International Journal of Information and Decision Sciences (39 papers in press)

Regular Issues

• A survey on various Alzheimer classification techniques using 3D MRI images: A challenging overview  
  by Neethu M., Roopa Jayasingh J 
  Abstract: This survey presents 50 research papers focussed on various techniques in Alzheimer classification techniques using 3D MRI images, and the categorization of the techniques is made based on the fusion-based, Convolutional Neural Network (CNN)-based, Random forest (RF)-based and Support vector Machine (SVM)-based approaches. Finally, the analysis is to be promoted in the survey based on the research technique, publication year, employed tools, utilized dataset, performance measures and achievement of the research methodologies towards Alzheimer classification techniques using 3D MRI images. At the end, the research gaps and issues of the techniques for Alzheimer classification techniques using 3D MRI images is to be revealed.
  Keywords: Alzheimer classification; Convolutional Neural Network; Random forest; Support vector Machine; Fusion.
  
  
• A Consumer Behaviour Assessment using Dimension Reduction and Deep Learning Classification  
  by Pragya Pandey, Kailash Chandra Bandhu 
  Abstract: Consumer behavior assessment is extremely important for online communities to finding out mindset of customer and change their views about specific products and services. Customers share their experiences with particular goods, and services on channels and social media, empowered by artificial intelligence for consumer knowledge sharing and acquire new information. In this proposed work, a deep learning model has been developed for statistical tests, statistical analysis using correlation and association testing are performed. The ordinary dimension reduction with principal component analysis and module eigenvalues, followed by a second normalization phase that maximizes the coefficient's size using possible values. The keras library was used on the third layer of the deep learning classification hierarchy with the rectified linear unit and sigmoid activation functions. The average F1 score was 98 % accurate and according to the statistics, the proposed strategy had an accuracy of 84% and a recall of 100%.
  Keywords: Consumer Behavior; Artificial Intelligence; Consumer Knowledge-Sharing; Principal Component Analysis; Deep Learning Classification.
  
  
• The Influence of Information Sources on Process and Content Confidence when Making Ill-structured Managerial Decisions  
  by David McLain, Jinpei Wu 
  Abstract: Although information is an important influence on decision confidence, disparate views exist about that influence. Engineering-derived psychological theory associates information non-negatively with confidence whereas the overconfidence literature suggests information has a non-positive influence on confidence. Previous research, however, has used information sources lacking ecological validity and almost exclusively studied well-structured decisions and single facets of confidence. Drawing on research and practice in management, decision making, and the neurosciences, the influences of technology-sourced (web) information and performance feedback information were studied as influences on confidence when making ill-structured decisions. Clear distinctions were made between judgment leading up to a decision, called process confidence, and evaluation of the final decision, called content confidence. Process-integrated web use only weakly increased either confidence while feedback significantly reduced content confidence and left process confidence little changed. This effect was amplified when the feedback clarified others decision expectations. Within subjects, the relationship between quantified feedback and confidence, especially process confidence, was positive and increased with each decision. These findings suggest that an information resource when making ill-structured decisions has little effect on confidence but that credible, post-decision performance information can affect content confidence while process confidence remains resilient.
  Keywords: confidence; information; decision-making; ambiguity; ill-structured decisions; meta-cognition; feedback; web; Internet.
  
  
• Sales Order Booking Process Lead Time Reduction by Deployment of the Lean Principle  
  by Rohit Kenge 
  Abstract: Changing environmental conditions, government imbalances, and COVID 19 disease are resulting in the more product delivery time. We studied the current sales order booking process in the literature survey, found some gaps, and proposed a hypothesis to reduce the lead time of the sales order booking process. We executed a survey of buyers and salespersons with a set of 39 questionnaires for the period of December 2020 to March 2021 on a convenience sampling basis for the 500 samples by circulating the Google form. 479 responses are received and we considered 402 valid responses after rejecting 77 wrongly ?lled answers. Hence, we got 80.33% correct responses. We performed the analysis of survey response data by testing the reliability, validity, correlation matrix, and structural equation modelling and concluded that our proposed model is the best fit and improved the overall lead time for the sales order booking process.
  Keywords: Sales management; Lean; Lead time reduction; Sales Operation excellence; and Sales order booking process.
  
  
• A Comparison of Statistical and Machine Learning Models for Stock Price Prediction  
  by Saurab Iyer, Vraj Patel, Joy Mehta, Jai Prakash Verma, Ankit Sharma 
  Abstract: A huge proportion of money around the world is held by the stock markets. It is one of the most pivotal aspects of the financial institutions and experts. Predicting the movements of stock markets can improve decision making for traders. In this paper, data science techniques are employed to predict the
  Keywords: deep learning; machine learning; stock price prediction; statistical modelling.
  DOI: 10.1504/IJIDS.2025.10061178
   
  
• COVID Patients' Severity Level Detection Using Machine Learning Approach  
  by Rishika Anand, Meenakshi Saroha, Pooja Gambhir, Dimple Sethi 
  Abstract: COVID-19 is a contagious disease that is caused by the SARS-CoV-2. This disease originated in Wuhan, China, in 2019, which resulted in a pandemic. This virus is diagnosed using chest computed tomography. Preventive measures like not touching face, maintaining distance, and frequent washing hands are taken care of to reduce disease transmission. There is a vaccine for COVID-19, but it is effective to some extent, whereas fewer hospitals are there for the patients suffering from COVID-19 in India. So, the government needs to admit the patients with the severe infection from COVID-19, and the patients with less severity have to isolate themselves in their homes. In this article, various parameters are considered to detect the severity of the patient suffering from COVID-19. Machine learning techniques are applied to get better accuracy while detecting the severity of the patients.
  Keywords: COVID-19; symptoms of COVID-19; machine learning; the severity of patients.
  DOI: 10.1504/IJIDS.2025.10061179
   
  
• Predictive Data Using Linear Regression in Agricultural Production  
  by Clovis Santos, Carina Dorneles 
  Abstract: In agribusiness some challenges are related to generating information for predictability with an acceptable safety accuracy. In this context, data management systems are usually developed to meet only the operational, legal, and regulatory requirements. The gap in functionalities regarding data science creates the opportunity to develop complementary tools such as business intelligence, data warehousing, online analytics, and others. This paper presents an approach to predict possible scenarios from historical harvested crops datasets. We conducted our proposal using a set of government data on harvests in all regions of Brazil in a historical series of 45 years. We have developed a descriptive application for predictive data analysis and information generation for forecasting scenarios in agriculture, using machine learning with a predictive algorithm implemented with linear regression. Objectively, the results show the use of real datasets to generate possible values in crops according to previous seasons.
  Keywords: agribusiness; database; linear regression data extraction; machine learning.
  DOI: 10.1504/IJIDS.2025.10061180
   
  
• Managerial Practices for Speedy Strategic Decision in Multinational Firms  
  by Amira Khelil 
  Abstract: Making speedy strategic decisions (SSDs) stands as a prerequisite critical for Top management teams (TMTs) to lead their organizations effectively in the international business world. Recently, only a few managers seem to have actually realized how TMTs could reach an efficient strategic decision (SD). For effectively addressing this shortfall, we draw on SD literature to advance a set of relevant enablers, whereby, decisions could be more easily reached. By relying on the SD and RBV theories, we maintain that such factors as centralization, ERP, collaborative culture, and intuition represent key elements likely to help TMTs make prompt decisions and achieve international performance. In this context, using PLS software-based data sources, this study, conducted to deal with Tunisia-based multinational firms, turns out to indicate that both the collaborative culture and ERP factors appear to represent key antecedents of prompt SD a significantly influential key factor necessary for maintaining international performance.
  Keywords: The Strategic Decision; ERP; Collaborative culture; Intuition; International Performance.
  
  
• Lemon Fruit Classification by Transfer Learning Technique: Experimental Investigation of Convolutional Neural Network (CNN)  
  by K. D. Mohana Sundaram, T. Shankar, Sudhakar N 
  Abstract: Before exporting fruits, quality control is extremely important in the fruit industries. The most crucial step in the quality assessment process is to classify the fruit as fresh or spoiled. Convolutional neural network (CNN) is the most recent technology used for classification. Henceforth, in this work, the performance of eight widely used CNNs, namely AlexNet, DenseNet, GoogleNet, Inceptionv-3, MobileNetv-2, ResNet-18, SqueezNet, and VGGNet-19, was evaluated and compared for fruit classification, utilising the Lemon fruit dataset. To classify the lemon fruits into three categories of good-quality, medium-quality, and poor-quality, 1,000 fully connected layers in each CNN were substituted with three fully connected layers. For comparison, all of the CNNs were trained using the Transfer Learning technique with learning rates of 0.1, 0.01, and 0.001. The VGG Net-19 architecture was found to have a validation accuracy of 92.6% for a learning rate of 0.001.
  Keywords: convolutional neural network; CNN; fruit classification; fully connected layers; transfer learning.
  DOI: 10.1504/IJIDS.2025.10061181
   
  
• Pothole Detection and Localization from Images using Deep Learning  
  by Archit Dhiman, Mohit Kumar, Arun Yadav, Divakar Singh Yadav 
  Abstract: The existence of potholes threatens road safety and contributes to a significant portion of accidents worldwide. It takes a lot of work to constantly patch potholes and keep track of when new ones appear. Our goal in this work is to create a pothole detection system that would make it simpler to accurately detect potholes from images. The system can potentially save human lives and assist the government authorities to fix the potholes. In order to achieve this objective, we first make use of a pre-trained deep learning model (VGG-16) and thereafter, propose a novel convolutional neural network (CNN) model. This work employs a publicly available dataset, Nienaber Potholes 2 (Complex), for experiments. The proposed model provides 98.87% accuracy on pothole classification task in images and outperforms recent state-of-the-art approaches in the literature. Further, since no past work has been done on this dataset to detect bounding boxes for potholes, we use YOLO-v3 and YOLO-v5 to generate bounding box predictions on this dataset and evaluate the results. The bounding box task achieves 83.23% mAP and 87.45% precision. Due to the absence of significant existing results, these results for bounding box prediction may be considered as a benchmark.
  Keywords: pothole detection; pothole; convolutional neural network; CNN; bounding box; you only look once; YOLO; Nienaber.
  DOI: 10.1504/IJIDS.2025.10059513
   
  
• The Factors Driving Buyers to Post Their Online Feedback - Ordered Logistic Regression Analysis  
  by Xubo Zhang, Yanbin Tu, Ke Zhong 
  Abstract: Reputation is vital for sellers to survive and grow at online auction marketplaces. Positive feedback ratings from buyers help sellers build such a reputation. In this study, we explore the factors that affect feedback ratings from buyers at online auction marketplaces. We try to identify the factors related to three types of feedback (+, 0, ) posted by buyers. We also study the effects of sellers first move to post their feedback to buyers on the counter-feedback from buyers. We find that characteristics of sellers and products, selling strategies, auction outcomes, and the first mover strategy are significantly associated with feedback posted from buyers. More specifically, sellers first move to post their positive feedback to buyers helps them receive positive counter-feedback from buyers. Our study contributes to the literature by exploring the determinants of online feedback posted from buyers and providing empirical evidence on the effects of sellers first mover strategy.
  Keywords: online auction; buyer's feedback; first mover strategy; marketing analytics.
  DOI: 10.1504/IJIDS.2026.10061463
   
  
• Macroeconomic Variables and Exchange Rates a complex interplay and the role of a central bank  
  by Anupam Mehrotra, Amit Kumar Pandey, Ashok Chopra 
  Abstract: Fluctuations in exchange rates are both the causes and consequences of changes in major macroeconomic variables. One triggers the other in a complex interplay of forces, and there is a chain of actions and reactions leading to a sizeable shift in certain macroeconomic variables at an unacceptable pace or in an undesired direction calling, at times, central banking or government intervention to break the momentum. The paper analyses the nexus between some major macroeconomic variables and the exchange rate. It also examines the situations where it may be required for the central bank to make changes in the policy rates or other components of its monetary policy to curb excessive volatility in exchange rates and/or to influence the macroeconomic variables in the general interest of the economy.
  Keywords: exchange rate; macroeconomic variables; central bank; GDP; inflation; interest rates.
  DOI: 10.1504/IJIDS.2026.10062350
   
  
• A Binomial Simulation Approach to More Consistent AHP Matrices  
  by Phillip W. Witt, Mohsen Hamidi 
  Abstract: Different methods have been proposed for simulating analytical hierarchy process (AHP) matrices. In this paper, we develop a new method assuming responses for AHP matrices follow binomial distributions. In this paper, we exhibit the method with a small data sample which we use to estimate the binomial parameters by transformation, and then backwards solving the logit Newton-Raphson updating algorithm. A parametric bootstrap sample is then used to compare the simulated results against the actual results from the data. In addition to the new simulation method we discover some interesting findings regarding AHP matrix consistency.
  Keywords: analytic hierarchy process; AHP; simulation; decision-making; group decision-making; decision science; managerial decision-making; consistency; Newton-Raphson; binomial.
  DOI: 10.1504/IJIDS.2026.10062775
   
  
• Design of Hybrid SVM Job recommender (HSJR) system for the overlapping target classes  
  by Santhosh Kumar Rajasekar, N. Prakash 
  Abstract: The fresh graduates with no prior experience are struggling to find suitable jobs. The job searching time of the fresh graduate is not reduced. Few researchers used machine learning models for matching the recommended job skill-set with the graduate skill set. If the skill-set of the two jobs is the same, the machine learning algorithms recommend only one job and ignore the other job. To address this problem, we design a hybrid support vector machine job recommendation (HSJR) model. The proposed HSJR model collects the skill set of the graduate and matches it with the current jobs and recommends the most suitable jobs for the graduates. To evaluate the proposed HSJR model, the jobs are recommended for the engineering graduates and the feedback received from the participants. The proposed HSJR model achieves 90% accuracy in the job recommendation. The proposed HSJR model performs better than the traditional job recommender system.
  Keywords: job recommender system; support vector machine; SVM; skill set; career recommendation; recommendation system; recommender system.
  DOI: 10.1504/IJIDS.2025.10063418
   
  
• A Classification Model for Terror Incidents by Affiliation Category of Perpetrators  
  by Donald D. Atsa’am, Benjamin Terzungwe Tough, Doose Atsa'am 
  Abstract: A terror incident could be perpetrated by either a lone wolf who acts on their own or affiliated terrorists who work for a terror group. In this study, the data from the global terrorism database and the artificial neural network algorithm were employed to construct a classification model that could predict the probable affiliation category of the perpetrator(s) of a terror incident. The model uses information such as type of attack, casualty figure, claim of responsibility, and damage to property to distinguish a lone wolf attack from a terror group attack. Various metrics of model diagnostics were employed to test the suitability of the model for predictions, and it yielded a balanced classification accuracy of 85%. The model adds another dimension to the existing criteria for terrorism classification. Further, the model could serve as a useful tool in the study of terrorism and counterterrorism.
  Keywords: lone wolf; affiliated terrorist; affiliation category; classification model; artificial neural network; ANN.
  DOI: 10.1504/IJIDS.2026.10063799
   
  
• Prediction of return on equity using machine learning algorithms: an evidence from India  
  by Amit Hedau, S.V.S. Raja Prasad, Sasikanta Tripathy 
  Abstract: The present study analysed and predicted the return on equity using machine learning algorithms from the historical financial data during April 2018-March 2022 for construction firms operating in India. The study considered sampling bias method to consider the listed 172 companies from construction sector, as this sector generates the second largest contribution to the GDP of India. The machine learning algorithms is used to model the regression equation. The results indicate that market capitalisation, sales, return on asset, current ratio, earning per share, promoter holdings and profit after tax significantly influence the return on equity for construction firm in India during the study period. We conclude that out of six classifiers, XGBoost is more accurate (86%) to predict the return on equity of the construction firms in India. Finally, a financial performance prediction tool is developed to predict the results.
  Keywords: return on equity; ROE; construction; India; machine learning; XGBoost.
  DOI: 10.1504/IJIDS.2025.10064231
   
  
• The Effect of Software-Based Mind Map of Educational Design in Development of the Electrical Engineering Students' Learning Level  
  by Zahra Jamebozorg, Fatemeh Jafarkhani, Khaled Nawaser 
  Abstract: The present study aims to investigate the effect of a software-based mind map for educational design in the electrical engineering students' learning level development. The qualitative phase of the research featured deductive method of content analysis while the quantitative phase was characterised by a quasi-experimental design. The analytical framework employed for the first phase of the research entailed open and axial coding, whereas the second stage involved the utilisation of descriptive and inferential statistical analyses. Results of the first phase of the study including 54 participants revealed the components of instructional design for mind map. The lesson plans for the treatment phase were prepared with respect to the educational design elements and they were conducted by the experimental group including 23 students. Results also showed that applying mind map into the instructional design has improved students' learning level.
  Keywords: instructional design model; mind map; software-based; electrical engineering; learning level.
  DOI: 10.1504/IJIDS.2026.10065142
   
  
• A Bibliometric Analysis of Information Criteria for Forecasting Volatility  
  by W.U. Youyuan, Choo W.E.I. Chong, Matemilola Bolaji Tunde, Jen Sim Ho 
  Abstract: Volatility forecasting model selection is an essential issue when making financial decisions, which increasingly focus on modelling, forecasting, and evaluation. However, this area has not yet undergone a systematic analysis in the relevant literature. This paper takes advantage of the VOSviewer and bibliometric techniques to overview the temporal distribution of articles, the corresponding author's countries, the citation network, the co-occurrence, the thematic evolution, and the top of the journal or authors or articles. Content analysis of 60 pieces of literature, including their data characteristics, theoretical basis, and practical application, as well as suggestions for potential research directions. Through bibliometric techniques and content analysis, this study provides a thorough overview of the research done in the field of volatility forecasting model selection. The research findings indicate that scientific productivity on the subject is expanding rapidly. New methodologies, such as neural networks, have been introduced, necessitating a broad perspective by the researcher in the evaluation of empirical results.
  Keywords: bibliometric analysis; information criteria; volatility forecasting; model selection.
  DOI: 10.1504/IJIDS.2026.10065147
   
  
• Contracted near-shore service part production predictive modelling using BOM-based feature generalisation and deep statistical learning  
  by Donovan Fuqua, Faruk Arslan, Victor Pimentel, Jimho Fatoki, Barry Brewer, Phillip W. Witt, Edward Kennedy 
  Abstract: Intermittent service part production (SPP) is a common manufacturing resource planning (MRP II) problem occurring when a customer requests spare parts from the manufacturer for an item no longer in production but still in widespread use. Manufacturers increasingly turn to contracted SPP (outsourcing) for fabrication of specialised components, including service parts. Despite the ubiquity of contracted SPP in contemporary manufacturing, it is a neglected area of study that relies on dated research, standard operations research models, and simplistic forecasting. Most available literature depends upon the availability of maintenance and part reliability information generally not available to contracted suppliers. In practice, manufacturers tend to add rough service demand estimates into contract costs or negotiate additional production as separate orders. Our model adds to SPP theory by managing irregularly contracted SPP by component item families using out-of-sequence service order histories as a proxy for reliability data.
  Keywords: smart MRP II; lumpy demand; agile manufacturing; explainable machine learning; demand chain management; DCM.
  DOI: 10.1504/IJIDS.2026.10065172
   
  
• AHP Approach for Employee Recruitment with COVID-19 Situation in Thailand  
  by Akan Narabin, Veera Boonjing, Kanognudge Wuttanachamsri 
  Abstract: With COVID-19 circumstance, unlike usually situation, to select an appropriate person for a job position, the criteria and a weight of each criterion are needed to determine and adjust to suit with the crisis. The criteria chosen in this work are emphasized on selecting applicants who, while studying, have been in the midst of the COVID-19 situation. In this research, we employ Analytic Hierarchy Process to assist the committee to have an agreement. In this study, each person in the committee can have his/her own pairwise comparison matrix of the criteria with a three-level hierarchical model. Since initiating hierarchical model may occur some ambiguity in sometime, in this work, the criteria used in the three-level model is properly adjusted to create a four-level hierarchical model. The comparison inspected, which provide some guidance in both theoretical manner and applications.
  Keywords: Analytic Hierarchy Process (AHP); COVID-19; Employee recruitment; Multi-criteria decision-making problem.
  DOI: 10.1504/IJIDS.2026.10065340
   
  
• An Efficient Hybrid Denoising Algorithm for ECG signal using Adaptive Hybrid filtering method and Empirical Model Decomposition method.  
  by Kirubha D, Vinayagam P, Uthayakumar G.S., Usha S 
  Abstract: The majority of the time, the signal from the electrocardiogram (ECG) is obscured by the frequency of the mains, which is either 50 or 60 hertz. A notch filter that is able to selectively filter individual frequencies can be used to cut down on the mains frequency portion of an electrocardiogram (ECG). The adaptive hybrid filter cleans up the ECG signals by removing background noise. The global MIT-BIH database provides the ECG data that is used in the simulation research. Our mathematical analysis makes use of a number of different real ECG recordings in addition to synthetic ECG that has been contaminated by a number of different kinds of noise. The performance of our suggested system is measured by the signal-to-noise and distortion ratio (SINAD), improvement in signal-to-noise ratio (SNR), approximation entropy, and fuzzy entropy. These metrics are used to assess the system’s effectiveness.
  Keywords: ECG signal; empirical mode decomposition; EMD.
  DOI: 10.1504/IJIDS.2026.10065526
   
  
• Optimizing Accuracy Rate of Genomic Image Representation of Human Coronavirus Sequences for COVID-19 Detection  
  by Palanikumar S, Sivakumar K, Harikrishnan R, Selvi K 
  Abstract: Due to the significant mortality rate associated with the coronavirus disease 2019 (COVID-19), it is impossible to ignore this newly discovered illness that has an impact on healthcare on a worldwide scale. At this time, physicians are making use of pictures produced by computed tomography (CT) in order to aid them in recognising COVID-19 in its earlier stages. In this study, a COVID-19 diagnostic system is built with the help of a convolutional neural network (CNN) and stacked autoencoder. Before using the three different CT imaging methods to tell the difference between normal and COVID-19 cases. During the training phase of the deep learning model that was used, a demanding and large-scale CT image dataset was utilised. This allowed for accurate reporting of the model’s ultimate performance. This model was correct 88.30% of the time, sensitive 87.65% of the time, and specific 87.97% of the time.
  Keywords: COVID-19; artificial intelligence; AI; deep learning; machine learning tasks; supervised and un-supervised learning.
  DOI: 10.1504/IJIDS.2026.10065685
   
  
• Impact of Exogenous Emotions on Financial Decision-Making: an Empirical Study on Indian Investors  
  by Shivangi Kaushik 
  Abstract: New fronts in investment and financial markets have been swiftly emerging in the recent years. Theories of rational behaviour may be normative or descriptive in nature, that is, they may prescribe how people or organisations should behave in order to achieve certain goals under certain conditions, or they may purport to describe how people or organisations do, in fact, behave. However, in a market that is frequently in frenzy, it is difficult for traders and investors to remain rational. The present research is empirical in nature, investigating the impact of emotions, particularly the exogenous emotions, induced by external factors such as policymakers' decisions or institutional features of the market, impact financial decision making of individual investors. Five hundred eleven retail investors from the northern states of India were chosen for the study. The study presents a scale on exogenous emotions and financial decision making using factor analysis and structural equation modelling (SEM). The present research statistically establishes the impact of exogenous emotions on financial decision making.
  Keywords: emotions; financial decision making; scale development; exploratory factor analysis; EFA; confirmatory factor analysis; CFA; structural equation modelling; SEM.
  DOI: 10.1504/IJIDS.2026.10065852
   
  
• Engagement of University Stakeholders in Social Networks and Characteristics of Posts  
  by Manuela Escobar-Sierra, Javier A. Sánchez-Torres 
  Abstract: This study investigates how sustainability content and message form impact stakeholder engagement at higher education institutions (HEIs). Five top-tier accredited private universities in Medell
  Keywords: sustainability; marketing; engagement; exploratory analysis; machine-learning algorithms; Twitter®; higher education institutions; HEIs; universities.
  DOI: 10.1504/IJIDS.2026.10065867
   
  
• Exploring the Role of Asymmetry in Interval Forecasting from a Tail Risk Perspective  
  by Zhe Zhang, CHOO WEI CHONG, Jayanthi Arasan, WU YOUYUAN 
  Abstract: Compared to evaluating overall interval forecasting performance, this study proposes to assess interval forecasting performance from a tail risk perspective. The focus of this study lies in the interval forecasting performance of different models in the tail data. In this study, GARCH mdoels are employed for interval forecasting of the three major U.S. stock price indices: S&P500, Nasdaq, and DJI. The Coverage rate (CR) and the average Winkler Score (AWS) are used to evaluate the interval forecasting performance. The results of this study show that, for the left-skewed data, asymmetric models have superior interval forecasting performance in the left tail data. And the GJR-GARCH-ST model has the best interval forecasting performance in the left tail data. Overall, this study emphasizes the importance of asymmetric models in interval forecasting, especially for the data with skewness.
  Keywords: Interval forecasting, tail risk, asymmetric models, GARCH models, distributional assumptions, forecasting performance
  
  
• Enhancing Body Fat Prediction Using Machine Learning Hybrid Model integrating Regression and Cluster Analysis  
  by Nihar Ranjan Panda, Kamal Lochan Mahanta, Manoranjan Dash, Preeti Y. Shadangi, Jitendra Kumar Pati 
  Abstract: Body fat percentage (BFP) measurement accuracy is critical for obesity management and BFP estimating approaches are time-consuming and expensive to overcome, cost-effective BFP estimating methods must be developed. Machine learning (ML), particularly hybrid models may efficiently analyse complicated data and produce accurate predictions, providing a potential method to improve obesity therapy. Six regression techniques were used and the predictive performance of the different models was evaluated, which also went through clustering techniques using methods like distance metrics or density-based measurements, to determine the Relationship or dissimilarity of data points. Body density and BFP have a high negative correlation. Support vector regression (SVR) and regularised linear regression performed the best accuracy for predicting BFP. BFP is a vital measure, especially obesity in human health, thus calculating it correctly is currently problematic and expensive ML approaches on large datasets will enhance this procedure more efficiently and cost-effectively.
  Keywords: body fat percentage; BFP; machine learning; regression; clustering.
  DOI: 10.1504/IJIDS.2026.10065992
   
  
• ABCS: an Extended Framework for Data Integration Solutions on Big Data  
  by Thi-Kim-Hien Le, Thanh Ho Trung, Thien Le, Van-Ho Nguyen, Su Le Hoanh 
  Abstract: Across a wide range of industries, big data is increasingly delivering substantial value to businesses. In a broad sense, big data assists companies in enhancing cost efficiency, streamlining time usage, and empowering managers to make precise and prompt decisions. However, to build big data, data needs to be integrated from many different sources via the ETL/ELT process. Therefore, a framework must be established to ensure the data transmitted between information systems is complete and accurate. Today, the role of intermediaries in the audit is vital; data security and access authorisation are set to the highest possible level. Based on those requirements, this research proposes to extend the ABC framework to add security aspects, entitled ABCS framework, including audit (A), balance (B), control (C) and security (S). This is an experimental study with a cloud-based solution based on data from the tourism and hospitality industry. The result shows that data integration systems ensure the recording of data integration history and monitor and control data balance. The systems also help to enhance end-to-end data quality and support the intermediaries in examining the security and auditing the system quickly. This solution is utterly applicable to other domains and platforms.
  Keywords: ABC framework; ABCS framework; data integration; data security; tourism and hospitability industries; big data.
  DOI: 10.1504/IJIDS.2026.10066249
   
  
• A Comparative Study of LSTM Models and Sentimental Analysis for Stock Price Prediction  
  by Sapna Singh, Vishal Agrawal, Abhay Mishra, Suman Kumar Swrnakar 
  Abstract: For several decades, academics have conducted substantial research into stock market patterns. The emergence of computing technology and the growth of machine learning have accelerated research and presented new opportunities. This study seeks to anticipate future stock price shifts by combining previous price data with sentiment-related information. In this study, two models were used. The first is the long short-term memory (LSTM) model, which uses historical prices as independent variables. The stock market prices are then analysed using the support vector machine (SVM) and naive Bayes (NB) techniques. The model was also modified by integrating macro characteristics such as gold and oil prices, USD exchange rates, and yields on Indian Government securities. The models were used to estimate the values of four stocks: Reliance, HDFC Bank, TCS, and SBI. The results shown are the direct outcome of using our method with an accurate count of 96 LSTM cells by using S&P 500 stock dataset.
  Keywords: stock trend prediction; long short-term memory; LSTM; sentiment analysis; financial news.
  DOI: 10.1504/IJIDS.2026.10066253
   
  
• Leaf Disease Detection based on Deep Learning Methods  
  by Sankarsan Panda, Sivajothi E, Ramya R, Rajalakshmi Ramanathan 
  Abstract: There is a direct correlation between plant quality and yield and plant diseases and pests. Through the use of digital image processing, diseases and pests in plants can be identified. Deep learning has made substantial progress in digital image processing in the last few years, beating earlier methods by a wide margin. This paper describes the difficulty of identifying plant diseases and pests and makes a comparison with currently used methods. According to the findings, deep learning has been used to study plant diseases and pests in recent years from three different perspectives: finally, using deep learning, this research examines and predicts how plant disease and pest detection may change in the future. The testing of these structures and methodologies also makes use of a number of operational measures. The study's suggested deep learning method has important consequences for intelligent agriculture, environmental protection, and agricultural production.
  Keywords: soyabean; mung; chilli; mung phali; tomato; cotton; deep learning.
  DOI: 10.1504/IJIDS.2026.10067088
   
  
• A New Framework for Decision Support Systems Based on Big data Analysis  
  by Peyman Arebi 
  Abstract: Organisational environments contain very large data that can only be stored and analysed using big data technology. In this paper, various parts of the decision support systems (DSS) are combined with big data concepts and technologies so that a large amount of data in the organisation is analysed and senior managers use the results of data analysis to make decisions. The big data decision-making has been proposed, which enables managers to use big data analysis effectively in decision-making processes. A new framework for this type of decision-making has been proposed, in which the organisational decision-making process is redefined using big data technologies. In all phases and stages of proposed framework, the latest new technologies in the field of big data have been used so that the analytical results of big data can be used in the shortest possible time in the decision-making of managers at different levels of organisations.
  Keywords: big data; decision support system; DSS; big data analytics; Hadoop; MapReduce.
  DOI: 10.1504/IJIDS.2026.10067772
   
  
• Advanced Psychometric Analysis of Learners' Multiple Levels and Parameters using Machine Learning  
  by Ashima Bhatnagar Bhatia, Kavita Mittal 
  Abstract: Learning is a complex and continuous process that encompasses various cognitive, emotional, and behavioural mechanisms. It occurs throughout life, adapting to different contexts and involving diverse modalities and dimensions. Learning involves acquiring new knowledge, developing cognitive and motor skills, organising information, and discovering new facts and theories. Machine learning algorithms can assist in analysing learner responses, particularly in psychometrics, which aims to understand learners' performance based on limited observations, often in standardised testing. Learning analytics evaluates learners' behaviour and performance in digital educational experiences to improve the learning process. Cognitive and behavioural analytics serve similar purposes but employ different approaches and theories. Deep learning models like the Ludwig Classifier, powered by AI algorithms, can differentiate learning levels based on parameters such as age, gender, and location. By training the model and monitoring its performance, we can assess the effectiveness of the machine.
  Keywords: cognitive; emotional; behavioural; acquisition; knowledge; motor skills; cognitive skills.
  DOI: 10.1504/IJIDS.2026.10068481
   
  
• Workplace Health and Safety Promotion at Restroom Spaces: Strategies for Minimising Biological Hazard Exposition  
  by Vanessa C. Erazo-Chamorro, Ricardo P. Arciniega-Rocha, Ivana Matoska, Mireya Cuarán, Yesenia M. Paz-Cerón, Rudolf Nagy, Gyula Szabo 
  Abstract: Public health protection has become a very intriguing field of interest since the Covid-19 pandemic. Inspired by the efforts to minimize exposure to germs and make public spaces safer. This research is focused on the design possibilities for making public restrooms more efficient at minimising the spread of disease and infections. The point of interest was based on a research survey conducted through social media to collect user concerns about restroom facilities. As a result, the Biological Hazard Exposition after using these facilities was identified as a main matter. In addition, a mechanism that allows minimal interaction with public toilets by creating the possibility to flush using one's foot - while lowering the toilet cover can happen automatically and simultaneously. In that way not only can the excretion of germs from the toilet bowl be avoided, but exposing our skin can be brought to a minimum. New ergonomic creations for public bathroom facilities must evolve from being a taboo topic to finding their place in industrial design solutions as they are an inseparable part of our daily routine.
  Keywords: Health and Safety Promotion; Biological Hazard Exposition; Workplace Health and Safety; Restroom Spaces.
  DOI: 10.1504/IJIDS.2026.10068594
   
  
• A Lesson from a Coffee Beverage Segmentation Study on Enhancing Traditional Cluster Analysis with AI Analytical Approaches?  
  by Elia Oey 
  Abstract: The research aims to perform market segmentation for coffee beverages consumer in the greater Jakarta area and propose possible improvements strategies for each cluster. The research uses a conjoint model from a previous study as the base model, with 5 attributes (brand, price, taste, service quality, and location) each with 2,2,3,2, and 4 levels. The base model is then extended into market segmentation analysis using two-step clustering techniques. The result suggests four consumer clusters: "coffee drinking for benefit", "coffee drinking for necessity", "coffee drinking for lifestyle", and "coffee drinking for indulgence". Proposed marketing and operational strategy action plans are then developed and analyzed utilizing inputs from two AI technologies, ChatGPT and Bard. The novelty of the study is in combining traditional analysis using two-step clustering with innovative AI tools as source of marketing strategy in extending the result that gives a holistic proposal to relevant stakeholders.
  Keywords: Cluster Analysis; ChatGPT; Coffee; Market segmentation,.
  DOI: 10.1504/IJIDS.2027.10068999
   
  
• Performance Evaluation and Development of knowledge-based Systems: A Survey  
  by Huma Parveen, S.W.A Rizvi, Raja Sarath Kumar Boddu 
  Abstract: One of the foremost family members of the Artificial Intelligence (AI) group is known as Knowledge-Based System (KBS). With the accessibility of sophisticated computing services and other sources, nowadays consideration is turning to high challenging tasks that may need intelligence. This survey intends to make a review on 68 papers concerning knowledge-based systems. As a result, systematic examinations of the approaches used are carried out and briefly described. The results of each contribution are also shown in this survey. Finally, the report offered a number of research challenges that may be useful to scholars working on KBS models in the future. The key findings of the research study are, the need for stronger methodological support and adherence, improved knowledge availability and traceability, and a quantitative methodology to ensure the efficiency of KBS development and implementation projects.
  Keywords: Knowledge-Based System; CAD Modelling; Reliability; Expert Knowledge; Domains.
  DOI: 10.1504/IJIDS.2027.10069008
   
  
• Adaptive Short-Term Parking Demand Prediction: a Case Study  
  by Semeneh Hunachew Bayih, Tilahun Surafel Lulseged 
  Abstract: Urban parking demand is rapidly increasing, leading to severe traffic congestion and environmental issues. Accurate prediction of parking demand is essential for effective urban planning and traffic management. This study proposes a novel approach using a discrete non-homogeneous Markov chain model with an adaptive learning algorithm to predict short-term parking demand. The model dynamically adjusts to changes in demand patterns by incorporating new data. A case study is conducted to validate the model's performance. Sensitivity analysis is performed to assess the impact of learning parameters on prediction accuracy. The results demonstrate the model’s effectiveness using Mean Absolute Error (MAE), Mean Squared Error (MSE) and Root Mean Squared Error (RMSE) in accurately predicting parking demand, with a low average error of 1.1%. This study contributes to improved urban planning, traffic management, and sustainable transportation solutions.
  Keywords: parking search; demand prediction; discrete Markov chain; non-homogeneous Markov chain; adaptive algorithm; algorithm validation.
  DOI: 10.1504/IJIDS.2027.10069442
   
  
• Modelling and Predicting the Spread of Epidemic Outbreak using Machine Learning Model  
  by Soni Singh, Sonam Mittal, Glory Prasanth K, Vaitheeshwari S 
  Abstract: The COVID-19 outbreak is now posing a severe hazard to the worldwide community. Every nation's government must pay special attention to the study of this disease to take the necessary efforts to decrease the impact of this global epidemic. This study studied the disease outbreak in the Indian region through July 21st, 2021, trained on it, and assessed the total number of infected cases over the next upcoming weeks. Machine learning algorithms such as the ARIMA model were used to create predictions based on information received from the World Health Organization's (WHO) official webpage for India between January 20, 2020, and May 21, 2021. R2-score RMSE, a measure of model performance, was employed to evaluate performance, and it ranged between 2150.435068 and 42.523137. The expected incidences throughout the four weeks of test data are projected to be between 200K and 390K, which is quite close to the actual statistics. With the help of this study, the government and clinicians will be able to develop future initiatives.
  Keywords: Health; Growth Rate; ARIMA Model; Analysis and Prediction.
  DOI: 10.1504/IJIDS.2027.10069559
   
  
• Mediating Impact of Attitude and Pro-Environmental Self-Identity between Gandhian Values and Sustainable Consumption Behaviour using Theory of Planned Behaviour  
  by Nancy Gupta, Ipshita Bansal, Meenakshi Gandhi 
  Abstract: The conceptual framework incorporates Gandhian Values, pro-environmental self-identity, impact on sustainable consumption behaviour extending Theory of Planned Behaviour. The main objective of the research is to investigate the impact of Gandhian values on sustainable consumption behaviour. A total of 716 consumers were used for analysing the data with the help of SmartPLS 4.0.9.5 software, Partial Least Square Structural Equational Modelling. The results revealed that Gandhian values significantly influence sustainable consumption behaviour. Attitude and pro-environmental self-identity mediates the values-behaviour. The research offers a fresh perspective to the existing theoretical frameworks in behavioural social sciences where values play a key role to understand sustainable consumption.
  Keywords: Sustainable consumption behavior; Gandhian Values; intention; attitude; pro-environmental self-identity.
  DOI: 10.1504/IJIDS.2027.10069699
   
  
• Mastering the Beauty of Arabic Script: Pioneering Guided Classification for Handwritten Character Recognition  
  by Walid Fakhet, Salim El Khediri, Moulahi Tarek, Salah Zidi 
  Abstract: Automatic recognition of handwritten characters from im- ages poses significant challenges across various languages, with the Ara- bic language presenting unique difficulties due to its distinct writing sys- tem. Despite considerable advancements in optical character recognition (OCR), Arabic handwritten character recognition (AHCR) remains par- ticularly problematic. This paper introduces a novel classification system termed guided classification, which integrates convolutional neural net- works (CNN) with both K-means and hierarchical agglomerative clus- tering (HAC) algorithms. The proposed model was evaluated on three datasets, AIA9K, AHCD, and HIJJA, achieving classification accuracies of 95%, 98%, and 90.8%, respectively. Comparative analysis revealed that K-means clustering outperforms HAC in terms of classification accuracy. These results underscore the model’s efficacy in improving AHCR per- formance through the synergistic use of CNN and K-means clustering.
  Keywords: Arabic Handwritten Character Recognition; Convolutional Neural Networks; Deep Learning; K-Means Clustering; Hierarchical Agglomerative Clustering.
  DOI: 10.1504/IJIDS.2027.10069851
   
  
• Optimising Accuracy Rate of Genomic Image Representation of Human Corona Virus Sequences for COVID-19 Detection using Modified Quantum-Based Marine Predators Algorithm  
  by Subashree S, Sharanyaa S., Harikrishnan R, Gowri Ganesh 
  Abstract: Over a million people around the world got the awful coronavirus (CoV) sickness (COVID-19). This study is the first to show that genomic image processing (GIP) methods can be used to quickly and correctly identify COVID-19 and other human CoV diseases. At first, genomic data-based graphics mapping methods were used to turn the genome sequences into genomic greyscale photos. Statistics were used to build and test different models, such as k-nearest neighbours (KNN), which were based on the pictures. KNN was very good at finding COVID-19 and other COVs that come from people. A total of 99.39% of the time, it was right. It had an F1-score of 0.99, a correlation value of 0.99, a sensitivity score of 99.31%, and a specificity score of 99.47%.
  Keywords: covid 19; genomic image; deep learning; feature selection; modified quantum-based marine predators algorithm (Mq-MPA); SVM.
  DOI: 10.1504/IJIDS.2027.10070075