with shared resources (DA) is proposed. The DA algorithm exploits the dynamic slack time to save energy while preserving the system reliability. The experimental results show that the DA algorithm saves about 19.28% energy compared with the MF algorithm.
Keywords: fixed priority; energy; scheduling; reliability; shared resources.
Waiting time influence on customer repeated behaviour in chat service systems with staffing policy
by Ying Liu, Miao Yu, Tao Zou
Abstract: In this paper, a behavioral queuing model with feedback is developed for chat service system, in which managers determine capacity sizing to maximize profit. We explicitly consider customer repeated and queueing behavior, because this will have a positive impact on arrival rates. For this case, customer satisfaction as perceived from the perspective of waiting time changes according to the capacity sizing. We define the optimization of the staffing of chat service system as the number of agents to maximize profits, including the income from customers and the costs from agents. Using a numerical analysis, we compare it with the traditional model without considering repeated customer behavior. In addition, we also point out how managers can optimize staffing through various customer behavior mechanisms.
Keywords: behavioural queuing; staffing; chat service system; customer satisfaction.
Data acquisition and stream processing with Matlab using system objects
by Agostino Giorgio, Alessio Melibeo
Abstract: In this paper we will describe how to perform Data Acquisition and Stream Processing using MATLAB
Keywords: audio applications; development tools; signal processing; computer applications; software engineering.
Application of novel big data processing techniques in process industries
by Pavel Maksimov, Tuomas Koiranen
Abstract: Modern process engineering industry offers great opportunities for harvesting tremendous amounts of data, both structured and unstructured. However, traditional data analysis tools can be rather inefficient when dealing with significant volumes of information. Still, this issue is even further aggravated by frequently occurring inconsistencies and discrepancies within analyzed datasets. Novel methods and advanced algorithms are being developed to address this challenge, yet, as regards analytics of actual industry related data, application of these instruments has been comparatively limited so far. In light of this, within the limits of this work, applicability of novel analytical instruments in the context of process engineering industry is studied for both structured and unstructured data processing. In the former case, the data describing matte smelting process of copper production is analyzed focusing on identification of interdependencies between key process parameters and products quality indicators, while in the latter case a dataset consisting of relevant scientific articles is investigated with a view to extracting key concepts and determining relations among them. In the scope of copper production process analysis, crucial operating parameters affecting composition of main and secondary products are determined and major relations between concentrations of key constituents are revealed and explained. In the frame of unstructured data exploration, a cognitive search platform is configured and trained in accordance with specific traits and peculiarities of the analyzed information with further filtering of contained documents and identification of the most relevant insights.
Keywords: data processing; predictive analysis; cognitive search; data extraction; process engineering; metal industries.
A novel approach of cursive signature generation for personal identity
by Jungpil Shin, Md Abdur Rahim, Md Rashedul Islam, Keun Soo Yun
Abstract: Signatures are used in many situations of daily life. In many non-English-speaking countries like Japan, in general people are not familiar with English and they do not have English signatures in most cases. English signatures are written by combining the letters of the English alphabet in cursive. Many people find difficulty in writing English in cursive, and most of them want to learn how to write a good signature. To meet this demand, this study proposes a technique for generating an English signature for people who cannot write in cursive and hope to have an English signature. In the proposed model, we use a cubic Bezier curve for the cursive connection of input characters for a signature generation, and an affine transformation is used for the modification of the character of the generated signature. Modifications were made in the slant, scale, space between the characters and line emphasis. In addition to these, we added some decorative functions, such as putting a circle around the signature. The system also provided an animation to teach users how to write cursive English and the order of strokes used in a signature. After that, we conducted a questionnaire survey about the usability of this system and compared it with the state of the art system. As a result, we were able to provide system-generated signatures that satisfied the users.
Keywords: signature generation; human computer interaction; personalisation; cubic Bezier curve; cursive English.
Improved low-cost recognition system for handwritten Bengali numerals
by Md Aktaruzzaman, Tewodros Mulugeta Dagnew, Massimo Walter Rivolta, Roberto Sassi
Abstract: Handwritten recognition has drawn massive attention during the last decade owing to its numerous potential applications. This paper is concerned with the low-cost features extraction for the development of an improved Bengali handwritten numeral recognition system. Each numeral was first transformed and resampled to a binary image of fixed size. A set of new features based on shape analysis was derived from the resampled image, and then a multilayer neural network was trained using the extracted features. The recognition accuracy of the developed system was tested on both training and test sets of a publicly available Bengali handwritten numerals database at three different resolutions. Besides accuracy, the reliability of the system was also estimated using Cohen's kappa. The highest accuracy, 99.12% with reliability about 99%, was obtained for the test database at resolution of 32 x 32. The use of PCA reduces the feature dimension from 142 to 68, resulting in a slight reduction in accuracy to 98.80%. The proposed system provided very high accuracy with the lowest number of simple features.
Keywords: feature extraction; Bengali; handwritten numerals recognition; artificial neural network; machine learning; OCR.
A new four-dimensional two-scroll hyperchaos dynamical system with no rest point, bifurcation analysis, multi-stability, circuit simulation and FPGA design
by Sundarapandian Vaidyanathan, Esteban Tlelo-Cuautle, Aceng Sambas, Leutcho Gervais Dolvis, Omar Guillén-Fernández
Abstract: This paper deals with the design of a new four-dimensional two-scrollrnhyperchaos dynamical system with three quadratic nonlinear terms. The new two-scroll dynamical system does not possess any rest point suggesting the existence of hidden attractor. This paper provides a detailed analysis such as multistability, symmetry,coexisting hyperchaos attractors and bifurcation properties of the new hyperchaos dynamical system with two-scroll hidden attractor. We realise the dynamic equations of the two-scroll hyperchaos system with an electronic MultiSim circuit. Next, we build design and implementation of the two-scroll hyperchaos system on FPGA.
Keywords: hyperchaos; hyperchaotic systems; bifurcations; FPGA; circuit design.
Temperature variation impact on estimating costs and most critical components in a cloud data centre
by Demis Gomes, Guto Leoni, Glauco Gonçalves, Patricia Endo, Paulo Maciel, Djamel Sadok
Abstract: Cooling plays an important role in data centre availability by mitigating the overheating of information technology (IT) equipment. Although many existing works have evaluated the performance of the cooling subsystems in data centres, only a few studies have considered the important relationship between cooling and IT subsystems. This work provides efficient models (using Stochastic Petri Nets (SPNs)) to represent a cooling subsystem and analyse the impact of its failures in terms of service downtime and financial cost. The study identifies the components that are the most critical with respect to service availability through the use of sensitivity analysis. Results show that the adoption of a redundant architecture reduces the annual costs related to downtime by about 70%. The chiller is observed as the main component that affects service availability and operation costs.
Keywords: availability; downtime cost; operational cost; sensitivity analysis; cooling subsystem.
Design of capacitance sensor for two-phase flow monitoring based on finite element models
by Zhihong Huang, Hanxiang Wang, Xin Zhang
Abstract: Monitoring water-oil two-phase flow is of great industrial significance. In this work, an electrical capacitance sensor was designed and tested to monitor the two-phase flow. The geometry of the capacitance sensor is a key factor for sensor design, which greatly influences the performance of the sensor. In order to optimise the capacitance sensor for two-phase flow monitoring, it is necessary to analyse capacitance sensors with different geometries. In this paper, the capacitance sensors with concave plates, double ring electrodes, helical electrodes, parallel strips and perpendicular strips are proposed and briefly introduced. The finite element (FE) models for capacitance sensors were constructed in COMSOL multiphysics, and the preliminary experiments were also carried out. Both simulation and experimental results show that the capacitance of the sensor tends to increase with decreasing oil content. In addition, the capacitance sensors with different geometries were studied using FE models. The measurement sensitivity distributions obtained from FE models vary with different electrode geometries, based on which design parameters can then be selected to address different requirements.
Keywords: flow monitoring; capacitance sensor; sensor design; finite element models.
A hybrid collaborative filtering recommendation algorithm for requirements elicitation
by Qusai Shambour, Mosleh Abualhaj, Mayy Al-Tahrawi
Abstract: Requirements elicitation is one of the most critical and difficult tasks in software development. The quality of elicited requirements is a significant aspect that affects the success of a software project. Requirements reuse has shown to be an effective and efficient elicitation technique that can enhance the quality of the requirements elicitation process and, as a result, lead to a projects success. However, the information overload problem, which caused by the rapidly growing number of reusable software requirements in large requirements repositories, hinders the effectiveness of the requirements reuse process. Recommender systems proved to be a well-known solution to such problem. This paper focuses on the adoption of recommender systems to mitigate the problem of information overload that is inherent in the requirements elicitation process, specifically, by assisting requirement engineers in retrieving relevant reusable requirements from large-scale requirements repositories. This paper proposes an effective hybrid user-item based collaborative filtering recommendation algorithm by integrating enhanced versions of the user-based and item-based collaborative filtering approaches. The validation results on the RALIC and sparse datasets illustrate that the proposed algorithm outperforms and mitigates the drawbacks the benchmark collaborative filtering-based recommendation approaches in terms of recommendation accuracy, precision, recall and F1 measures, as well as significantly alleviating the data sparsity problem.
Keywords: requirements engineering; requirements elicitation; requirements reuse; information filtering; collaborative filtering; recommender systems.
Multidimensional data visualisation method based on convex-corrected Radviz
by Jingjing Yin, Haibo Shi, Xiaofeng Zhou, Liang Jin, Shuai Li, Yichi Zhang
Abstract: Radviz is one of the most commonly used multidimensional data visualisation methods. Considering the projection points overlapping a lot by Radviz, this paper puts forward a new Radviz optimisation method to correct the position of the projected data points. Firstly, the new method introduces the Prim algorithm to realise the optimal ordering of the dimension anchors on Radviz. Secondly, the convex hull mapping and the second Radviz mapping are used to correct the position of the projected data points. Finally, the data points are visualised. In addition, in order to verify the effectiveness of the algorithm, the Dunn index is used to do a quantitative evaluation of visualization. By comparing multiple sets of dataset experiments, the results show that the new method is beneficial to obtain the better visualisation effect of multidimensional data in Radviz projection.
Keywords: Radviz; visualisation; multidimensional data; convex-corrected.
Adaptive Self Recurrent Wavelet Neural Network and Sliding Mode Controller/Observer for a Slider Crank Mechanism
by Ahmad Taher Azar, Fernando E. Serrano, Josep M. Rossell, Sundarapandian Vaidyanathan, Quanmin Zhu Zhu
Abstract: In this paper, a novel control strategy based on an adaptive self recurrent wavelet neural network (SRWNN) and a sliding mode controller/observer for a slider crank mechanism is proposed. The aim is to reduce the tracking error of the linear displacement of this mechanism while following a specified trajectory. The controller design consists into two parts. The first one is a sliding mode control strategy and the second part is an SRWNN controller. This controller is trained offline first, and then the SRWNN weights are updated online by the adaptive control law. Apart from the hybrid control strategy proposed in this paper, a velocity observer is implemented to replace the use of velocity sensors. The outcomes obtained in the numerical experiment section prove that the smallest tracking error is obtained for the linear and angular displacements in comparison with other strategies found in literature due to the uncertainty and disturbance rejection properties of the sliding mode and the self recurrent wavelet neural network controllers. Besides, it is corroborated an accurate velocity estimation due to the precise theoretical design of the proposed observer in order to reduce the error between the measured and estimated state to zero. This paper begins with the derivation of the dynamic equations of the slider crank mechanism followed by the derivation of the proposed observer and control strategies. Finally, to demonstrate the effectiveness of the controller/observer strategy, a numerical example is supplied to analyze the variables of the system, tracking error and the estimated variables
Keywords: Adaptive wavelet neural networks; Sliding mode control; Sliding mode observer; Slider crank mechanism
A runtime model-based framework for specifying and verifying adaptive RTE systems
by Nissaf Fredj, Yessine Hadj Kacem, Mohamed Abid
Abstract: Adaptive Real-Time Embedded Systems (RTES) may execute in an unpredictable context that is impossible to definitely consider in the development time. Therefore, these systems are required to adapt their behavior to unpredicted changes at runtime in order to maintain their feasibility and usefulness. Their design requires effective runtime modeling formalisms for monitoring, reconfiguration planning and adaptive system analysis. In this context, software designers need to evaluate, refine and validate runtime models at early stages of development via adaptation tools, in particular for runtime adaptive systems to avoid execution problems. In the present paper, we propose a runtime model-based framework that allows the modeling, simulation as well as the traceability of adaptive RTES. Our proposal starts by a high-level specification based on the UML/MARTE profile, which describes an adaptive system and supports the reasoning about its behavior and structure at runtime. The runtime UML/MARTE models are translated into an adaptive one that instantiates MAPE patterns for the control and the traceability of the runtime system. Then Model-to-Text (M2T) transformations allow us to generate simulation scripts for the analysis of adaptive system behavior at runtime and evaluate its real-time constraints.
Keywords: RTES; Runtime adaptation; Runtime model; M2T transformation; MAPE control loop
Skew Decision Process based on Machine Learning Content Analysis and Clustering
by Tanzila Saba
Abstract: Skew decision process includes skew detection and correction that is mandatory for automatic information retrieval from documents. Hence, there is an utmost need to correct the information skew prior to further processing. Accordingly, this research presents a robust document information skew detection and correction approach based on histogram clustering for efficient information retrieval. The proposed approach is quite generic and therefore, could detect skew angle for various types of documents such as graphics, charts, postal labels, handwritten text, forms, drawings and their possible combination. The proposed approach is robust that could deal up to ±89 degree skew angle even scanned at least resolution of 50 dots per inch. Additionally, it is language independent. The proposed technique consists of mainly two steps. In the first step, corners are located except the top corner. The skew angle is estimated using the cross-correlation of located corners with minimum computational complexity. However, to verify the alignment, the horizontal projection profile is analyzed. The proposed approach is examined using a benchmark database of document images available online free. Success rate approaching 100% within a confidence range of 0.3 degrees is reported.
Keywords: Skew decision process; automatic information processing; document analysis; semantic web
Simulation Results and Practical Implementation of a PD-Super-Twisting Second Order Sliding Mode Tracking Control for a Differential Wheeled Mobile Robot
by Ebrahim Elyoussef, Nardênio Martins, Douglas Bertol, Edson De Pieri, Ubirajara Moreno
Abstract: A robust solution to the trajectory tracking control problem for a differential wheeled mobile robot should deal with the existence of parametric and structural uncertainties, external disturbances and operation limitations. The first order sliding mode control with boundary layer is a common and suitable solution that can ensure chattering attenuation, but with poor degree of robustness. Fortunately, higher order sliding mode control can achieves greater degree of robustness with the reduction of the chattering phenomenon. Based on this knowledge, a control strategy is proposed using a super-twisting sliding mode control, which enforces a second order sliding mode, integrated with a proportional plus derivative control to solve the problem achieving good robustness. This linear control technique plays an important role in increasing the robustness by mitigating the influence of neglected dynamics. Simulation and experimental results are explored to prove the effectiveness of the proposed control strategy.
Keywords: Differential wheeled mobile robot, trajectory tracking, sliding mode control, PD control, chattering attenuation, uncertainties and disturbances.
Smart grid resources allocation using smart genetic heuristic
by Abderezak Touzene, Sultan Al Yahyai, Farid Melgani
Abstract: In this paper, we propose a new smart genetic algorithm SGA-SG which allows Smart Grid Constituencies (SGC) such as power generators, power distributers, and power consumers to optimise their pay-offs. The proposed resource allocation algorithm connects real-time power consumers to the best power distributers in terms of cost. SGA-SG algorithm uses the concept of genetic algorithm, smartly guided towards the solution by reducing the random walk effect of the classical genetic algorithm. Usually, smart grid systems are large scale systems (millions of customers). Hence, the design of the proposed SGA-SG algorithm takes into consideration the scale of the system in terms of memory and speed requirements to produce a good quality allocation within a reasonable time. SGA-SG algorithm is designed to quickly respond to any power failure on a real-time basis. Experimental results show that SGA-SG algorithm gives near optimal solution and reduces by 20% the overall cost of the smart grid constituencies compared with the traditional grid system.
Keywords: smart grid; resource allocation; optimisation; smart genetic algorithm.
Inland river image dehazing algorithm based on water surface depth Prior
by ZhongYi Hu, ChangZu Chen, Qi Wu, MianLu Zou, YuLian Cao, MingHai Xu, ZuoYong Li
Abstract: This study proposes a single-image restoration algorithm requiring no additional scene information that is suitable for the removal of haze from images of inland waterways. This algorithm uses a water surface depth of focus prior to obtain a rough atmospheric-light transmission image, and then applies guided filter refinement and sky segmentation based on grey level histograms to estimate the atmospheric light intensity, thereby performing image dehazing automatically. The performance and applicability of our proposed algorithm are verified by the dehazing results obtained using the proposed algorithm for a large sample set of hazy images of inland waterways compared with those obtained using two standard single-image dehazing algorithms in terms of the processed image quality and processing speed. The results confirm the reliability of the water surface depth of focus prior model. Our method is appropriate for inland waterway images and provides better image quality and computational performance than the existing algorithms.
Keywords: guided filter; image dehazing; inland river image; water surface depth prior.
Identification of nonlinear stochastic systems using a new Hammerstein-Wiener neural network: a simulation study through nonlinear hydraulic process
by Saif Eddine Abouda, Donia Ben Halima Abid, Mourad Elloumi, Yassine Koubaa, Abdessattar Chaari
Abstract: Hammerstein-Wiener models have been proved to be suitable in modelling a class of typical nonlinear dynamic systems. This paper aims at developing a Hammerstein-Wiener Neural Network (HWNN) which formulates Hammerstein-Wiener mathematical model, in order to identify a nonlinear dynamic system operating in stochastic environment. A central aspect is that a general situation has been considered wherein non-invertible nonlinearity output and correlation of stochastic disturbances after the dynamic linear block. Different from the existing parameter identification methods, the model is developed to handle two types of learning algorithms that can directly obtain the parameters of the unknown time-varying nonlinear system. Firstly, all neural network weights in HWNN are adapted using a Back Propagation based Gradient algorithm (BPG). While, the second, namely Recursive Least Square Back Propagation based Gradient method (RLSBPG), is derived from the BPG algorithm to achieve the parametric estimation of Hammerstein scheme where the remaining parameters are estimated by the least-squares approach based on fuzzy technique to ameliorate the estimation quality. The convergence analysis of the algorithms is presented, and their performances are tested through a simulation study of a nonlinear hydraulic process.
Keywords: Nonlinear stochastic systems, Hammerstein-Wiener mathematical model, Hammerstein-Wiener Neural Network, BPG learning algorithm, RLSBPG learning algorithm, Fuzzy technique, convergence analysis, hydraulic process.
Fast Recognition and classification of static and dynamic signs for Persian Sign Language
by Milad Moghaddam, Manoochehr Nahvi, Negin Pourmomtaz
Abstract: Sign language(SL) is the most effective way for communication between deaf and hearing-impaired people. Since most non-deaf people are not familiar with SL, a vision-based translator/interpreter can be a very useful tool to enhance their communication. This paper presents a recognition system for Persian static and dynamic signs. The system is designed based on proposed modified non-linear kernel-based fast feature extraction methods, consisting of hybrid kernel principal component analysis and hybrid kernel discriminant analysis. For recognition of dynamic signs, the proposed feature extraction method is employed in association with spatio-temporal approach. The proposed methods are examined and compared with several existing feature extraction methods, including linear and non-linear kernel-based methods. The experiments indicate that our feature extraction methods significantly outperform other methods and reduce computational time while they achieve high recognition rates. Our simulations achieved a promising classification accuracy rate of 96.78% and 96.99% on static and dynamic signs, respectively.
Keywords: Human-computer interaction; Persian Sign Language recognition; Hand Gestures; Kernel-based feature extraction; Static signs; Dynamic signs.
A Parallel MultiObjective Swarm Intelligence Framework for Big Data Analysis
by Amr AbdelAziz, Kareem A.Ghany, Taysir Soliman, Adel Sewisy
Abstract: Nowadays, Data generated from smart devices, such as sensors, computers, and tablets in huge volumes, different formats, and in a high pace, which comply with Big Data characteristics. Big Data led to the emergence of new technologies, such as Hadoop and Spark. They provide both Big Data management and analysis. AnalyzingrnBig Data is a time consuming process when using traditional data mining techniques. Swarm Intelligence (SI) are population-based meta-heuristic methods inspired from the behavior of bird flocks in nature. Particle swarm and ant colony optimization are examples of these methods. They have been combined with data mining techniques to solve MultiObjective Problems (MOPs) in small and medium sized data, presenting good performance. However, when applying SI methods to solve MOPs in Big data, an efficient scalable framework will be required, such as MapReduce. MapReduce is a programming framework developed to execute tasks in parallel. In this paper, we summarize new technologies proposed to manage and analyze Big Data. We present how meta-heuristics can be adapted with Big Data technologies. We characterize problems arose when analyzing MO Big Data problems, in addition to proposed methods to overcome these problems, giving examples in Bioinformatics field.
Keywords: Big Data; Big Data Analysis; Data Mining; Particle Swarm Optimization;rnMultiObjective Optimization; MapReduce; Spark.
Age Identification of Chinese Rice Wine using Electronic Nose
by Wei Ding, Peiyi Zhu, Ya Gu
Abstract: This paper is concerned with the identification of the age of Chinese rice wine. To address with this problem, a new electronic nose system with the multivariate analysis method based on the artificial olfactory technique is developed. First, four features are extracted to represent the dynamic behavior of the signal that is generated from the array of the Taguchi Gas Sensor (TGS) deployed in the volatile substance of the rice wine. Then, the principal component analysis (PCA), the linear discriminant analysis (LDA) and the error back propagation neural network (BPANN) are combined to build a model for the identification of the age of Chinese rice wine. The results show that the LDA model fails to distinguish the Chinese wine with a one-year age difference in the proposed electronic nose system, whose accuracy of training and prediction are 98.44 % and 96.88%, respectively. By contrast, the optimized BPANN model is capable of identifying the age of the Chinese wine and achieves the accuracy of 100% in the training and the prediction sets. It is verified that the self-designed electronic nose with the optimized BPANN is valuable on the application of the age prediction of Chinese rice wine.
Keywords: Age identification, Chinese rice wine, Electronic nose system, Multivariate analysis.
Special Issue on: Computational Intelligence and Applications
Intelligent game-based learning: an effective learning model approach
by Tanzila Saba
Abstract: Game-Based Learning (GBL) broadly refers to the use of video games applications to support teaching and learning processes. This research focuses on the concept of GBL in the context of stimulating interest in the field of computer science education specifically. In contrast to theoretical learning, GBL is a practical learning approach that is meant to teach and be enjoyed at the same time. Additionally, a GBL model with visual features has been proposed and tested. Promising feedback has received from learners through the post conducted surveys. The research findings exhibit that GBL is an effective methodology in transferring knowledge, enhancing learning, and making the learning a more enjoyable process in computer science studies than just the theoretical approach.
Keywords: binary games; game-based learning; logical games; theoretical learning.
Special Issue on: Theoretical Advances and Applications of Computational Intelligence
Intelligent system for feature selection based on rough set and chaotic binary grey wolf optimization
by Ahmad Taher Azar, Ahmed M. Anter, Khaled M. Fouad
Abstract: Feature selection (FS) has non-trivial role in supervised learning; like classification, for many causes. FS aims at facilitating the model processes and reducing the computation time. In feature selection, trivial features are eliminated from the data to produce transparently and comprehensibly a model. Furthermore, feature selection process can decrease a noise data, wherefore; feature selection enhances the accuracy measure of classification process. This paper proposes a robust hybrid dynamic model for feature selection; called RS-CBGWO-FS. RS-CBGWO-FS is a combination of both rough set (RS), chaos theory and binary grey wolf optimization (BGWO). GWO parameters are estimated and tuned by using ten various chaotic maps. Five complex medical datasets are used in the evaluation experiments. The selected datasets have various uncertainty attributes and missing values. The overall result indicates that RS-CBGWO-FS with the singer and piecewise chaos maps provide the better effectiveness, minimal error, higher convergence speed and lower computation time.
Keywords: Grey wolf optimisation; meta-heuristics; rough set theory; chaos theory; feature reduction and selection; data classification.
Intelligent approach for large-scale data mining
by Khaled M. Fouad, Doaa Elbably
Abstract: Large-scale data mining has become a very difficult issue using traditional methods because of the data complexity is very high. Therefore, many techniques rely on correction; such as statistics, data mining and data science, can be used to analyse large-scale datasets. The researchers continue to improve these techniques and develop new techniques, particularly in response to the requirements for large-scale data analysis. In the proposed approach, an integration of three methods; optimised principal component analysis (OPCA), optimised enhanced extreme learning machine (OEELM) and stratified sampling, called OPCA-EELM2SS, is presented to provide intelligent and enhanced large-scale data mining. By using OPCA, a proper number of principal components (PCs) is achieved by using particle swarm optimisation (PSO), which is necessary to transform the high dimensional spaces into low dimensional data. OPCA provides a good representation of large-scale datasets by using the stratified sample (SS); sample with a perfect distribution of categories, to select the optimal components with the minimum computation time. By using OEELM, the optimal number of hidden nodes (HNs) in ELM is exploited to build a single hidden layer feedforward neural network (SLFN) to obtain the optimised enhanced ELM. The proposed approach is tested by using 19 benchmark datasets. The experimental results demonstrate the effectiveness of the proposed approach by performing different experiments for classical PCA and independent component analysis (ICA), which are integrated with the enhanced ELM using different evaluation criteria. For more reliability, the proposed approach is compared with many previous methods, which are used in the domain of selecting the optimal number of hidden nodes of ELM and in the domain of dimensionality reduction by feature selection techniques.
Keywords: principal component analysis; extreme learning machine; particle swarm optimisation; large-scale data mining.
Arabian horse identification based on whale optimised multiclass support vector machine
by Ayat Taha, Ashraf Darwish, Aboul Ella Hassanien, Ahmed ElKholy
Abstract: The protection of the Arabian horse from extinction and conservation of the purity of this oldest breed needs an approach for identification. The classical identification approach causes harm, duplication, and theft, and is liable to fraud for the Arabian horse, so the biometric identification approach such as muzzle print is considered the solution for the Arabian horse identification which is effective and animal welfare. In this study, biometric identification approach for Arabian horse identification is proposed based on the optimised MultiClass Support Vector Machine (MCSVM). The identification approach is performed in three phases, feature extraction, classification, and optimise the classification. The feature extraction phase uses Histogram of Oriented Gradient (HOG) to extract feature vectors from the muzzle print image of the Arabian horses, which is then stored in the database with its labels. The second phase is the classification phase, which uses MCSVM for training and testing classification. Finally in the optimised MCSVM phase, three different swarms, Particle Swarm Optimisation (PSO), Gray Wolf Algorithm (GWA) and Whale Optimisation (WO) are used to optimise the MCSVM parameters to enhance the identification accuracy of the Arabian horse. The results obtained show that the polynomial kernel of MCSVM achieves higher accuracy of 93.2% compare with linear and Radial Basis Function (RBF) kernels; this increased to 97.4% with WO algorithm, which achieves better accuracy than PSO and GWA.
Keywords: Arabian horse identification; histogram of oriented gradient; multiclass support vector machine; whale optimisation algorithm.
An efficient binary whale optimisation algorithm with optimum path forest for feature selection
by Ahmed Samy, Khalid M.Hosny, Abdel Nasser H.Zaied
Abstract: The process of feature selection is an essential process in image processing and computer vision applications. This process aimed to find the most representative features from the extracted features. Generally, the reduced selected features improve the efficiency of the used classifier and increase the classification rate. Also, this process reduced required time for classification. In this paper, a new binary whale optimisation algorithm for feature selection is proposed. This optimisation algorithm based on behaviour of whales. The optimum-path forest (OPF) technique is used as an objective function. This function is much faster than the other classification techniques. The proposed algorithm binary whale optimisation algorithm is evaluated using five well-known datasets of colour images. The proposed algorithm is outperformed over the existing binary whale optimisation algorithms. The performance of the proposed algorithm is compared with the well-known optimisation algorithms such as Particle Swarm Optimisation Algorithm (PSOA), Firefly Algorithm (FFA), Gravitational Search Algorithm (GSA), Binary Harmony Search (BHS), Binary Clonal Flower Pollination Algorithm (BCFA), Binary Cuckoo Search Algorithm (BCSA), and Binary Bat Algorithm (BBA), where the obtained results clearly show the superiority of the proposed algorithm in terms of classification accuracy, number of selected features and execution times.
Keywords: WOA; OPF; feature selection.
Time sensitive clustering evolving textual data streams
by Mohamed Ammar, Minyar Sassi Hidri, Adel Hidri
Abstract: Clustering a stream of text documents is an emerging subject of interest since it is widely used in analysing the content in social media and e-journals. The aim is to find a certain structure for unlabeled data based on a similarity criterion. However, few works have focused in this field and falls in this perspective, that's why a new document clustering approach adapted to a stream of text data and test it on news articles datasets is proposed. A distributed representation of words is used, and a bottom-up approach is proceeded to represent documents as vectors on a unit hyper-sphere. The proposed approach gains its roots from the SPherical K-Means (SPKM) algorithm and its underlying mixture of von-Mises Fisher (vMF) distributions. The proposed approach yields comparable results to baseline batch algorithm for stable data streams and superior results for rapidly evolving data streams.
Keywords: natural language processing; document clustering; competitive learning; data streams; machine learning.
An implementations method for Arabic keyword tendency using decision tree
by Hassan Hashim, El-sayed Atlam, Ahmad Reda Alzighaibi, Malik Almaliki
Abstract: The concept of keywords refers to the fact that the title of a document can generally be identified by looking at specific keywords or sentence in that document. Generally, keyword recurrences change over certain periods of time. Traditional approaches estimated classes (increasing, relatively constant, and decreasing) that indicate keywords attributes changes in a document over certain periods of time using a decision tree. Furthermore, all earlier approaches are based on keywords in English and French languages. Therefore, the extension of keywords to other language such as Arabic could strengthen further researches in this domain. This paper introduces a new method to extract Arabic keywords from corpora based on their recurrences changes in a document over given periods of time using a decision tree. The new approach is applied on a new dataset field (computer science) which makes it different from traditionally used methods. For training data, we extracted the attribute values of 450 nouns that were collected from 2,825 articles of Arabic Wikipedia dumps and Alhayah newspaper (2015-2017) that discussed computer science topics. For testing data, 480 proper nouns were extracted from 975 articles of Arabic Wikipedia dumps and Alhayah newspaper (2015-2018) and then classified using a decision tree approach. The comparison between the manually classified results and the evaluation of the decision tree results reveals that F-measures of decreasing, relatively constant and increasing classes were 0.188, 0.789, and 0.877, respectively. This indicates that the effectiveness of this method is achieved.
Keywords: Arabic Wikipedia dumps; Alhayah news; time-changing; keywords attribute; decision tree.
A multifunctional BCI system for exigency assistance and environment control based on ML and IoT.
by Mayank Singh, Indu Saini, Neetu Sood
Abstract: Brain-Computer Interface (BCI) is a modality to create an interface which sustains a direct and bidirectional communication between the brain and computers. The major disadvantage in implementing such systems is its bulky design and system cost. This paper implements a simple multifunction BCI system for the environment control and exigency assistance by just using a single channel Electroencephalogram (EEG). In the proposed model environment control is achieved through the Internet of Things (IoT) as a function of the cognitive state of the person while for exigency assistance served as a function of Event-Related Potential (ERP) generated during oddball paradigm. Hardware based on the Arduino microcontroller (AMC) is designed for controlling the environment. Different Machine Learning (ML) algorithms are used and observed for training the classifiers. Weighted k-Nearest Neighbour (Wk-NN) algorithm trained classifiers deliver the best results, with an accuracy of 98.3% to detect ERP and 95% accuracy for cognitive state detection. The simple, low-cost prototype system was implemented in practice for environment control and exigency assistance.
Keywords: brain computer interface; EEG; event related potential; machine learning; IoT; IFTTT; Arduino microcontroller; GUI.
Special Issue on: Advanced Big Data and Artificial Intelligence Technologies for Edge Computing
An Improved Hybrid Error Control Path Tracking Intelligent Algorithm for Omnidirectional AGV on ROS
by Yaqiu Liu, Hui Jing
Abstract: In order to improve the accuracy and stability of intelligent omnidirectional AGV path tracking based on mecanum wheels, an improved intelligent hybrid error control path tracking method is proposed. The method combines the angular velocity of the intelligent AGV vehicle with the error correction of longitudinal velocity as the coupling estimation error. The coupling estimation error and the improved pure tracking algorithm are combined as the lateral control of the intelligent AGV car, while the PID control is used as the vertical control to further reduce the error interference. The ROS simulation results showed that compared with the tracking effect of the traditional pure tracking algorithm, the tracking path of the improved intelligent hybrid error control path tracking algorithm is closer to the real path, which greatly improved the trajectory deviation phenomenon, and the path tracking accuracy and stability are significantly improved.
Keywords: Mecanum Wheel; Path Tracking; Improved Hybrid Error Control; Coupling Estimation Error; Intelligent Omnidirectional AGV; Pure Pursuit; ROS
Special Issue on: Advances in Computer Graphics and Imaging
Research on the Design of Visual Interface in Information Visualization
by Guangtao Ma, Tao Liu, Yang Zhou, Jun Li
Special Issue on: Computer Technology Applications in the Immersed Tunnel Engineering
Experimental and modelling study on the response of mooring container ships in port under medium to long period waves
by Zhu Feng, Geng Ying, Miao Hui
Abstract: For understanding the influence of medium to long period waves on the motion and mooring force response of ships and knowing the sensitivity of wave period and wave direction to the dynamic response of ships, the hydrodynamic analysis of three typical moored container ships under wave interaction is carried out based on potential flow theory. The response amplitude operators of ships are calculated first in the analysis, and the influences of wave period and direction on ships are discussed. The comparison of calculated and experimental results shows that the numerical calculation is more suitable for simulation of long-period wave, as the dynamic response of ship is larger, but more accurate. For the larger ship, the peak response period of the mooring system usually reaches 100 s because the mooring stiffness is relatively small compared with the ship's inertia. So when wave period extends, the ship's motion response increases almost linearly. The calculation results also show that the symmetrical mooring arrangement and the similar mooring stiffness can effectively reduce the inhomogeneity response of mooring forces. In addition, the ship's motion and mooring force response can reach a minimum value at a special angle between ship and wave.
Keywords: mooring system; medium to long period wave; motion response; mooring force; potential flow; numerical simulation.
Research on artificial synthetic seismic record based on adaptive positive definite least squares method
by Liangzhi Chen, Jie Qin, Yongchang Lu
Abstract: Earthquake is a typical natural stochastic process, and the ground movement caused by earthquake cannot be accurately predicted. The traditional method of generating an artificial seismic record is based on the empirical and least squares method. This method is suitable for general geology, but has poor applicability and low efficiency for unconventional cases. An adaptive regression method is proposed in this paper to synthesise an artificial seismic record, and the effect of seismic duration on response spectrum is considered. A numerical model is further established to verify the effectiveness of the artificial seismic record. The results show that the structure dynamic response under the synthesised artificial seismic record in this paper is close to the natural seismic record, which has a significant engineering reference value.
Keywords: seismic record; artificial synthesis; adaptive regression; positive definite; response spectrum.
Vortex dislocation characteristics of a dual-step cylinder in low-Re flow
by Chunning Ji, Xiaoxiao Yang, Yuting Cui, Weilin Chen
Abstract: Flow around a dual step cylinder for D/d = 2 and L/D = 5 at a low Reynolds number of ReD = 200 is numerically investigated utilizing the immersed boundary method. The vortex dislocation caused by two steps is investigated. It was found that a pair of streamwise vortex the center vortex exists at the downstream of the large cylinder. Meanwhile, due to the barrier effect of the center vortex, a very weak L-cell at the downstream behind the centre of large cylinder is also observed. In a complete dislocation cycle, three positive and negative half-loop connections appear alternately, and this cycle is not only related to the phase realignment of the different vortex cells, but also to the connection mode realignment. The variations and spectra of three velocities (U, V and W) at different downstream locations are analysed in detail. It was found that the lateral velocity is always dominated by the frequency of vortex shedding in the whole downstream. While as the streamwise velocity travels downstream, vortex shedding frequency is gradually dissipated, only leaving lower frequencies of dislocation.
Keywords: vortex dislocation; dual-step cylinder; wake; low-Re flow.
A large-scale field test on sand compaction piles including three-dimensional numerical analysis
by Hongtao He, Jianyu Li, Yougao Lin
Abstract: This paper presents a large-scale field test study performed on soft ground improved by a set of 216 sand compaction piles in a mesh of 12
Keywords: field test; sand compaction piles; ground improvement; three-dimensional numerical analysis.
Numerical simulation on offshore artificial island cofferdam of Hong Kong-Zhuhai-Macao bridge
by Tingting Wang, Heng Liang, Zhihao Peng
Abstract: The deep burying steel cylinder structure has the characteristics of gravity structure and pile foundation structure, the mechanism and design method still being in its infancy. Based on the offshore artificial island of Hong Kong-Zhuhai-Macao Bridge, spatial 3D elastic-plastic numerical analysis of the island wall structure was established, and the stability and deformation characteristics of the deep-buried steel cylinder cofferdam was studied throughout the rapid island construction process. laws. Stability calculation of the deep-buried steel cylinder on deep soft foundation was carried out based on the embedded steel cylinder theoretical formula in OCDI, and the measured values in situ was summarized. The results show that the steel cylinder displacement using 3D numerical simulation method is consistent with the measured data, and much larger than that using 2D equivalent calculation method. The safety stability characteristics of 2D theoretical calculation is consistent with the 3D numerical simulation and measured data, indicating that it is suitable for analyzing the stability of deep-buried steel cylinders on soft foundations. The instability judgment of the buried steel cylinder and the selection criteria of the bottom bearing layer are also given.
Keywords: Hong Kong-Zhuhai-Macao bridge; artificial island; deep-buried large cylinder; deep soft foundation; stability.
Prediction on hydroelastic responses of very large floating structure with the eigenfunction expansion-matching method
by Zhinan Wan, Gangjun Zhai, Yong Cheng
Abstract: This paper investigates the hydroelastic responses of a mat-like, rectangular very large floating structure with analytical method. The very large floating structure is considered as a two dimensional thick plate and the wave linearity theory are employed in this paper. The flow field is divided into three regions and the eigenfunction expansion-matching method is applied in solving velocity potential in each region, including diffraction potential and radiation potential. and then the the Rayleigh-Ritz method is used to solve the elastic equation of motion. The analytical method has the advantages of high speed, small memory and high precision, and verified by comparing with the published numerical and experimental results. The elastic deformation and wave exciting force of the very large floating structure are computed and the effects of water depth, wavelength, draft and stiffness on the elastic deformation of the very large floating structure are further discussed in this paper
Keywords: very large floating structure; eigenfunction expansion-matching method; Rayleigh-Ritz method; hydroelastic response.
Special Issue on: Machine Vision and Computational Intelligence in Recent Industrial Practice
Robust Skin Segmentation using Color Space Switching
by Ankit Chaudhary, Ankur Gupta
Special Issue on: Xxxx
A Query Driven Method of Mapping from Global Ontology to Local Ontology in Ontology-based Data Integration
by Haifei Zhang