This issue presents a diverse collection of research addressing emerging challenges across artificial intelligence, information security, cloud computing, blockchain, healthcare, education, smart transportation, energy transition, and enterprise technologies. The featured studies explore blockchain-enabled research integrity, reputation quantification, neuroevolutionary autonomous systems, AI-driven medical diagnosis, privacy-preserving machine learning, immersive photovoltaic adoption, cloud performance, SaaS customization, supply-chain analytics, computational thinking assessment, wireless security, reproducible computing, configuration management, product authenticity, precision industrial synchronization, decentralized asset exchange, and bias-aware natural language processing. Together, these contributions highlight innovative computational approaches, practical deployment frameworks, and interdisciplinary solutions for advancing intelligent, secure, and scalable digital ecosystems.
Published
September 2026
Contributions
20 articles
Access
Open access

Explore the research published in this issue of ijisds.
Kaushal Thaker
This manuscript analyzes a severe security flaw embedded within standard wireless protocols, demonstrating how threat actors can silently force devices onto unintended, yet seemingly secure, Wi-Fi networks. We highlight a core architectural oversight wherein the Service Set Identifier (SSID) is not continuously cryptographically validated across all stages of connection, paving the way for advanced SSID spoofing. To substantiate this threat, we engineered a multi-channel machine-in-the-middle (MC-MitM) framework utilizing independent wireless transceivers to capture and manipulate beacon and probe response packets, achieving successful network deception across Windows, macOS, iOS, Android, and Linux environments. The empirical results verify that contemporary wireless hardware is broadly defenseless against passive SSID manipulation. We dissect the precise mechanics of this exploit, outline the substantial risks it poses to network integrity and data confidentiality, and recommend backward-compatible defenses alongside necessary revisions to the IEEE 802.11 standards. This analysis emphasizes the urgent need to integrate rigorous authentication checks to protect wireless links from sophisticated digital impersonation.
Sheshukumar Vangala
This paper advances a novel IT-centric methodology for evaluating academic reputation within distinct computer science subareas, leveraging a Markov network-based metric known as P-score. Unlike traditional citation-based rankings, the proposed approach introduces a normalized and weighted reputation scoring system that mitigates cross-subarea encroachment and accurately captures the research impact of publication venues and graduate programs. By integrating DBLP data with curated subarea taxonomies, the study demonstrates a precision-optimized mechanism for identifying top-performing institutions and venues in fields such as Information Retrieval, Databases, and Data Mining. This subarea-specific evaluation provides actionable insights for funding allocation, policy design, and strategic research positioning within the information technology domain, revealing notable divergences in research emphasis between Brazilian and U.S. academic landscapes.
Sheshukumar Vangala
This paper applies Neuroevolution of Augmenting Topologies (NEAT) to learn control policies for autonomous racing in a simulated continuous action space. We evolve neural networks to optimize racing performance through a multi-stage experimental framework, evaluating their ability to learn steering, speed regulation, and trajectory planning. Results show that NEAT can discover near-optimal steering behaviors but struggles with simultaneous acceleration and positioning optimization, revealing challenges in evolving policies for complex multi-output control tasks. The study offers insights into fitness function design, state representation, and curriculum learning in neuroevolution for dynamic control applications.
Apeksha Bhuekar
The goal of this paper is to develop intelligent agents through fuzzy logic so that they can be capable of adaptability and context awareness in a simulated operational environment. Concentrating on dynamic interactions, fuzzy inference systems help agents to adjust their behavior according to proximity, velocity, and environmental conditions. The suggested approach helps to develop adaptive and robust automated decision-making systems. These components can optimize complex multi-stakeholder systems explicitly beneficial for modern supply chain systems. The paper states that AI can be used to enhance the flexibility and reactivity of logistics and inventory management systems, offering various technical and practical contributions.
Apeksha Bhuekar
This manuscript presents a refined iteration of Dr. Scratch, an online platform designed to autonomously evaluate Computational Thinking (CT) proficiencies demonstrated within visual coding artifacts. To overcome the constraints inherent in traditional rule-centric evaluation engines, we introduce a scoring architecture grounded in fuzzy logic. This study surveys pertinent historical efforts, outlines the analytical methodology used to parse Scratch programs, and clarifies the computational parameters evaluated when calculating CT metrics from student-generated submissions. By embedding fuzzy inference, our approach yields continuous, transparent evaluations across fundamental CT vectors. An empirical review involving upwards of 250 Scratch submissions indicates that, in contrast to rigid deterministic models, this fuzzy framework delivers superior precision, closer correspondence with teacher appraisals, and enhanced clarity. We outline initial outcomes from this research, propose upcoming trajectories, and tackle prevailing bottlenecks in digital pedagogical evaluation. Ultimately, this research propels Educational AI forward, offering a more sophisticated, instructionally aligned paradigm for measuring computational reasoning.
Santosh Vemula
This paper presents MetaConfigurator, a tool that generates customizable graphical user interfaces (GUIs) for editing YAML and JSON configuration files based on a provided data schema. By leveraging the expressiveness of JSON Schema (draft 2020-12), MetaConfigurator offers a flexible and efficient way to edit configuration files while maintaining the speed and control of traditional code editors. The tool reduces the need for bespoke GUIs tailored to specific schemas, streamlining workflows for developers and non-technical users alike. MetaConfigurator's key features include schema-based data retrieval, file modification, and schema editing. Although it currently supports JSON Schema 2020-12, potential improvements include extending support to other schema drafts, integrating code generation, and enhancing support for YAML and comment preservation. User feedback from a study indicates that MetaConfigurator effectively addresses practical tasks, suggesting its applicability in real-world scenarios. Further refinements such as desktop integration, interactive tutorials, and expanded format support are proposed to enhance the user experience.
Mohammed Mafaz Nadherssa
Respiratory and cardiovascular diseases represent significant global health burdens, particularly in resource-constrained settings where access to specialized medical expertise is limited. This paper presents a comprehensive machine learning pipeline for auscultation-based diagnosis that converts short electronic stethoscope recordings into spectrogram- and chromogram-based tensors, trains a compact convolutional model with a fused scalar-audio head, and outputs multi-condition diagnostic labels. The system addresses asthma, COPD, pneumonia, heart failure, lung fibrosis, pleural effusion, and normal findings using a dataset comprising 112 participants recorded with a 3M Littmann electronic stethoscope across standardized chest zones. Preprocessing includes 2.5-second segmentation, 4 kHz resampling, denoising, and multi-channel feature construction to support robust learning from nonstationary respiratory and cardiac signals. The proposed architecture achieves strong performance on held-out data with overall accuracy, precision, recall, and F1-score all approximately 0.89, demonstrating particular resilience across minority classes. The complete system is operationalized on embedded hardware using a Raspberry Pi with a USB audio interface and a touch LCD for on-device recording, inference, and user feedback. This work illustrates a practical pathway from clinical audio machine learning to real-world telehealth deployment at the edge, offering potential for improved healthcare accessibility in underserved regions.
Mohammed Mafaz Nadherssa
This paper presents a probabilistic approach to binary image segmentation that models foreground-background occlusion with pixel-wise Gaussian emissions and mask-conditioned independence, comparing iterated conditional modes, exact expectation maximization, Gibbs-sampled EM, and variational mean-field EM for learning and inference under a free-energy objective grounded in KL minimization. The dataset is synthesized by compositing masked foreground exemplars over background textures and injecting Gaussian sensor noise, enabling controlled evaluation of convergence behavior and parameter recovery for class priors, per-pixel mask probabilities, and emission statistics. An engineering-focused pipeline is outlined for operationalizing the segmentation workflow with Azure services and DevOps: infrastructure-as-code for GPU compute and storage provisioning, CI/CD for training artifacts, reproducible runs and model registry integration, and experiment tracking for algorithm variants; this demonstrates how classical probabilistic graphical models can be productionized alongside modern MLOps while preserving explainability and modular update rules. Results highlight trade-offs between hard assignments and uncertainty-aware posteriors, noting local optima sensitivity in ICM and improved robustness from stochastic sampling and variational factorization, and motivate deployment patterns that separate data synthesis, inference kernels, and monitoring to support maintainable computer engineering systems.
Eeshwar Pasula
Reproducibility in computational text analysis is often undermined not by missing data or code, but by the gradual decay of software environments. This paper introduces a framework for the retrospective reconstruction of R-based computational environments used in natural language processing research, enabling the re-execution of legacy text analysis pipelines that would otherwise fail due to package obsolescence, version conflicts, or system-level dependencies. We present a method that queries archival snapshots of CRAN, Bioconductor, and GitHub to resolve complete dependency graphs at specific historical timestamps, capturing not only package versions but also R interpreter versions and system requirements. These specifications are then containerized via Docker, producing isolated environments that faithfully replicate the original computational context. We demonstrate the utility of this approach on several case studies drawn from computational social science and bioinformatics, including the recovery of a defunct text classification package (maxent) and the successful re-execution of code accompanying a quanteda software paper. The method supports both retrospective archaeology and prospective compendium construction, offering a pathway toward long-term executability of NLP workflows independent of commercial snapshot services. All tools are open-source and designed to integrate with existing reproducibility ecosystems.
Muneebuddin Syed
Ensuring product authenticity and in‑market quality has become a core responsibility for product and operations teams, especially in categories exposed to counterfeiting and spoilage. This paper presents an AI‑driven framework that uses computer vision and machine learning to support product integrity management by automating logo authenticity checks and physical condition assessment. A multimodel pipeline combining object detection, convolutional neural networks and classical classifiers is applied to branded items and perishable goods, enabling near real‑time detection of counterfeit logos and early signs of quality degradation from standard product images. Experimental results show high accuracy in distinguishing genuine from fraudulent products as well as in classifying fresh versus spoiled items, demonstrating the system’s potential as a decision‑support tool for product managers, quality teams and supply‑chain partners. By embedding these AI capabilities into product workflows, brands can reduce counterfeit circulation, protect customer trust, and make more data‑driven decisions on inventory, recalls and lifecycle interventions.
Read the articles online or download individual PDFs from this issue.