International Journal of Business Intelligence and Data Mining (24 papers in press)

Regular Issues

• An English MOOC Similar Resource Clustering Method Based on Grey Correlation  
  by Xianzhuang Mao 
  Abstract: Due to the problems of low clustering accuracy and efficiency in traditional similar resource clustering methods, this paper studies an English MOOC similar resource clustering method based on grey correlation. Using principal component analysis to extract similar resource features of English MOOC, and using feature selection methods to pre-process similar resource features of English MOOC. On this basis, based on the grey correlation method, the pre-processed English MOOC similar resource features are standardised, and the correlation degree between different English MOOC similar resource features is calculated. The English MOOC similar resource correlation matrix is constructed to achieve English MOOC similar resource clustering. The experimental results show that the contour coefficient of the proposed method is closer to one, and the clustering accuracy of similar resources in English MOOC is as high as 94.2%, with a clustering time of only 22.3 ms.
  Keywords: Grey correlation; principal component analysis method; English MOOC; feature selection; clustering of similar resources.
  DOI: 10.1504/IJBIDM.2024.10062019
   
  
• Study on Personalized Recommendation Method of English Online Learning Resources Based on Improved Collaborative Filtering Algorithm  
  by Xiuqin Zhang, Jigang Xie 
  Abstract: In order to improve recommendation coverage, a personalised recommendation method for English online learning resources based on improved collaborative filtering algorithm is studied to enhance the comprehensiveness of personalised recommendation for learning resources. Use matrix decomposition to decompose the user English online learning resource rating matrix. Cluster low dimensional English online learning resources by improving the K-means clustering algorithm. Based on the clustering results, calculate the backfill value of English online learning resources and backfill the information matrix of low dimensional English online learning resources. Using an improved collaborative filtering algorithm to calculate the predicted score of learning resources, personalised recommendation of English online learning resources for users based on the predicted score. Experimental results have shown that this method can effectively backfill English online learning resources, and the resource backfilling effect is excellent, and it has a high recommendation coverage rate.
  Keywords: improve collaborative filtering; English learning resources; personalised recommendation; matrix decomposition; K-means clustering; heuristic clustering.
  DOI: 10.1504/IJBIDM.2024.10062020
   
  
• Learning Behavior Recognition Method of English Online Course Based on Multimodal Data Fusion  
  by Liangjie Li 
  Abstract: The conventional methods for identifying English online course learning behaviours have the problems of low recognition accuracy and high time cost. Therefore, a multimodal data fusion based method for identifying English online course learning behaviours is proposed. Firstly, the analytic hierarchy process is used for decision fusion of multimodal data of learning behaviour. Secondly, based on the fusion results of multimodal data, weight coefficients are set to minimise losses and extract learning behaviour features. Finally, based on the extracted learning behaviour characteristics, the optimal classification function is constructed to classify the learning behaviour of English online courses. Based on the transfer information of learning behaviour status, complete the identification of online course learning behaviour. The experimental results show that the recognition accuracy of the proposed method is above 90%, and its recognition accuracy is and can shorten the recognition time of learning behaviour, with high practical application reliability.
  Keywords: multimodal data fusion; English online course; learning behaviour; behaviour recognition.
  DOI: 10.1504/IJBIDM.2024.10062021
   
  
• Evaluation Method of Teaching Reform Quality in Colleges and Universities Based on Big data Analysis  
  by Xiumin Wang 
  Abstract: Research on the quality evaluation of teaching reforms plays an important role in promoting improvements in teaching quality. Therefore, an evaluation method of teaching reform quality in colleges and universities based on big data analysis is proposed. A multivariate logistic model is used to select the evaluation indicators for the quality evaluation of teaching reforms in universities. And clustering and cleaning of the evaluation indicator data are performed through big data analysis. The evaluation indicator data is used as input vectors, and the results of the teaching reform quality evaluation are used as output vectors. A support vector machine model based on the whale algorithm is built to obtain the relevant evaluation results. Experimental results show that the proposed method achieves a minimum recall rate of 98.7% for evaluation indicator data, the minimum data processing time of 96.3 ms, the accuracy rate consistently above 97.1%.
  Keywords: big data analysis; colleges and universities; reform quality evaluation; multivariate logistic model; whale algorithm; support vector machine model.
  DOI: 10.1504/IJBIDM.2024.10062022
   
  
• A Method for Evaluating the Quality of College Curriculum Teaching Reform Based on Data Mining  
  by Xuepeng Huang 
  Abstract: In order to improve the effectiveness of the current evaluation of teaching reform in universities, a data mining algorithm based quality evaluation method for university curriculum teaching reform is designed. Firstly, based on the optimal data clustering criterion, evaluation indicators are selected and selected to establish a quality evaluation system for university curriculum teaching reform. Then, a reform quality evaluation model is constructed using BP neural network, and its training process is improved using genetic algorithm to obtain the optimal solution for model weights and thresholds. Finally, the evaluation data is substituted into the model to achieve accurate evaluation of the quality of university curriculum teaching reform. The results show that the evaluation accuracy of this method is higher than 96.3%, and the evaluation time is less than 10ms, which is superior to the Comparative law.
  Keywords: Data mining; University courses; Teaching reform; Quality evaluation.
  DOI: 10.1504/IJBIDM.2024.10062023
   
  
• A Personalized Recommendation Method for English Teaching Resources on MOOC Platform Based on Data Mining  
  by Yalei Yan, Liya Chen, Wenjing Wang 
  Abstract: In order to enhance the accuracy of teaching resource recommendation results and optimise user experience, a personalised recommendation method for English teaching resources on the MOOC platform based on data mining is proposed. First, the learner’s evaluation of resources and resource attributes are abstracted into the same space, and resource tags are established using the Knowledge graph. Then, interest preference constraints are introduced to mine sequential patterns of user historical learning behaviour in the MOOC platform. Finally, a graph neural network is used to construct a recommendation model, which adjusts users’ short-term and short-term interest parameters to achieve dynamic personalised teaching recommendation resources. The experimental results show that the accuracy and recall of the resource recommendation results of the research method are always higher than 0.9, the normalised sorting gain is always higher than 0.5.
  Keywords: data mining; MOOC platform; English teaching resources; personalised recommendation; knowledge graph; neural network.
  DOI: 10.1504/IJBIDM.2024.10062024
   
  
• Integrating MOOC Online and Offline English Teaching Resources Based on Convolutional Neural Network  
  by Kelu Wang, Dexu Bi 
  Abstract: In order to shorten the integration and sharing time of English teaching resources, a MOOC English online and offline mixed teaching resource integration model based on convolutional neural networks is proposed. The intelligent integration model of MOOC English online and offline hybrid teaching resources based on convolutional neural network is constructed. The intelligent integration unit of teaching resources uses the Arduino device recognition program based on convolutional neural network to complete the classification of hybrid teaching resources. Based on the classification results, construct an English online and offline mixed teaching resource library for Arduino device MOOC, to achieve intelligent integration of teaching resources. The experimental results show that when the regularisation coefficient is 0.00002, the convolutional neural network model has the best training effect and the fastest convergence speed. And the resource integration time of the method in this article should not exceed 2 s at most.
  Keywords: MOOC English; online and offline; mixed teaching resources; intelligent integration method; convolutional neural network.
  DOI: 10.1504/IJBIDM.2024.10062025
   
  
• Prediction method of College Students' Achievements Based on Learning Behavior Data Mining  
  by Haiqing Zhang, Chao Zhai 
  Abstract: This paper proposes a method for predicting college students’ performance based on learning behaviour data mining. The method addresses the issue of limited sample size affecting prediction accuracy. It utilises the K-means clustering algorithm to mine learning behaviour data and employs a density-based approach to determine optimal clustering centres, which are then output as the results of the clustering process. These clustering results are used as input for an attention encoder-decoder model to extract features from the learning behaviour sequence, incorporating an attention mechanism, sequence feature generator, and decoder. The characteristics derived from the learning behaviour sequence are then used to establish a prediction model for college students’ performance, employing support vector regression. Experimental results demonstrate that this method accurately predicts students’ performance with a relative error of less than 4% by leveraging the results obtained from learning behaviour data mining.
  Keywords: learning behaviour; data mining; college students; achievement prediction method; K-means; support vector regression.
  DOI: 10.1504/IJBIDM.2024.10062026
   
  
• A Method for Evaluating the Quality of Teaching Reform Based on Fuzzy Comprehensive Evaluation  
  by Weimiao Cui, Chen Zhang, Xiaoqi Zhang 
  Abstract: In order to improve the comprehensiveness of evaluation results and reduce errors, a teaching reform quality evaluation method based on fuzzy comprehensive evaluation is proposed. Firstly, on the premise of meeting the principles of indicator selection, factor analysis is used to construct an evaluation indicator system. Then, calculate the weights of various evaluation indicators through fuzzy entropy, establish a fuzzy evaluation matrix, and calculate the weight vector of evaluation indicators. Finally, the fuzzy cognitive mapping method is introduced to improve the fuzzy comprehensive evaluation method, obtaining the final weight of the evaluation indicators. The weight is multiplied by the fuzzy evaluation matrix to obtain the comprehensive evaluation result. The experimental results show that the maximum relative error of the proposed method’s evaluation results is about 2.0, the average comprehensive evaluation result is 92.3, and the determination coefficient is closer to 1, verifying the application effect of this method.
  Keywords: fuzzy comprehensive evaluation; teaching reform; quality assessment; factor analysis; fuzzy entropy; fuzzy evaluation matrix.
  DOI: 10.1504/IJBIDM.2024.10062027
   
  
• Research on the correlation between corporate financial performance and strategic risk based on panel data model  
  by Su Guo, Junfu Cui, Taile Zhang 
  Abstract: In recent years, the trend of economic globalization and multilateral trade has expanded rapidly, and the risk issues related to enterprises have received widespread attention from the people. For this problem of the panel data model, the research uses the entropy theory of ordinal space to quantify the strategic risk of the enterprise, constructs a panel-PLS estimation model to analyze the financial correlation of the enterprise. The results show that in most industries, the difference between the entropy value of rising and falling in the ranking of enterprises is 0.008, which is in a relatively stable state. Corporate strategic risk is negatively correlated with ROE and total asset turnover, and positively correlated with non-current asset turnover and dividend payout ratio. The above results can be used to predict the risk situation of the enterprise strategy and arrange targeted management decisions, which can promote the long-term development of the enterprise.
  Keywords: Strategic Risk; Financial Performance; Ordinal Space; Panel Data Model; PLS.
  DOI: 10.1504/IJBIDM.2024.10062518
   
  
• A three-way density peak clustering algorithm based on sinusoidal fuzzy entropy.  
  by Yudong Meng, Xin Xu, Leyuan Yan, Yuan Cao 
  Abstract: The Density Peaks Clustering algorithm (DPC) is an efficient and concise method for clustering that automatically detects density centres and noise points. However, it is vulnerable to inaccuracies in outlier identification due to the cutoff distance parameter. To address this drawback, this paper proposes a novel three-way density peak clustering algorithm called sinusoidal fuzzy entropybased DPC (SFE-DPC). An important aspect of SFE-DPC is determining the thresholds. To tackle this issue, a criterion using sinusoidal fuzzy entropy is developed, and genetic algorithms are utilized to search for the optimal thresholds. By employing the optimal thresholds determined through the proposed criterion, SFE-DPC divides each cluster into three sections, with points in the trivial region identified as outliers. To assess the performance of SFE-DPC, we evaluate it on UCI datasets that include outliers using three baseline measures (NMI, RI, and F1-score), and compare it to DPC, k-means, FCM, BIRCH, and SC methods. Experimental results confirm that SFE-DPC is more effective in outlier detection.
  Keywords: three-way clustering; sinusoidal fuzzy entropy; outlier identification; genetic algorithm.
  DOI: 10.1504/IJBIDM.2024.10062646
   
  
• A Condensed Hybrid Feature Selector for Enhancing the Classifiers Performance using TOPSIS and Improved Rao Optimization  
  by Karthik Kannan A. S, S.Appavu Alias Balamurugan, Millie Pant 
  Abstract: A wide range of fields are increasingly utilising high-dimensional data, such as text mining, bioinformatics, image processing, and pattern recognition. A classification system is less efficient as a result of the curse of dimensionality problem, which incurs high computational costs. It is efficacy to identify the optimal features from the feature space. An approach to selecting the more informative features based on MCDM and improved Rao optimisation methods is proposed. As a measure of candidate solutions’ fitness, the proposed work uses the classifier error rate and feature selection ratio. A comparison of the proposed method with state-of-the-art methods is conducted using 12 popular benchmark datasets. A hybrid approach outperforms the standard strategy in terms of selected features and classification accuracy, according to the results of the experiment.
  Keywords: hybrid feature selector; classification; multi-criteria decision making; MCDM; TOPSIS; improved Rao optimisation.
  DOI: 10.1504/IJBIDM.2024.10062647
   
  
• An influence-based k-nearest neighbour classifier for classification of data with different densities  
  by Hassan Motallebi, Amir-Hossein Fakhteh 
  Abstract: The k-nearest neighbour (KNN) is a simple and yet effective classification rule. To achieve robustness against outliers, several local mean-based extensions of the KNN classifier has been proposed which assign the query to the class with nearest local mean. However, using the conventional proximity measures causes poor performance in situations with multi-scale classes. Here, we propose a new local mean-based KNN classifier that uses a new modified distance measure which adjusts the proximity around each sample with respect to the situation and density. We scale the distance from the sample to each class with respect to the size of its influence set such that the sample seems closer to classes in which it has higher number of reverse neighbours. We apply the proposed method on three local mean-based KNN classifiers. Our results show that the proposed method improves the performance of the local mean-based classifiers.
  Keywords: local mean-based KNN; modified distance measure; reverse KNN; gradient descent direction; different densities.
  DOI: 10.1504/IJBIDM.2024.10062901
   
  
• A data classification method for innovation and entrepreneurship in applied universities based on nearest neighbour criterion  
  by Xiuhong Qin, Na Li 
  Abstract: Aiming to improve the accuracy, recall, and F1 value of data classification, this paper proposes an applied university innovation and entrepreneurship data classification method based on the nearest neighbour criterion. Firstly, the decision tree algorithm is used to mine innovation and entrepreneurship data from applied universities; Then, dynamic weight is introduced to improve the similarity calculation method based on edit distance, and the improved method is used to realise data de-duplication to avoid data over fitting; Finally, the nearest neighbour criterion method is used to classify applied university innovation and entrepreneurship data, and cosine similarity is used to calculate the similarity between the samples to be classified and each sample in the training data, achieving data classification. The experimental results demonstrate that the proposed method achieves a maximum accuracy of 96.5% and an average F1 score of 0.91. These findings indicate a high level of accuracy, recall, and F1 value for data classification using the proposed method.
  Keywords: nearest neighbour criterion; innovation and entrepreneurship; data classification; decision tree algorithm; dynamic weight; cosine similarity.
  DOI: 10.1504/IJBIDM.2024.10063366
   
  
• Intelligence assistant using deep learning: use case in crop disease prediction  
  by U. Dinesh Kumar, Manaranjan Pradhan, Shailaja Grover, Naveen Kumar Bhansali 
  Abstract: In India, 70% of the Indian population is dependent on agriculture, yet agriculture generates only 13% of the country’s gross domestic product. Several factors contribute to high levels of stress among farmers in India, such as increased input costs, draughts, and reduced revenues. The problem lies in the absence of an integrated farm advisory system. A farmer needs help to bridge this information gap, and they need it early in the crop’s lifecycle to prevent it from being destroyed by pests or diseases. This research involves developing deep learning algorithms such as ResNet18 and DenseNet121 to help farmers diagnose crop diseases earlier and take corrective actions. By using deep learning techniques to detect these crop diseases with images farmers can scan or click with their smartphones, we can fill in the knowledge gap. To facilitate the use of the models by farmers, they are deployed in Android-based smartphones.
  Keywords: agro-analytics; convolutional neural networks; CNNs; crop disease detection; data augmentation; intelligent assistant.
  DOI: 10.1504/IJBIDM.2024.10063463
   
  

Special Issue on: Edge Computing in Business Intelligence and Data Mining

• The application of machine learning in real estate enterprise risk management  
  by Hongtao Pan 
  Abstract: As a pillar industry of the national economy, real estate plays a pivotal role in economic development, social stability, employment and other fields. In recent years, the rapid development of the real estate industry has become a common concern of the whole society. The changes of the market economy and the national macro-control will have a huge impact on the real estate industry, and the real estate industry has become the industry with the highest risk. It is an inevitable trend to introduce new technologies into the risk management of real estate enterprises and to improve the automation and intelligence of risk management. By analysing the risk management of real estate enterprises, this paper constructs a risk management model and implementation path based on machine learning, and elaborates its implementation process in detail. The study found that compared with the risk level of the real estate industry, under the enterprise risk management model based on machine learning, the risk level of enterprises is lower.
  Keywords: risk management; real estate business; machine learning; business management.
  DOI: 10.1504/IJBIDM.2024.10055528
   
  
• Innovative model of real estate financing based on internet of things thinking  
  by Shihan Zhang 
  Abstract: This paper studied the model innovation of real estate financing and proposed the financing model of the internet of things platform. From the five aspects of financing cost, financing efficiency, financing information transparency, financing risk-taking level and enterprise evaluation, the experimental study was carried out on the internet of things platform financing model and the traditional real estate financing model. The research showed that the financing model of the internet of things platform could improve the financing efficiency and reduce the level of financing risk.
  Keywords: IoT thinking; real estate financing; financing model innovation; traditional real estate financing model; IoT platform financing model.
  DOI: 10.1504/IJBIDM.2024.10054654
   
  
• Information accuracy verification system of invoice metadata based on data warehouse  
  by Hui Chen, Yuening Wang, Weilin Xue 
  Abstract: This paper aims to explore the information accuracy verification system based on the invoice metadata of the data warehouse. Metadata defines the role of the data warehouse and specifies the content and location of the data warehouse, and describes the data extraction and transformation rules. The application of neural network in data warehouse was discussed. Finally, based on this research, it analysed the management and application of electronic invoice metadata. The experimental results of this paper showed that to accelerate the popularisation of electronic invoices and vigorously promote electronic invoices is an inevitable choice for developing the economy and deepening tax reform. When processing electronic invoice filing, it is necessary to realise the automatic entry of core metadata in the electronic document management system, so that it has the function of core metadata and gives full play to its due role.
  Keywords: electronic invoice; data warehouse; BP neural network; invoice metadata; artificial neural network.
  DOI: 10.1504/IJBIDM.2024.10060201
   
  
• Design and application of a new massive open online training platform  
  by Zhe Wang, Jingjing Li 
  Abstract: Over the past decade, e-learning has been a tremendous success. Many MOOCs have been established around the world. A mounting number of college students study through MOOCs. But with the rapid development of cloud computing, big data and artificial intelligence technology, there is an increasing number of IT training requirements in colleges. The mode of traditional IT training can not match the needs of college students and teachers, such as fragmentation, anytime, anywhere, etc. IT training is more complex than e-learning, so it cannot simply copy the mode of e-learning. This article proposes a framework of a massive open online training platform based on Docker and cloud services, which overcomes the limitations of traditional training. It has the advantages of quickness, economy, efficiency and flexibility. It provides one-stop services for online learning, online training and online assessment for college students. The application results of Shuishan online show that the proposed framework is reliable and excellent.
  Keywords: e-learning; massive open online training platform; MOOTP; online training; cloud services; Docker.
  DOI: 10.1504/IJBIDM.2024.10058390
   
  
• Visual analysis of financial big data based on data centre  
  by Wentao Yang, Rui Tian, Lifang Zhang 
  Abstract: This paper aims to study the data middle-end means in data mining (DM) technology, and combine back propagation (BP) network to research and analyse the visualisation of financial data, so that financial data can be better combined with intelligent and convenient means. Based on the experiments in this paper, it can be seen that by analysing the relevant financial statements of H Group from 2016 to 2019, it can be effectively found that the accuracy of financial data has been effectively improved in 2016 after combining the data centre. The experimental results of this paper have shown that using the BP network as the basic method to study the visual analysis of financial big data can obtain intuitive and scientific relevant experimental data, and help the managers of the management organisation to make scientific decisions.
  Keywords: data middle office; financial data; finance visualisation; data mining; BP neural network.
  DOI: 10.1504/IJBIDM.2024.10060196
   
  
• Safety assurance mechanism of athletes in ice and snow sports based on edge computing  
  by Di Wu, Yongqi Li 
  Abstract: The development and application of information and communication technology is expected to reduce the fatality rate of sports-induced sudden death through remote monitoring of biological signals. This paper proposes an athlete safety assurance system based on edge computing suitable for ice and snow sports. By monitoring the physiological index information of athletes in real-time, and integrating random forest algorithm for data analysis and decision-making, it provides real-time analysis of athletes' status for coaches and logistics teams. To verify the effectiveness of the proposed system in this paper, the performance of the data processing module is evaluated using public datasets. Compared with the experimental results of related work, the method in this paper can effectively monitor the physiological index information of athletes and realise real-time grasp of the physical state of athletes. The method proposed in this paper can provide a guarantee for the safety of athletes.
  Keywords: snow sports; edge computing; random forest algorithm; safety assurance.
  DOI: 10.1504/IJBIDM.2024.10061471
   
  
• Intelligent construction project management schedule technology based on internet of things computing  
  by Xiao Wang 
  Abstract: In recent years, the development of the information technology industry has driven changes in all walks of life. Under the background of information technology, the construction industry has also achieved transformation and development, which is mainly reflected in the increase of modern building intelligent system engineering. Intelligent system management is different from ordinary construction projects; its own complexity and systematicness exceed ordinary projects. Project management schedule technology is an effective management model for intelligent building system engineering projects. Project management schedule can effectively control project cost and project completion quality, effectively ensure the delivery of construction schedule, and effectively reduce construction cost and resource consumption. This article looks at construction project management, pointing out that IoT assistance to current project progress can improve the overall quality of smart buildings. The experiment shows that the internet of things has increased the efficiency of construction project management by 72.73%.
  Keywords: internet of things computing; intelligent building; intelligent building engineering; construction project; project management progress.
  DOI: 10.1504/IJBIDM.2024.10055705
   
  
• Identification of enterprise financial risk based on logistics model  
  by Zhiqi Li 
  Abstract: With the deepening of market economy, financial risk seriously affects the healthy development of enterprises. This paper proposed a company financial risk crisis based on logistic regression model. The main components were extracted by factor analysis method, and the financial risk identification model was constructed by the logistic regression method, which combined factor analysis and logistic regression. After testing, the identification accuracy rate of the risk early warning model was 68.98% in the first three years of the financial crisis and 83.74% in the first two years, and 93.45% in the previous year. Through empirical analysis, the risk prediction model established in this paper had a certain practical value, and it was found that the effectiveness of its prediction was affected by time factors, and its prediction accuracy can reach 80% within two years before the crisis occurs.
  Keywords: logistic model; corporate financial risk; financial crisis; risk warning.
  DOI: 10.1504/IJBIDM.2024.10061725
   
  
• Application of artificial intelligence technology in electronic information security protection system  
  by Guoqiang You 
  Abstract: Creating a fully functional electronic information security protection system is extremely important for today's information security. How to improve the electronic information security protection system is an urgent problem that needs to be solved. Artificial intelligence technology is one of the most popular and widely used technologies at present. It is widely used in various fields and has achieved good results. Based on this, this article proposes to use artificial intelligence technology to build and improve electronic information security protection systems. Research results show that the normal data recognition rate of network intrusion has increased by about 2% compared with traditional methods, and the unknown data intrusion rate has increased by about 14% compared with traditional methods. This shows that artificial intelligence technology is suitable for electronic information security protection systems and can better monitor the internal message security and network attacks of traditional security protection products.
  Keywords: electronic information security protection system; artificial intelligence technology; artificial neural network; intrusion detection.
  DOI: 10.1504/IJBIDM.2024.10061923