International Journal of Computer Applications in Technology (12 papers in press)

Regular Issues

• FPGA implementation and Multisim simulation of a new four-dimensional two-scroll hyperchaotic system with coexisting attractors  
  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  
  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  
  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.
  
  
• Research on machine reading comprehension for BERT and its variant neural network models  
  by Yanfeng Wang, Ning Ma, Wenrong Lv 
  Abstract: Currently, machine reading comprehension model is mainly models primarily rely on the basis of LSTM network networks with the gate mechanism. In the present this study, we employ BERT and its variant pre training-trained language model are used models to conduct research and experiment experimentation on the DuReader dataset. It is found We find that improved mask methods enhanced masking techniques, such as full -word mask masking and dynamic mask masking, can notably significantly enhance the model's performance of the model in machine reading comprehension tasks. Therefore, the ROUGE-L and BLEU-4 values of Consequently, the best RoBERTRoBERTa-wwm-ext model on the test set are achieves ROUGE-L and BLEU-4 scores of 51.02% and 48.14% separately, on the test set, respectively, which are 19.12% and 8.94% higher than the benchmark model. In addition, in view of the problem that the, Moreover, addressing the issue of suboptimal model performance is not optimal when the data dealing with large-scale is large data and the relatively dispersed effective information is relatively dispersed, this paper adopts employs a three-step preprocessing of approach for the dataset.
  Keywords: machine reading comprehension; BERT pre-training language model; masking mode.
  DOI: 10.1504/IJCAT.2024.10063844
   
  
• YOLO-based gripping method for industrial robots  
  by Wei Gao 
  Abstract: With the current development of industrial intelligence in society, new challenges have been created for traditional industrial robots, and grasping is a significant capability of robots. The problem of robot grasping has been a famous research problem at home and abroad. With the rise of deep learning technology in recent years, it has been applied to various fields because it can extract better features. In this paper, two target detection models are optimized, and the Faster R-CNN target detection model is optimized to adjust the network structure, the scale size of anchors, the target classification, and the position regression structure. The YOLO-v2 target detection model is optimized, and the Darknet-19 feature extraction network structure and the loss function are adjusted. The experimental results demonstrate that the target detection network learns useful image features, and the grasping system can complete the autonomous grasping task.
  Keywords: convolutional neural network; target detection; automatic grasping.
  DOI: 10.1504/IJCAT.2023.10067187
   
  
• An unsupervised video summarisation method based on temporal convolutional networks  
  by Ke Jin, Haoran Li, Hui Li, Qichuang Liu, Rong Chen, Shikai Guo 
  Abstract: Video summarisation automatically select a sparse subset of video frames that best represent the semantic content of the input video. Previous work mainly used Long Short-Term Memory (LSTM) networks to learn how to assess the importance of each video frame and then select appropriate frames to compose a video summary. However, these models still represent shortcomings, such as limited memory capacity in handling long-term dependencies, and extended training time. Therefore, we present a deep video summarisation model, named TCN-SUM, which centres around Bi-TCN and models the frame sequence. TCN-SUM consists of three modules: frame selection module incorporates both Bidirectional Temporal Convolutional Network (Bi-TCN) and self-attention to model inter-frame dependencies, video reconstruction module reconstructs the original video based on the summary, and discriminator module measures the similarity between the original and reconstructed videos. Experimental studies on two benchmark datasets demonstrates that TCN-SUM outperforms state-of the- art techniques, achieving superior performance in unsupervised approaches and showing competitiveness compared to supervised methods.
  Keywords: Bi-TCN; video summarisation; self-attention; LSTM.
  DOI: 10.1504/IJCAT.2024.10067536
   
  
• Machine learning applied in blood laboratory database for identification of an obesogenic/ diabetogenic diet consumption: a preclinical modelling approach  
  by Laize Dariele De Lima Trindade, Diovana Gelati De Batista, Maira S. Brigo, Matias N. Frizzo, Rafael Z. Frantz, Fabricia Roos-Frantz, Thiago Gomes Heck, Sandro Sawicki 
  Abstract: Routine blood tests usually do not show changes during the development of diseases, nor indicate the quality of food being digested. In this study, we tested whether it is possible to use Machine Learning techniques to identify the type of diet intake from laboratory tests. For doing so, seven different machine Learning techniques were used to analyze CBC data, with 15 variables from 44 laboratory animals consuming either a standard diet or a high fat diet. In the analyses, the metrics accuracy, precision, recall and f1-score were considered. The results presented by the techniques proved effective in identifying the type of diet, with accuracy above 88% making it a good alternative to support decision-making by health professionals.
  Keywords: obesity; chronic non-communicable diseases; hematological parameters; artificial intelligence; machine Learning.
  DOI: 10.1504/IJCAT.2024.10068585
   
  
• Artificial intelligence-based drug structure extraction and representation in chemistry documents  
  by Xin Xu, Jiaheng Pan, Dazhou Li 
  Abstract: The feature extraction and representation of chemical bond linear molecular structure from chemistry publication images is of great significance to rediscover the properties of chemical structure, but the rule-based method and the existing deep learning methods are facing the problem of low recognition rate. This paper presents ChemRAL, an automatic conversion model for chemical molecular images and identifiers. ChemRAL employs an encoder-decoder architecture with a ResNet residual network for image feature extraction, and an attention-based LSTM long-term memory network for converting molecular structure images into chemical identifiers. Comparative evaluations demonstrate that the ChemRAL model outperforms existing methods in terms of cross entropy loss and accuracy of the longest common subsequence. The conducted experiments have successfully showcased the advancements achieved by the ChemRAL model. The findings unequivocally indicate that ChemRAL not only enhances the precision and effectiveness of molecular image feature extraction and representation but also provides a significant benchmark.
  Keywords: artificial intelligence; drug discovery; drug structure extraction and representation; image characteristics extraction; drug information representation; LSTM.
  DOI: 10.1504/IJCAT.2024.10068749
   
  
• Automatic synthesis and control of dance movements based on music characteristics  
  by Panle Yang 
  Abstract: With the continuous development of music processing technology in recent years, the automatic synthesis and control of dance movements based on music has gradually become a research hotspot in the field of dance synthesis. To improve the authenticity of synthetic dance based on music, this study proposed to use transition frame interpolation and cubic spline interpolation algorithm to study the fluency and path control of synthetic dance. The results show that the fluency of the synthesized dance based on the method proposed in this study is similar to the original dance movement, and the dance movement path can be effectively controlled. It is hoped that this study can provide some reference for the current research on automatic synthesis and control of dance movements based on music characteristics.
  Keywords: musical characteristics; dance movements; automated synthesis; transition frame interpolation method; cubic spline interpolation algorithm.
  DOI: 10.1504/IJCAT.2024.10068779
   
  
• Assisted English Oral Teaching with Mouth Recognition Technology  
  by Shaoli Xiong, Rui Cong, Siew Eng Lin, Chunyan Ruan 
  Abstract: Deep learning-based speech emotion analysis has been widely applied in English oral teaching. Due to the close relationship between oral pronunciation and mouth shape, mouth recognition has received increasing attention to assist speech recognition. To effectively improve the effectiveness of English oral teaching, this paper constructs an efficient emotion analysis model by introducing human mouth-shape features. Specifically, we first use the Dlib tool to locate 68 facial landmarks and crop mouth-associated landmark information. To improve the extraction of mouth landmark features, we introduce the spatiotemporal graph convolutional network which can effectively mine spatial and temporal features from landmark information. In addition, to effectively model local and global dependencies, we utilise Focal-Transformer for speech feature extraction. To verify the effectiveness of our proposed model, we conducted extensive comparative experiments on two publicly available multimodal sentiment analysis datasets and the self-built English oral teaching dataset. All the experimental results confirm that our proposed model obtains a higher performance compared to other deep models.
  Keywords: deep learning; mouth recognition; English oral teaching; multimodal emotion analysis; facial landmarks; Focal-Transformer.
  DOI: 10.1504/IJCAT.2024.10068792
   
  
• Building heating management based on deep learning to strengthen intelligent building design  
  by Yipeng Wang, ShiLin Zhang 
  Abstract: Building heating systems based on deep networks plays an important role in intelligent urban construction, providing a comfortable environment for residents. Accurate heating prediction can help operation and maintenance personnel grasp the energy demand of buildings in advance, avoiding unnecessary energy waste. To improve the long-term dependence between multiple variables, LSTM-based networks have been widely used in building heating prediction tasks. However, local dependencies cannot be utilized, and the model requires a large amount of computation. Therefore, this paper proposes a new Swin Transformer-based model for building heating system prediction. In addition, We use convolution operations for local dependency modeling. We conducted extensive experiments on our self-built dataset. All experimental results show that the proposed model achieves higher performance than LSTM and Transformer models.
  Keywords: building heating system; deep learning; sparse self-attention; LSTM; Transformer.
  DOI: 10.1504/IJCAT.2024.10068871
   
  
• Inverted U-shaped influence of informal field-based learning on the continuous adoption of artificial intelligence technology  
  by Yanhong Guo, Zixuan Zhang, Hua Zhang, Yifang Dong 
  Abstract: The application of Artificial Intelligence Technology (AIT) in organisations is becoming increasingly widespread. It has greatly improved efficiency and effectiveness in management practices. Through the investigation of 1003 employees in China, this study analyses the mechanism of Informal Field-Based Learning (IFBL) on Continuous Adoption of Artificial Intelligence Technology (CAAIT). The results reveal: (1) there is an inverted U-shaped relationship between IFBL and CAAIT; (2) employees helping behaviour plays an intermediary role between IFBL and CAAIT; (3) teams work passion moderates the inverted U-shaped relationship between IFBL and employees helping behaviour and (4) teams work passion also moderates the mediating effect played by employees helping behaviour between IFBL and CAAIT. This study expands the theoretical basis of CAAIT, and the results provide a non-linear perspective on the antecedent variables of CAAIT for future research.
  Keywords: informal field-based learning; continuous adoption of artificial intelligence technology; employees’ helping behaviour; team’s work passion.
  DOI: 10.1504/IJCAT.2024.10068872