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 Articles will not be published until the final proofs are validated by their authors.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.

International Journal of Computer Applications in Technology (25 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
  • Electronic management of enterprise accounting files under the condition of informatisation   Order a copy of this article
    by Xia Liu, Zhengfu Zhao, Yun Zhao 
    Abstract: With the rapid development of computer information technology, the work of accountants has gradually evolved to an electronic trend, and the management of accounting files has also undergone great changes. Combining with the current development trend of informatization, this paper has discussed the electronic management mode of enterprise accounting files under the condition of informatization. Combined with the latest information technology, an enterprise electronic accounting file system is established, and the research and development system is compared with the traditional paper accounting file management. The results have shown that the retrieval and query time of traditional paper accounting files is close to 2 hours. After the implementation of the electronic accounting file system, the retrieval and query time of files can be completed in only 2 minutes, and the query efficiency of files has been increased by nearly 60 times.
    Keywords: accounting files; system development; financial management; electronic management.
    DOI: 10.1504/IJCAT.2024.10062854
  • Application of artificial intelligence in enterprise human resource management and employee performance evaluation   Order a copy of this article
    by Qingguo Nie 
    Abstract: With the rapid development of artificial intelligence technology, significant breakthroughs have been made in its application in many fields. Especially in field of enterprise human resource management and employee performance evaluation, AI has demonstrated its powerful ability to optimise and improve performance. This study explores the application AI in enterprise human resource management and how to use AI to evaluate employee performance. The research includes analysing and comparing existing AI-driven human resource management models, evaluating how AI can help improve employee performance and leadership styles, and designing and developing human resource management computer systems for enterprise employees. Through empirical research and case analysis, this study proposes a new AI-optimised employee performance evaluation model and explores its application and effect in practice. At present, artificial intelligence technology has been widely used in various fields of daily life, especially in corporate human resource management, providing better support for the development of enterprises.
    Keywords: artificial intelligence; enterprise human resource management; employee performance evaluation; AI optimised human resource model.
    DOI: 10.1504/IJCAT.2024.10062884
  • Numerical simulation of financial fluctuation period based on non-linear equation of motion   Order a copy of this article
    by Guixian Tian 
    Abstract: The traditional numerical simulation method of financial fluctuation cycle does not focus on the study of nonlinear financial fluctuation, but has problems such as high numerical simulation error and long time. In order to solve this problem, this paper introduces the nonlinear equation of motion to optimize the numerical simulation method of financial fluctuation cycle. A comprehensive analysis of the components of the financial market, the establishment of a financial market network model, and the acquisition of relevant financial data under the support of the model. Based on the collection of financial data, set up financial volatility index, measuring cycle, the financial wobbles, to establish the nonlinear equations of motion, financial wobbles, The simulation results show that, compared with the traditional method, the numerical simulation of the proposed method has high precision, low error and short time, which provides relatively accurate reference data for the stable development of regional economy.
    Keywords: non-linear equation of motion; financial fluctuation; fluctuation period; numerical simulation.
    DOI: 10.1504/IJCAT.2023.10063134
  • Research on machine reading comprehension for BERT and its variant neural network models   Order a copy of this article
    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
  • Rainfall rate prediction using recurrent neural network with long short-term memory algorithm: Iraq case study   Order a copy of this article
    by Qahtan Yas, Younis K. Hamead 
    Abstract: Rainfall is one of the primary sources of water for many countries in the world. Recently, the problem of variant rainfall rates has emerged in most countries, especially in the Middle East, due to the phenomenon of global warming. Consequently, this phenomenon affected all aspects of human life, especially the agricultural sector. To address this problem, machine learning algorithms were adopted to predict rainfall in Al-Diwaniya city in Iraq. A recurrent neural network (RNN) algorithm based on long short-term memory (LSTM) technology was applied. This technique was implemented by calculating the weight of previous observations or time shift variables in the form of time series based on the simulating neural networks. This network is trained to reach the minimum mean square error (MSE) rate by adjusting the values of the estimated weights for the chosen model structure. The finding of the study showed the prediction values for LSTEM are better than the RNN algorithm according to the MSE values that are obtained.
    Keywords: recurrent neural network; long short-term memory; rainfall rate; machine learning; Iraq.
    DOI: 10.1504/IJCAT.2024.10064526
  • Information scheduling method of big data platform based on ant colony algorithm   Order a copy of this article
    by XinDi Tong, YanMing Wan 
    Abstract: This paper proposes an information security scheduling method for big data platform based on ant colony algorithm. First, collect big data platform information and conduct noise reduction and compression processing on the information. Then, determine the priority of the big data platform information scheduling task, refer to the task priority, and use the ant colony algorithm for task scheduling and resource allocation. Finally, build the information scheduling function of big data platform, use the pheromone update mechanism to constrain the scheduling function, and achieve the goal function solution through the volatilization of ant colony pheromone, so as to achieve the safe scheduling of information. The experimental results show that the data acquisition accuracy of the proposed method can reach 0.95, the transmission delay can not exceed 0.3s, and the information security can reach 99.99%, effectively improving the information security scheduling effect of big data platform.
    Keywords: ant colony algorithm; information denoising and compression; big data platform; information scheduling; task priority.
    DOI: 10.1504/IJCAT.2024.10064527
  • Study on online English learning resource push based on Bayesian inference   Order a copy of this article
    by Wenfeng Zhang 
    Abstract: Currently, there are issues with poor customer satisfaction, unsatisfactory push results, and low rationality in the push and distribution of online English learning resources. Therefore, this paper proposes online English learning resource push method based on Bayesian inference. Firstly, obtain online English learning resource data and classify online learning resource data. Then, by mining and analyzing learner learning data, clustering algorithms are used to locate the learner's learning style and infer the learner's learning style. Finally, based on Bayesian inference, a naive Bayesian classifier is designed, and a network English online learning resource push model is designed to achieve network English online learning resource push. Through relevant experiments, it has been confirmed that the customer satisfaction of this method varies from 96.0% to 99.8%,the push reliability varies from 90.5% to 99.8%, and the resource push recall rate is 99.9%, which has the characteristic of good push effect
    Keywords: Bayesian inference; online English; learning resource push; classify; clustering algorithm; naive Bayesian classifier.
    DOI: 10.1504/IJCAT.2024.10064528
  • A social network user behaviour data recommendation system based on fuzzy partition clustering   Order a copy of this article
    by Han Ge, Shumin Ren, Hongliang Zhang 
    Abstract: To address the problems of low recommendation accuracy and recall in existing recommendation methods, this paper proposes a social network user behavior data recommendation system based on fuzzy partition clustering. Firstly, design the hardware of a social network user behavior data recommendation system. Secondly, collect topology data of social network user behavior and extract preference features of social network users browsing certain category label content. Once again, construct a fuzzy partition clustering sample grid to cluster social network user preference features. Finally, based on the Pearson similarity algorithm, social network user behaviour data recommendation is implemented. The experimental results show that the proposed recommendation system has an average accuracy of 90% and an average recall rate of 90.83%, indicating good application performance.
    Keywords: fuzzy partition clustering; social network users; user behaviour; recommendation system; Pearson similarity.
    DOI: 10.1504/IJCAT.2024.10064529
  • Deep fusion method of IoT monitoring data based on extended Kalman filter   Order a copy of this article
    by Jixiang Ding 
    Abstract: To overcome the problems of low fusion accuracy and high data loss rate in traditional IoT monitoring data fusion methods, the paper proposes a deep fusion method for IoT monitoring data based on extended Kalman filtering. Firstly, obtain monitoring data from IoT sensors and correct the frequency domain characteristics of sensor signals. Secondly, wavelet coefficients are used to remove noise from the data. Then, calculate the Kalman gain of the monitoring data. Finally, the mean value of the node state is linearised and updated to achieve deep fusion of monitoring data through the fusion value and fusion variance of the node data. The results show that the data fusion accuracy of this method can reach 96%, and the minimum data missing rate is only 3%. The fusion effect is good and has certain application value
    Keywords: IoT monitoring data; data fusion; extended Kalman filtering; sensor signal; Kalman gain.
    DOI: 10.1504/IJCAT.2024.10064530
  • Network data privacy security aggregation method based on big data pattern decomposition   Order a copy of this article
    by Qiang Yu 
    Abstract: In order to improve the hiding rate of network data privacy information and shorten the encryption and decryption time, the paper proposes a new network data privacy security aggregation method based on big data pattern decomposition. Firstly, the empirical mode decomposition method is used to divide the upper and lower envelopes and complete the decomposition processing of network data. Secondly, the Paillier algorithm is used to calculate public and private keys and encrypt network data privacy. Finally, the encrypted ciphertext and signature are sent to the aggregator for secure aggregation of network data privacy through bilinear pairing. The experimental results show that the method proposed in this paper can improve the hiding rate of privacy information in network data, and the hiding rate of privacy information is basically above 95%, and the encryption and decryption time of network data privacy is significantly shortened.
    Keywords: big data decomposition mode; network data privacy; secure aggregation; Paillier algorithm.
    DOI: 10.1504/IJCAT.2024.10064531
  • Classification method of English micro-course resources on MOOC platform based on improved decision tree algorithm   Order a copy of this article
    by Juan Wang 
    Abstract: Aiming at the problem of inaccurate classification of educational resources in application, this paper studies the classification method of English micro-course resources on MOOC platform based on improved decision tree algorithm. Firstly, using adaptive reconstruction technology and feature sequence detection technology, the storage structure model of cloud resource distribution spatial imbalance data optimization on MOOC platform is constructed. Then, using the information entropy of each attribute of English micro-course resources to determine the information gain rate of each attribute and construct a decision tree; Finally, the improved information entropy is used to optimize the decision tree and realize the classification of English micro-course resources. The experimental results show that the AUC values of the classification results of this method are all higher than 0.85, and the precision, recall and F-scale values are all higher than 0.7, so the classification accuracy of resources is high.
    Keywords: decision tree algorithm; MOOC platform; English micro-course resources; classification method; information entropy; information gain rate.
    DOI: 10.1504/IJCAT.2024.10064532
  • Adaptive recommendation method for network resources based on improved transfer learning   Order a copy of this article
    by Xinsheng Chen 
    Abstract: In order to overcome the problems of high MAE and RMSE values and long recommendation time in traditional recommendation methods, an adaptive recommendation method for network resources based on improved transfer learning is proposed. Firstly, statistical theory is used to partition network resource data, normalise and label the data characteristics globally. Then, conventional transfer learning algorithms that are typically designed for user preference are transformed into transfer learning algorithms for network resources. By adjusting the weight ratios of transfer learning, the learning results are improved. Finally, the C-CMF algorithm is applied to establish a resource adaptive recommendation process, ensuring the effectiveness of network resource recommendations through the modified processing steps. The experimental results show that the MAE values of this method range from 0.40 to 0.52, the RMSE values range from 0.40 to 0.55, and the average recommendation time does not exceed 2 s
    Keywords: improved transfer learning; network resources; adaptive recommendation; statistical theory; normalisation; C-CMF algorithm.
    DOI: 10.1504/IJCAT.2024.10064533
  • Hybrid recommendation of English online learning materials based on self-supervised learning   Order a copy of this article
    by Kelu Wang 
    Abstract: To overcome the low recall rate, precision, and satisfaction of traditional recommendation methods, a hybrid recommendation method of English online learning materials based on self supervised learning is proposed. Firstly, English learning knowledge point information is crawled to obtain user preferences for English online learning materials. Then, a multi-granularity node deletion strategy is used to enhance user representation and a self-supervised learning trainer is constructed to train English online learning materials and user preferences. Finally, a recommendation function for material design based on group representation learning is developed, and an attention mechanism is used to calculate the weighted sum of member preference representations, solving the recommendation function to obtain the final recommendation results. The experimental results demonstrate that when the English learning material is 500GB, the recall rate of this method is 99.2%, the accuracy rate reaches 99.9%, and the recommendation satisfaction can reach 99.8%.
    Keywords: self-supervised learning; English online learning materials; hybrid recommendation; multi-granularity node deletion strategy; attention mechanism.
    DOI: 10.1504/IJCAT.2024.10064534
  • Online learning data mining method based on improved fuzzy clustering   Order a copy of this article
    by Pei Li 
    Abstract: Aiming at the problems of low data mining precision, large feature classification error and slow mining speed in online learning data mining methods, a fast online learning data mining method based on improved fuzzy clustering is designed. First, analyse the internal and external factors in the process of online learning data generation. Then classify online learning data through three dimensions, determine key data features by singular value decomposition through value calculation, construct data feature extraction model, and complete online learning data feature extraction. Finally, put the online learning data in the fuzzy universe, calculate the membership of different online learning data, calculate the distance centre of online learning data according to the clustering algorithm, and then build an improved fuzzy clustering mining model to complete the rapid mining of online learning data. The results show that the proposed method has high precision and fast speed.
    Keywords: improved fuzzy clustering; online learning data; fast excavation; value; degree of membership; objective function.
    DOI: 10.1504/IJCAT.2024.10064535
  • Assisted decision making for conditional maintenance of distribution network equipment based on multi-task deep learning   Order a copy of this article
    by Zhenyu Luo, Tu Xiong, Minghui Chen, Mingzhu Kong, Chunkai Zhang 
    Abstract: In order to solve the problems of low accuracy, long time, and high cost in traditional decision-making methods, an assisted decision making method for conditional maintenance of distribution network equipment based on multi task deep learning is proposed. Install sensors on key equipment in the distribution network, combine with decision trees to obtain preliminary mining results of distribution network equipment status information, and cluster and fill in the preliminary mining information. The processed information is input into a multi task deep learning network, and the auxiliary decision-making results for distribution network equipment status maintenance are obtained through the operations of the representation layer, distribution network equipment operation status discrimination layer, maintenance period prediction layer, and multi task learning layer. The experimental results show that the maximum decision accuracy of the proposed method is 97.6%, the decision time is always below 74ms, and the total maintenance is 1.979
    Keywords: multi-task deep learning; distribution network equipment; conditional maintenance; assisted decision making; decision trees; cluster; fill.
    DOI: 10.1504/IJCAT.2024.10064536
  • Research on personalised recommendation method for English online course resources based on hybrid differential evolution algorithm   Order a copy of this article
    by Wei Zhu 
    Abstract: In order to improve personalized satisfaction and recommendation accuracy of English resources, and effectively reduce recommendation time. This article proposes a personalized recommendation method for English online course resources based on hybrid differential evolution algorithm. Firstly, collect English resource data. Secondly, matrix decomposition technology is introduced to determine the user's interest information; Then, select the naive Bayesian algorithm to classify the resources. Finally, the fitness value of the individual is calculated, and the personalised recommendation function is designed using the hybrid differential evolution algorithm. The recommendation function is solved through differential mutation, and the final recommendation result is obtained. The results show that the recommendation satisfaction of this method can reach up to 99.5%, the accuracy can reach 99.5%, and the recommendation time always does not exceed 4 seconds, effectively improving the personalized precision recommendation effect.
    Keywords: differential evolution algorithm; matrix decomposition; naive Bayes English online courses; personalised recommendations.
    DOI: 10.1504/IJCAT.2024.10064537
  • Study on travel route recommendation method based on improved ant colony optimisation algorithms   Order a copy of this article
    by Qinghua Fan  
    Abstract: The research goal is to improve the comprehensive attractiveness index of recommended routes, improve user satisfaction, and reduce road congestion time, a travel route recommendation method based on improved Ant colony optimization algorithms is proposed. Firstly, select the Scrap crawler technology for tourism data crawling. Then, construct a tourism route map model that visualizes the relationships between tourism destinations. Finally, the heuristic information and random search strategy are introduced to improve the ant colony optimisation algorithms. The improved ant colony optimisation algorithms is used to recommend travel routes, obtain the ant walking path, and extract the optimal path as the final travel route recommendation result. The experimental results show that the proposed method has a high comprehensive attractiveness index for recommended routes, with an average user satisfaction of 92.0 and a short road congestion time, fully verifying the application effect of this method.
    Keywords: ant colony optimisation algorithms; recommended tourist routes; Hadoop cloud computing technology; graph model.
    DOI: 10.1504/IJCAT.2024.10064538
  • An adaptive recommendation method for music resources based on LDA-MURE model   Order a copy of this article
    by Xiaoxing Lu 
    Abstract: To improve the quality of music resource recommendation, the paper proposes an adaptive recommendation method for music resources based on LDA-MURE model. Firstly, remove and reduce the dimensionality of music resource data, and then integrate multimodal feature fusion methods with attention networks to classify the processed music resources. Then, the strength of emotional energy and emotional positivity are introduced to estimate the human emotional state. Finally, the distribution and emotional state estimation results of different types of music themes are input into LDA-MURE model, and music resources are recommended for users based on their emotional states. According to the experiment, MEA index value of this method is always controlled within 0.2, with a coverage rate between 0.944 and 0.971, indicating that the application of this method can recommend more music resources of different types and styles, and the accuracy of the recommendation results is high.
    Keywords: music resources; noise reduction processing; dimension reduction treatment; feature classification; user emotions; adaptive recommendation.
    DOI: 10.1504/IJCAT.2024.10064837
  • Fast recommendation of literature materials in smart libraries based on improved collaborative filtering algorithm   Order a copy of this article
    by Bin Liu 
    Abstract: To overcome the issues of low accuracy and recall rate, as well as long response time in traditional recommendation methods, a fast recommendation method of literature materials in smart libraries based on improved collaborative filtering algorithm is proposed. The FCM clustering algorithm is used to cluster the knowledge in literature materials in the smart library, enabling knowledge discovery. The feature words in the knowledge texts are determined using the VSM model and TF-IDF algorithm, and the LDA topic model is employed to identify the topics in the knowledge texts. The collaborative filtering algorithm is improved through matrix factorization, and the improved algorithm is utilized for fast recommendation of literature materials in the smart library. The experimental results show that the proposed method achieves a maximum recall rate of 99.1%, a maximum accuracy rate of 98.8%, with a response time below 72 ms, indicating good recommendation performance.
    Keywords: improved collaborative filtering algorithm; smart library; literature materials; fast recommendation; VSM model; TF-IDF algorithm; matrix factorisation.
    DOI: 10.1504/IJCAT.2024.10064838