Forthcoming Articles
International Journal of Data Science

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 Articles will not be published until the final proofs are validated by their authors.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 also listed here. 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.
Register for our alerting service, which notifies you by email when new issues are published online.
International Journal of Data Science (20 papers in press) Regular Issues
Abstract: With the rapid development of the economy, the problem of population aging has become increasingly prominent. In the current shortage of social endowment resources and imperfect endowment facilities, home-based endowment, as the most common endowment method, has played a great role in alleviating the pressure and contradiction of social endowment. However, the development time of home-based elderly care is relatively short, and the functionality and safety of its living environment are not suitable for the elderly, which is often difficult to meet the actual needs of the elderly. To effectively alleviate this dilemma, based on the analysis of the characteristics of the elderly, the demand for interior space design, and its development status, this paper has conducted effective research on the design and transformation of interior space for home-based care for the aged in combination with network security. To verify the effectiveness of network security, this paper has carried out the practice of interior space design and transformation and evaluated it from the three dimensions of functionality, security, and aesthetics. Keywords: Interior Space Design; Network Security; Home-based Pension; Elderly Group. DOI: 10.1504/IJDS.2025.10070395
Abstract: This article proposes an e-commerce platform-based Intelligent Financial Risk Blockchain Management under the Internet of Things (IFRBM-IoT) system to investigate and enhance the service quality, the standardisation of assurance processes inside a company, and the provision of means for achieving optimum security and quality control are all outcomes of a better profitability ratio risk management strategy. The framework uses the Neuro-fuzzy decision method with the control chart method to build an effective financial risk management system with Hyper ledger blockchain technology on an e-commerce platform, enabling in-depth analysis of financial risk evaluation and pledging greater data credibility, accountability, confidentiality, and integrity. The empirical data analysis findings demonstrate the model's high accuracy in data assessment and strong symmetric fit for managing financial risks inside the Internet business plan. The approach is practical for managing financial risks and assessing the effectiveness of data security measures. Keywords: Internet of Things; financial risk management; E-commerce; panel data regression analysis; Hyper ledger blockchain. DOI: 10.1504/IJDS.2025.10071212
Abstract: This study proposes a multilevel grey evaluation method integrated with machine learning to assess tourism resource (TR) development potential. Addressing challenges like poor management, resource scarcity, and unsustainable practices, the approach optimises resource allocation through an evaluation system analysing variation and grey weight vectors. Results show steady increases in evaluation weights over time, with average variation weight at 1.87 (total increase: 1.80) and grey weight at 0.50 (increase: 0.21). Compared to traditional systems, the optimised model improved service quality (9.92%), management level (10.25%), and government support (9.07%). This method enhances resource utilisation efficiency and promotes sustainable tourism development by identifying optimal strategies for TR exploitation. Keywords: Tourism Resource Development; Machine Learning; Multi-level Grey Method; Potential Evaluation. DOI: 10.1504/IJDS.2025.10071283
Abstract: Financial shared service centre is an emerging financial management method, which has been widely used in many multinational enterprises. This model can effectively improve the financial management efficiency of the enterprise, reduce the investment of human and material resources, and promote the optimal allocation of resources of the enterprise. Under the current market conditions, many problems have arisen in the traditional financial management model, such as low financial processing efficiency and high financial management costs. It is vital to assess its running perks in order to fully exploit its economic potential and to support and ensure the long-term growth of the business. The key to guaranteeing the long-term and stable growth of the monetary pooling centre is the deployment of transfer networks blockchain technology to construct a scientifically financial management system. The Financial Sharing Center's strategic goals are broken down into four categories: finances, customers, internal procedures, learning and development. The efficacy of the money sharing centre is assessed in this study using the fuzzy complete assessment method. Keywords: Financial Sharing; Deep Learning; Blockchain Technology; Performance Evaluation. DOI: 10.1504/IJDS.2025.10071763
Abstract: This paper explores green logistics network optimisation and carbon emission reduction through blockchain technology, IoT, and big data. A blockchain-based logistics model was developed, incorporating smart contracts for automated carbon management and IoT devices for real-time emission monitoring. Big data analysis enabled logistics path optimisation. Experimental results showed that using ant colony optimisation reduced transportation time by 20%, fuel consumption by 15%, and carbon emissions by 18%. The proposed metho enhances logistics efficiency and reduces environmental impact, offering practical solutions and theoretical support for sustainable logistics networks. Keywords: Blockchain Technology; Green Logistics; Carbon Emissions; Path Optimization; Smart Contracts; Internet of Things; Ant Colony Optimization. DOI: 10.1504/IJDS.2025.10072254
Abstract: This paper aims to solve the problem of emergency Network Public Opinion (NPO) Risk Identification (RI) and Early Warning (EW). Firstly, the back propagation neural network (BPNN) optimized by Genetic Algorithm (GA) is used to process and model the data obtained on the network, identify the public opinion risk of emergencies, and realize the risk prediction and early warning. Secondly, through the analysis and mining of NPO data of emergencies, the factors affecting the risk of NPO, such as social media platforms, user characteristics, and text content, are explored. These factors are incorporated into the model to improve the predictive ability of the model. Finally, through the research, effective Risk Management (RM) and countermeasures of NPO in emergencies are proposed to provide feasible RM schemes for governments, enterprises, and the public to ensure social stability and security. Keywords: back propagation neural network; data mining; emergencies; network public opinion; risk identification and early warning. DOI: 10.1504/IJDS.2025.10072258
Abstract: In recent years, the rapid development of Financial Technology (FinTech) has profoundly changed the operation of the financial market, where the extensive application of machine learning technology in risk assessment, credit approval, and asset pricing has significantly impacted the financing structure of enterprises. This paper breaks through the traditional research framework, constructing a "technology-market" two-dimensional variable system from the perspective of the dynamic adjustment of enterprise financing structures, and quantitatively analyzes the influence of FinTech driven by machine learning on the proportion of enterprise financing sources, financing costs, and term structure. It is found that the investment intensity in FinTech is positively correlated with the direct financing ratio of enterprises, with a more pronounced impact on information-sensitive industries. This paper not only enriches the research on the relationship between FinTech and corporate financing structures but also provides valuable policy suggestions and practical guidance for regulators, corporate decision-makers, and financial institutions. Keywords: Machine learning; Quantitative analysis; Financial technology; Enterprise financing structure; Small and medium-sized enterprises. DOI: 10.1504/IJDS.2025.10072736
Abstract: This paper focuses on the construction of an intelligent Outcome-Based Education (OBE) platform driven by deep learning and explores how to integrate deep learning technology with the OBE concept to meet students' personalized learning needs and improve teaching quality. Firstly, the research reviews the application status of deep learning in the field of education and the progress of OBE, elucidating the necessity and feasibility of combining the two. Based on this, a design scheme for an intelligent OBE platform, structured around a hierarchical architecture, is proposed, covering key modules such as user modeling, knowledge map construction, intelligent recommendation, and evaluation feedback. The experimental results demonstrate that the platform significantly improves students' grades, knowledge mastery, and the accuracy of personalized recommendations. The improvement in students' grades in the experimental group is 2.4 times greater than that of the control group, and the click-through rate of recommended resources reaches 78%. Keywords: Outcome-Based Education; Deep Learning; Intelligent; Intelligent Recommendation; OBE Concept. DOI: 10.1504/IJDS.2025.10072737
Abstract: This work explores consumer demand and preferences for cultural and creative tourism products to enhance the effectiveness of visual design and market competitiveness. A comprehensive model integrating the deep convolutional neural network (DCNN) and deep belief network (DBN) is developed using deep learning technology. This model aims to extract both the underlying features of product images and the semantic features of consumers, thereby providing data support to optimise product design. The results indicate that the constructed model achieves a prediction accuracy of 98.5% and a recall rate of 98.2% in product image recognition, demonstrating its effectiveness in capturing consumer demand characteristics. Keywords: Deep learning; Image analysis; Product visual design; Cultural and creative products; Deep Belief Network. DOI: 10.1504/IJDS.2025.10072738
Abstract: With the rapid growth of residents disposable income, demand for tourism has surged, exposing critical challenges in the traditional tourism industry. A major issue is the inability of scenic spots to market tourism projects according to tourists' characteristics and preferences, resulting in resource waste and hindering sustainable development. To address these challenges, this study aimed to design a smart tourism information resource management (IRM) system based on GIS and big data (BD) technology. The intelligent tourism IRM system was developed by integrating tourism information collection with GIS and BD technologies. To evaluate its effectiveness in solving industry pain points and improving scenic spot revenue, 10 well-known scenic spots with an annual passenger volume exceeding 10 million were selected for comparative analysis. The evaluation focused on three key metrics: annual tourist reception, service satisfaction, and total annual revenue. The implementation of the intelligent tourism IRM system significantly improved all three performance indicators. On average, annual tourist reception, tourist service satisfaction, and total annual revenue increased by 26.61%, 17.53%, and 23.28%, respectively, demonstrating the system's substantial positive impact. Keywords: Smart Tourism; Information Resource Management System; Geography Information System; Big Data; Visitor Satisfaction. DOI: 10.1504/IJDS.2025.10072775
Abstract: The proposed intelligent automatic English translation system leverages advanced feature extraction algorithms and big data technologies to enhance translation accuracy and efficiency. Central to this system is an N-Gram-based scoring model, which evaluates translation quality by analysing word sequences. This model is further refined through the development of an English corpus scoring framework, enabling more precise assessments. Incorporating Latent Dirichlet Allocation (LDA), the system employs weighted LDA indices to assess the semantic depth of translations. When these indices are well-aligned, they indicate a translation that captures the nuances and depth of the original text. Conversely, scattered LDA indices suggest a loss of key semantic elements during translation. The integration of behavioural decompression algorithms facilitates the optimization of translation processes, ensuring that the system delivers high-quality English-Chinese translations by effectively capturing and preserving semantic information. Keywords: Feature extraction; Big data information technology; English-Chinese translation; Interactive. DOI: 10.1504/IJDS.2025.10072978
Abstract: With the rapid growth of tourism, traditional scenic area management struggles to meet increasing demands. This paper proposes an intelligent management system for tourist attractions based on Internet of Things (IoT) technology to optimise crowd control, enhance service quality, and improve visitor satisfaction. By integrating IoT with cloud and edge computing, the system enables real-time monitoring, efficient flow allocation, and personalised services. Experimental results show tourist satisfaction rose from 58% to 83% after implementation. The system also improves attraction capacity and operational efficiency, demonstrating the potential of IoT in smart tourism. The study highlights the synergy between information devices and mobile applications, offering a reference for future intelligent scenic area development Keywords: Intelligent Management System; IoT Information Technology; Tourist Attractions; Smart Tourism. DOI: 10.1504/IJDS.2025.10072979
Abstract: For the development of rural economy, accurately predicting the demand and price trend of agricultural products will help investors optimize their trading strategies and provide scientific reference for the government's macro-control. This article focuses on the application of intelligent algorithm in the accurate assessment and effect prediction of rural economic development policies, and puts forward a Deep Learning (DL) model that integrates deep belief network (DBN) and long-term and short-term memory network (LSTM) for the joint prediction of agricultural product demand and price. The model integrates multi-source sales data from e-business platform, and combines historical transaction records, market supply and demand relationship and external environmental factors to build a learning framework with temporal and spatial characteristics.The results show that the proposed model is significantly superior to traditional statistical methods such as random forest (RF) in many forecasting indexes, and has higher forecasting accuracy and stability. Keywords: Artificial intelligence; Intelligent algorithm; Rural economic development; Accurate policy assessment; Effect prediction. DOI: 10.1504/IJDS.2025.10072980
Abstract: With the rapid development of e-commerce and increasingly fierce market competition, customer satisfaction has become the key to enterprise competition. However, the current quality of e-commerce services is uneven, and there is room for improvement in customer satisfaction. This paper's method is not only targeted, but also reflects the real feelings and needs of customers more accurately. This paper not only calculates the mean, standard deviation and variance of related variables, but also further discusses the specific impact of various service quality indicators on customers' shopping experience. It is found that the six service quality indicators, practicality, safety, enthusiasm, reliability, feedback mechanism and compensation mechanism, have different degrees of influence on customer satisfaction and loyalty. This paper shows innovations in research methods, data analysis and interpretation of results, which provides strong theoretical support and practical guidance for e-commerce enterprises to improve service quality and enhance market competitiveness. Keywords: Online shopping; E-commerce; Service quality; Customer satisfaction; Big data. DOI: 10.1504/IJDS.2025.10072981
Abstract: Industry-education integration has become a pivotal national strategy in China, yet its complex interactions are difficult to capture with traditional models, which often rely on empirical methods lacking precision. To address this gap, this study introduces a BP neural network-based evaluation approach. By iteratively adjusting neuron weights to fit nonlinear functions, the method enables accurate assessment of industry-education integration. The research highlights the importance of vocational education, identifies key challenges, and explores its role in Chinas educational system. A neural network model is built using 10 secondary indicators, with simulation and validation performed in MATLAB on real-world data. Results show strong dynamic tracking and fitting accuracy, providing a scientific basis for precise evaluation. This study contributes an innovative data-driven method for optimising vocational training models and offers valuable insights for policy development and system improvement. Keywords: Industry-Education Integration; BP Neural Network; Vocational Education; Oriented Training; System Construction. DOI: 10.1504/IJDS.2025.10073096 A Commensurate Univariate Variable Ranking Method for Classification ![]() by Nuo Xu, Xuan Huang, Thanh Nguyen, Jake Yue Chen 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 Condition 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. Keywords: variable types; variable ranking; variable relevance; commensurate; statistical dependence. DOI: 10.1504/IJDS.2025.10067405 Beauty Aids: can AI Improve Human behaviours with Imperfect Data? ![]() by Wenfeng Wang, Baizhou Xu, Bin Hu, Fuqing Li, Lalit M. Patnaik, Lujie Cui, Yunzhu Pan Abstract: This article aims to examine whether AI can improve human behaviors 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 behaviors. 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 behaviors. 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. Keywords: models; parameters; data collection; makeup behaviors; facial beauty prediction. DOI: 10.1504/IJDS.2025.10070883 Remote Sensing-Based Wireless Spatial Data Analysis Integrating Machine Learning and Data Fusion for Enhanced Environmental Monitoring ![]() by YaHui Wang 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 models potential for scalable and accurate environmental monitoring. Keywords: Remote Sensing; Deep Learning; Environmental Monitoring Multi-Module Integration; Spatial Feature Extraction. DOI: 10.1504/IJDS.2025.10072712 A Study on Data Analysis of Student Achievement under Adult Education through Association Rule Algorithm ![]() by Yuan Dong 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 , the running time of the improved Apriori algorithm for the webdocs dataset was 1,123 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. Keywords: association rule; adult education; student achievement; Apriori algorithm. DOI: 10.1504/IJDS.2025.10073094 The Feature Extraction and Fusion Algorithm for Multi-source Data based on Deep Belief Network ![]() by Xinjie Qian, Guixiang Hu, Yuqin Dai 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. Keywords: Deep Learning; Multi-source Data Fusion; Deep Belief Network(DBN); Feature Extraction; Image Classification; Machine Learning. DOI: 10.1504/IJDS.2025.10073144 |