Template-Type: ReDIF-Article 1.0 Author-Name: Nanhua Duan Author-X-Name-First: Nanhua Author-X-Name-Last: Duan Author-Name: Jingwen Zhang Author-X-Name-First: Jingwen Author-X-Name-Last: Zhang Title: The development of a product-layer perceived value scale for the online experience products of young Chinese consumers: take online apparel as an example Abstract: With the COVID-19 outbreak, more and more young Chinese consumers are using the internet as their primary way of purchasing. Studies have shown that consumers' perceived value (CPV), which is multidimensional, situational, and dynamic, is important for online purchases. However, there are few CPV scales specifically for experiential products, and most studies focus on post-purchase evaluation rather than purchasing process behaviour. Therefore, this study took clothing as example and considered all the factors online in purchasing process into the scope of the CPV commodity layer. Semi-structured interviews, exploratory factor analysis, and confirmatory factor analysis (CFA) were taken to establish a product-level CPV scale for online experience products of young Chinese consumers, including six dimensions: word of mouth value, service value, aesthetic value, cost value, quality value, and brand value. The findings can help online experience products, especially online clothing brands, improve their marketing strategy and attract consumer buying intentions. Journal: Int. J. of Data Science Pages: 1-21 Issue: 5 Volume: 10 Year: 2025 Keywords: CPV; customer perceived value; experience products; online purchase decision; online apparel goods; Chinese young consumer. File-URL: http://www.inderscience.com/link.php?id=143886 File-Format: text/html File-Restriction: Open Access Handle: RePEc:ids:ijdsci:v:10:y:2025:i:5:p:1-21 Template-Type: ReDIF-Article 1.0 Author-Name: Oguzhan Akan Author-X-Name-First: Oguzhan Author-X-Name-Last: Akan Author-Name: Abhishek Verma Author-X-Name-First: Abhishek Author-X-Name-Last: Verma Author-Name: Sonika Sharma Author-X-Name-First: Sonika Author-X-Name-Last: Sharma Title: Prediction of customer churn risk with advanced machine learning methods Abstract: Customer churn risk prediction is an important area of research as it directly impacts the revenue stream of businesses. An ability to predict customer churn allows businesses to come up with better strategies to retain existing customers. In this research we perform a comprehensive comparison of feature selection methods, upsampling methods, and machine learning methods on the customer churn risk dataset: i) Our research compares likelihood-based, tree-based, and layer-based machine learning methods on the churn dataset; ii) Models built on the churn dataset without upsampling performed better than oversampling methods. However, synthetic minority oversampling technique (SMOTE) and adaptive synthetic sampling (ADASYN) helped stabilise model performance; iii) the models built on ADASYN dataset were slightly better than the SMOTE counterparts; iv) it was observed that XGBoost and deep cascading forest (DCF) combined with XGBoost were consistently better across all metrics compared to other methods; and v) information Value analysis performed better than PCA. In particular, IVR DCFX model has the best AUROC score with 89.1%. Journal: Int. J. of Data Science Pages: 70-95 Issue: 1 Volume: 10 Year: 2025 Keywords: customer churn; DNNs; deep neural networks; DCF; deep cascading forest; SMOTE; synthetic minority oversampling technique; ADASYN; adaptive synthetic sampling. File-URL: http://www.inderscience.com/link.php?id=144832 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:10:y:2025:i:1:p:70-95 Template-Type: ReDIF-Article 1.0 Author-Name: Adam C. Moyer Author-X-Name-First: Adam C. Author-X-Name-Last: Moyer Author-Name: William A. Young II Author-X-Name-First: William A. Young Author-X-Name-Last: II Author-Name: Timothy J. Haase Author-X-Name-First: Timothy J. Author-X-Name-Last: Haase Title: Self-evolving data collection through analytics and business intelligence to predict the price of cryptocurrency Abstract: This paper presents the self-evolving data collection engine through analytics and business intelligence (SEDCABI) for predicting Bitcoin prices. Traditionally models use either structured or unstructured data alone, limiting effectiveness. This research pioneers using both data types. SEDCABI harnesses analytics and BI to extract insights from structured historical price and market data. It also incorporates unstructured social media sentiment and news to capture Bitcoin perceptions. Experiments show integrating both data types significantly improves prediction accuracy. SEDCABI continuously adapts to the dynamic crypto market. The plug-in prediction module (PPM) enables customisation. Overall, SEDCABI offers robust Bitcoin price predictions by combining structured and unstructured data. This contributes to cryptocurrency prediction research with an innovative approach to informed decision-making. Journal: Int. J. of Data Science Pages: 1-26 Issue: 1 Volume: 10 Year: 2025 Keywords: SEDCABI; self-evolving data collection engine through analytics and business intelligence; prediction; Bitcoin; cryptocurrency; text mining; analytics; business intelligence; unstructured data; sentiment; price. File-URL: http://www.inderscience.com/link.php?id=144833 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:10:y:2025:i:1:p:1-26 Template-Type: ReDIF-Article 1.0 Author-Name: Xian Zhang Author-X-Name-First: Xian Author-X-Name-Last: Zhang Author-Name: Xinhui Luo Author-X-Name-First: Xinhui Author-X-Name-Last: Luo Author-Name: Dong Yin Author-X-Name-First: Dong Author-X-Name-Last: Yin Author-Name: Taiguo Qu Author-X-Name-First: Taiguo Author-X-Name-Last: Qu Author-Name: Hao Li Author-X-Name-First: Hao Author-X-Name-Last: Li Title: A study of MySQL protocol-based database proxy approval system for fortress machine Abstract: With the increase of enterprise informatisation, database security and compliance operation management have become increasingly important. Therefore, it is essential to design an efficient database proxy approval system. In this paper, we develop a database proxy approval system based on the MySQL protocol for fortress machines, which provides a real-time customised configuration scheme for high-risk commands, designs a real-time approval process for six types of high-risk commands, and creates a simple and efficient matching algorithm for high-risk commands. We designed a large number of experiments to test the system's connection success rate, operation stability, response time, CPU resource consumption, matching algorithm performance, and other aspects. The experimental results show that this database proxy approval system has good configuration flexibility, high accuracy, and good time performance. This system has a wide range of applications in electric power, finance, petroleum, and other fields. Journal: Int. J. of Data Science Pages: 96-117 Issue: 1 Volume: 10 Year: 2025 Keywords: fortress machine; MySQL protocol; database proxy; approval system; database security. File-URL: http://www.inderscience.com/link.php?id=144837 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:10:y:2025:i:1:p:96-117 Template-Type: ReDIF-Article 1.0 Author-Name: Liping Wu Author-X-Name-First: Liping Author-X-Name-Last: Wu Author-Name: Xuehua Zhu Author-X-Name-First: Xuehua Author-X-Name-Last: Zhu Title: Mobile target defence against IoT-DDoS attacks Abstract: This study analyses the mobile target defence method and feature extraction process based on multi-source information fusion technology (MSIFT), and introduces a feature level fusion (FLF) method for optimising backpropagation neural network (BPNN) DDoS attacks based on genetic algorithm. The models with 9 nodes and 11 nodes had the best learning performance, with learning rates of 0.37 and 0.15. When the intensity of DDoS attacks was low, the prediction accuracy of the proposed method was about 94%. The actual value was usually small, with the 10th group having the highest actual value, close to 800, and the 19th group having the lowest actual value, about 130. Introducing decision level fusion of DDoS attacks based on D-S evidence fusion can further improve the accuracy of attack detection. This study has made significant progress in improving the efficiency and accuracy of mobile target defence against DDoS attacks in the Internet of Things. Journal: Int. J. of Data Science Pages: 53-69 Issue: 1 Volume: 10 Year: 2025 Keywords: IoT; Internet of Things; DDoS attacks; target defence; multi-source information; genetic algorithm. File-URL: http://www.inderscience.com/link.php?id=144839 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:10:y:2025:i:1:p:53-69 Template-Type: ReDIF-Article 1.0 Author-Name: LinLiang Zhang Author-X-Name-First: LinLiang Author-X-Name-Last: Zhang Author-Name: LianShan Yan Author-X-Name-First: LianShan Author-X-Name-Last: Yan Author-Name: ZhiSheng Liu Author-X-Name-First: ZhiSheng Author-X-Name-Last: Liu Author-Name: Shuo Li Author-X-Name-First: Shuo Author-X-Name-Last: Li Author-Name: RuiFang Du Author-X-Name-First: RuiFang Author-X-Name-Last: Du Author-Name: ZhiGuo Hu Author-X-Name-First: ZhiGuo Author-X-Name-Last: Hu Title: A data value-driven collaborative data collection method in complex multi-constraint environments Abstract: Data collection is a foundational task in mobile crowd sensing. However, existing data collection methods prioritise quantity, neglecting heterogeneity, cooperation, energy efficiency, and collision avoidance, causing low multi-agent efficiency in complex scenarios. To address this issue, this paper integrates multi-agent reinforcement learning and deep learning to propose the CS_MCE method. The CS_MCE method, applying to unmanned aerial vehicle (UAV) collaborative data collection scenarios, utilises deep neural networks to solve representation problems in vast state-action spaces and provides intelligent decision-making capabilities. In various experimental environments with different data values, experiments comparing CS_MCE with the MADDPG and IL-DDPG algorithms in terms of reward values, data quality, energy efficiency, and the number of collisions showed that the data quality collected by CS_MCE increased by 5-6 times, and energy efficiency improved by more than 60%, demonstrating the efficiency and stability of the CS_MCE method. Journal: Int. J. of Data Science Pages: 27-52 Issue: 1 Volume: 10 Year: 2025 Keywords: MCS; mobile crowd-sensing; data collection; heterogeneous data; unmanned vehicles; deep reinforcement learning. File-URL: http://www.inderscience.com/link.php?id=144840 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:10:y:2025:i:1:p:27-52 Template-Type: ReDIF-Article 1.0 Author-Name: Shulei Yin Author-X-Name-First: Shulei Author-X-Name-Last: Yin Title: Life cycle prediction and survival model construction of digital economy enterprises integrating survival analysis Abstract: The life cycle of digital economy enterprises is affected by many complex and nonlinear factors. Traditional methods can only handle some simple linear relationships. This paper proposes an improved gradient boosting regression tree (GBRT) model to further enhance the prediction ability. Firstly, the Kaplan-Meier survival curve is used for descriptive statistics and exploratory analysis. Then, the accelerated failure time (AFT) model is used to model the enterprise life cycle. Finally, the GBRT model is used to predict the mean-square error (MSE) value, and it is compared with the MSE value of the linear regression model. The MSE value of the survival model is 0.015, much smaller than the MSE value of the linear regression model of 0.232, reflecting the superiority of the survival model. Journal: Int. J. of Data Science Pages: 1-19 Issue: 6 Volume: 10 Year: 2025 Keywords: AFT; accelerated failure time; Kaplan-Meier survival curve; GBRT; gradient boosting regression tree; survival model; linear regression method. File-URL: http://www.inderscience.com/link.php?id=146190 File-Format: text/html File-Restriction: Open Access Handle: RePEc:ids:ijdsci:v:10:y:2025:i:6:p:1-19 Template-Type: ReDIF-Article 1.0 Author-Name: Nuo Xu Author-X-Name-First: Nuo Author-X-Name-Last: Xu Author-Name: Xuan Huang Author-X-Name-First: Xuan Author-X-Name-Last: Huang Author-Name: Thanh Nguyen Author-X-Name-First: Thanh Author-X-Name-Last: Nguyen Author-Name: Jake Y. Chen Author-X-Name-First: Jake Y. Author-X-Name-Last: Chen Title: A commensurate univariate variable ranking method for classification Abstract: To apply a variable ranking method for feature selection in classification, the notion of commensurateness is necessitated by the presence of different types of independent variables in a dataset. A commensurate ranking method is one that produces consistent and comparable ranking results among independent variables of different types, such as numeric vs. categorical and discrete vs. continuous. We invent a ranking method named conditional empirical expectation (CEE) and demonstrate it is the most commensurate among several representative ranking methods. Further, it has the highest statistical power as a test of independence when the categorical dependent variable is imbalanced. These properties make CEE uniquely suitable for fast feature selection for any datasets, especially those with high dimensionality of mixed types of variables. Its usage is demonstrated with a case study in facilitating preprocessing for classification. Journal: Int. J. of Data Science Pages: 175-194 Issue: 2 Volume: 10 Year: 2025 Keywords: variable types; variable ranking; variable relevance; commensurate; statistical dependence. File-URL: http://www.inderscience.com/link.php?id=149831 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:10:y:2025:i:2:p:175-194 Template-Type: ReDIF-Article 1.0 Author-Name: Wen-Feng Wang Author-X-Name-First: Wen-Feng Author-X-Name-Last: Wang Author-Name: Bai-Zhou Xu Author-X-Name-First: Bai-Zhou Author-X-Name-Last: Xu Author-Name: Bin Hu Author-X-Name-First: Bin Author-X-Name-Last: Hu Author-Name: Fuqing Li Author-X-Name-First: Fuqing Author-X-Name-Last: Li Author-Name: Lalit Mohan Patnaik Author-X-Name-First: Lalit Mohan Author-X-Name-Last: Patnaik Author-Name: Lu-Jie Cui Author-X-Name-First: Lu-Jie Author-X-Name-Last: Cui Author-Name: Yun-Zhu Pan Author-X-Name-First: Yun-Zhu Author-X-Name-Last: Pan Title: Beauty aids: can AI improve human behaviours with imperfect data? Abstract: This paper aims to examine whether AI can improve human behaviours with imperfect data. Beauty aids with the pretrained AI model is taken as a practical example. This model integrated fuzzy reasoning with ResNet-50 for facial beauty prediction (FBP) and real-time recommendations of makeup behaviours. Results shown that the AI model can provide beauty aids for people whose facial data have not be included during the pretraining process and improve their makeup behaviours. The difference between the maximal and minimal values amounts to 33.62, implying that the effect of beauty aids is evident. The cross validation with perfect data further also confirmed that the effects of increased makeup experiences are worthy of further attention. The recommended degree of powder makeup for the volunteer is 0.118~0.2, while that of lipstick and blush makeup is 0.034~0.2. As an emerging technique, potential evolutions of the real-time beauty aids system with AI and data science will bring out the long-term future of FBP research. Journal: Int. J. of Data Science Pages: 119-135 Issue: 2 Volume: 10 Year: 2025 Keywords: models; parameters; data collection; makeup behaviours; FBP; facial beauty prediction. File-URL: http://www.inderscience.com/link.php?id=149851 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:10:y:2025:i:2:p:119-135 Template-Type: ReDIF-Article 1.0 Author-Name: YaHui Wang Author-X-Name-First: YaHui Author-X-Name-Last: Wang Title: Remote sensing-based wireless spatial data analysis integrating machine learning and data fusion for enhanced environmental monitoring Abstract: Remote sensing is vital for environmental monitoring, aiding in land use classification, vegetation health assessment, and climate change analysis. This study introduces an integrated model combining convolutional neural networks (CNN), Random Forests (RF), and graph neural networks (GNNs) to improve remote sensing data classification. The model leverages spatial feature extraction, classification robustness, and spatial relationship capture for enhanced performance. Evaluated on MODIS and Sentinel-2 datasets, it achieved 95.18% and 90.88% accuracy, outperforming state-of-the-art methods in accuracy and efficiency. The model also demonstrated high recall, F1 scores, and computational efficiency, making it suitable for real-time and large-scale applications. Ablation studies confirmed the importance of each component, highlighting the model's potential for scalable and accurate environmental monitoring. Journal: Int. J. of Data Science Pages: 156-174 Issue: 2 Volume: 10 Year: 2025 Keywords: remote sensing; deep learning; environmental monitoring multi-module integration; spatial feature extraction. File-URL: http://www.inderscience.com/link.php?id=149860 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:10:y:2025:i:2:p:156-174 Template-Type: ReDIF-Article 1.0 Author-Name: Yuan Dong Author-X-Name-First: Yuan Author-X-Name-Last: Dong Title: A study on data analysis of student achievement under adult education through association rule algorithm Abstract: Students receiving adult education must complete academic tasks while balancing work and life, which may cause poor learning results. The student learning situation can be better comprehended by analysing student performance data. In order to realise the analysis of students' course performance under adult education, this paper designed an improved Apriori algorithm based on the Boolean matrix for the problem of low efficiency. Through the experiments on the webdocs and mushroom datasets, it was found that when Sup<SUB align="right"><SMALL>min</SMALL></SUB> = 0.1, the running time of the improved Apriori algorithm for the webdocs dataset was 1123 s, which was 20.64% shorter than the FPGrowth algorithm and 26.17% shorter than the Apriori algorithm. The running time for the Mushroom dataset was 27.38 s, which was 76.73% shorter than the Apriori algorithm and 55.31% shorter than the FPGrowth algorithm. Journal: Int. J. of Data Science Pages: 195-209 Issue: 2 Volume: 10 Year: 2025 Keywords: association rule; adult education; student achievement; Apriori algorithm; Boolean matrix; minimum support; professional course performance; curriculum arrangement. File-URL: http://www.inderscience.com/link.php?id=149861 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:10:y:2025:i:2:p:195-209 Template-Type: ReDIF-Article 1.0 Author-Name: Xinjie Qian Author-X-Name-First: Xinjie Author-X-Name-Last: Qian Author-Name: Guixiang Hu Author-X-Name-First: Guixiang Author-X-Name-Last: Hu Author-Name: Yuqin Dai Author-X-Name-First: Yuqin Author-X-Name-Last: Dai Title: The feature extraction and fusion algorithm for multi-source data based on deep belief network Abstract: This paper proposes DGACO-Net, a new model combining deep belief network (DBN), graph convolution network (GCN), and ant colony optimisation (ACO) to address the challenges of feature extraction and spatial relationship modelling in multi-source remote sensing data for land cover classification. DBN is used to extract advanced features, GCN captures spatial topological relationships, and ACO optimises hyperparameters to enhance model accuracy. Experimental results on the UC Merced Land Use and WHU-RS19 datasets demonstrate significant improvements in classification performance, with accuracies of 95% and 94%, respectively, outperforming benchmark models like SVM, random forest, and CNN. Ablation studies and feature visualisation validate the synergy of DBN, GCN, and ACO. DGACO-Net shows great potential for remote sensing image analysis and land resource management, offering an innovative solution for multi-source data classification. Journal: Int. J. of Data Science Pages: 136-155 Issue: 2 Volume: 10 Year: 2025 Keywords: deep learning; multi-source data fusion; DBN; deep belief network; feature extraction; image classification; machine learning. File-URL: http://www.inderscience.com/link.php?id=149862 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:10:y:2025:i:2:p:136-155