International Journal of Business Intelligence and Data Mining (6 papers in press)

Regular Issues

• Improving brain MRI segmentation of multiple sclerosis using an advanced CNN approach  
  by V. Biksham , Sampath Korra, B. Pradeep Kumar , Salar Mohammad 
  Abstract: Multiple sclerosis (MS) can be detected early by looking for lesions in brain magnetic resonance imaging (MRI). Recently, unsupervised anomaly detection algorithms based on autoencoders were presented for the automatic identification of MS lesions. However, because these autoencoder-based approaches were created exclusively for 2D MRI pictures (e.g., 2D cross-sectional slices), they do not take use of the complete 3D information of MRI. In this research work, a novel 3D autoencoder-based methodological solution for detecting MS lesion volume in MRI is offered. We begin by defining a 3D convolutional neural network (CNN) for complete MRI volumes and then construct each encoder and decoder layer of the 3D autoencoder using 3D CNN. For optimal data reconstruction, we additionally include a skip link between the encoder and decoder layers. In the experimental results, we compare the 3D autoencoder-based method to the 2D autoencoder models using training datasets from the Human Connectome Project (HCP) and testing datasets from the Longitudinal MS Lesion Segmentation Challenge, and show that the proposed method outperforms the 2D autoencoder models by up to 20% in MS lesion prediction.
  Keywords: multiple sclerosis; brain MRI; image segmentation; CNN; chronic disease; healthcare.
  DOI: 10.1504/IJBIDM.2025.10068668
   
  
• Analysing the effectiveness of financial news sentiments on stock price prediction of twelve Indian sectoral stock indices using a hybrid LSTM-GRU model  
  by Meera George, R. Murugesan 
  Abstract: Despite the growing interest in combining news sentiments with historical data to improve stock price prediction, a considerable gap exists in predicting the sectoral stock indices using this methodology. This study addresses this gap by predicting the closing price of 12 Indian sectoral stock indices through a hybrid deep-learning architecture. It employs a hybrid TFIDF-Doc2Vec feature extraction technique and an SVM classifier to extract the financial news sentiments. These sentiments are utilised to create a sentiment Index, combined with historical stock data to predict each sectoral stock index using a hybrid LSTM-GRU model. The study evaluates the effectiveness of financial news sentiments in sectoral stock prediction by comparing models with and without sentiments. Results demonstrate a notable influence of sentiments on the stock price prediction of ten sectoral stock indices with a pronounced impact on the NSEBANK index. This study offers valuable insights for investors in formulating sector-specific trading strategies. It also aids policymakers in market regulation and helps financial analysts improve forecasting models by incorporating financial news sentiments. Future research could explore the integration of multi-source investor sentiments with advanced deep-learning models for even more accurate stock price predictions across diverse sectors.
  Keywords: stock price prediction; sectoral stock indices; financial news sentiments; FNSs; hybrid TFIDF-Doc2Vec; hybrid LSTM-GRU.
  DOI: 10.1504/IJBIDM.2025.10070322
   
  
• Data mining of abnormal behaviour in English learning based on dynamic grid generation algorithm  
  by Le Yang  
  Abstract: To address the limitations of traditional data mining methods for detecting abnormal behaviour in English learning - such as low accuracy, low recall rates, and long processing times - this paper proposes a joint data mining method based on a dynamic grid generation algorithm. The proposed approach begins by collecting instances of abnormal behaviour in English learning to construct a behavioural dataset. Next, the RANSAC algorithm eliminates erroneous feature matching points, while the dynamic grid generation algorithm performs data feature matching. Finally, an abnormal behaviour data mining function is constructed to identify anomalies in English learning behaviours. Experimental results demonstrate the methods effectiveness, achieving a recall rate of 96.5%, an accuracy of 99.15%, and a processing time of just six seconds, confirming its efficiency in mining abnormal behaviour data in English learning.
  Keywords: feature matching; dynamic grid generation algorithm; data mining; Ransac algorithm.
  DOI: 10.1504/IJBIDM.2025.10072627
   
  

Special Issue on: Innovative AI driven 3D Modelling for Business Intelligence Tools

• Leveraging traditional business culture for business intelligence: a scalable parameter server architecture with distributed machine learning  
  by Chengcai Xing 
  Abstract: Yanan, a significant historical and cultural hub in China, is being revitalised and utilised to drive development in various spheres. The citys traditional commercial and cultural resources are being harnessed to contribute to its political, cultural, educational, and economic growth. Yanan models other historically significant regions, demonstrating how heritage can be leveraged for contemporary development. Advanced machine learning approaches are used to overcome scalability and robustness issues in large-scale data-driven systems. The parameter server architecture decentralises the training process of machine learning models, enabling efficient handling of vast datasets and high computational demands. This design enhances fault tolerance and ensures seamless operation under challenging conditions. Intelligent simulations and tests validate the efficacy of these machine-learning approaches in modelling the evolution and application of traditional commercial culture. These simulations provide a dynamic and accurate representation of how cultural and business practices can adapt and thrive in modern contexts. The reliability and precision of machine learning models in capturing complex patterns and trends inherent in cultural and economic transitions are underscored through rigorous testing. This exploration highlights the innovative intersection of technology and tradition, showcasing how machine learning can play a transformative role in preserving and advancing historical and cultural assets.
  Keywords: traditional commercial and cultural resources; Yan’an historical value; distributed machine learning; parametric server architecture.
  DOI: 10.1504/IJBIDM.2025.10069536
   
  

Special Issue on: Knowledge Discovery from Big Data to Spur Social Development

• Deep learning based DAVS-UNet for medical image segmentation  
  by Zihui Zhu 
  Abstract: Deep learning based Convolutional Neural Networks (CNNs) and transformers are widely used in medical image processing tasks, while the State Space Sequence Model (SMM) architecture is proposed to address its limitations in improving the scaling efficiency and solving the transformed quadratic scale problem. Inspired by the Mamba architecture, this paper proposes Dual-Attention Vision Scaled-UNet (DAVS-UNet) for medical image segmentation, in which Adaptive Multi-scale Selection (AMS) is applied to the input image for better capturing details at different scales and extracting input features. Furthermore, Atrous Space Pyramid Pooling (ASPP) is introduced to expand the sensory field by collecting global contextual information after the final encoder. The experiments on a large number of publicly available datasets illustrate that DAVs-UNet shows excellent performance on the ISIC2017, ISIC2018, Synapse datasets, and outperforms existing SSM-architecture networks employed in medical image segmentation tasks. The code is available at https://github.com/zhzhuac/DAVS.
  Keywords: attention mechanism; multi-scale information; state space models; convolutional neural networks; CNNs; adaptive multi-scale selection; AMS; atrous space pyramid pooling; ASPP.
  DOI: 10.1504/IJBIDM.2026.10070330
   
  
• GA-TabNet: a novel approach for early dropout prediction in MOOCs based on genetic algorithms and TabNet  
  by Houssam Eddine Aouarib, Fatima Zohra Laallam, Salah Eddine Henouda, Mohamed Fouzi Djouhri 
  Abstract: Massive open online courses (MOOCs) represent one of the most effective educational methodologies due to their cost-effectiveness, flexibility, ubiquity, and their role in facilitating and improving education. MOOCs possess the capacity to revolutionise global education; nevertheless, the high dropout rates often undermine their effectiveness. The emergence of machine learning, deep learning techniques, and educational big data enables academics to address the student dropout problem through big data analytics. This study addresses the critical challenges of student dropout prediction by proposing GA-TabNet, an innovative model that combines a Genetic Algorithm with TabNet for early dropout prediction. The results of this study were validated using the Open University Learning Analytics Dataset. The proposed model attained an average accuracy exceeding 92%. Furthermore, it outperformed traditional predictive models, including Support Vector Machine, Long Short-Term Memory, Logistic Regression, MultiLayer Perceptron, Decision Trees, and Random Forest models, by margins ranging from 0.79% to 4.79%.
  Keywords: student dropout prediction; massive open online course; MOOC; TabNet; genetic algorithm; big data; machine learning; ML; deep learning; DL.
  DOI: 10.1504/IJBIDM.2026.10073518