International Journal of Data Science, Bioinformatics and Cyber Security

International Review of Digital Trade and Artificial Intelligence

Rony Barua — 2026-01-28

The acceleration of digital trade has fundamentally reshaped the global economic landscape, with Artificial Intelligence (AI) emerging as a central driver of cross-border innovation, efficiency, and competitiveness. Recent advances in AI-enabled e-commerce automation, predictive logistics, data governance, and digital financial systems have increased the velocity, trustworthiness, and scalability of international digital markets. However, the integration of AI into global trade remains fragmented due to uneven regulatory regimes, data sovereignty conflicts, infrastructure disparities, and algorithmic risks. Existing studies provide important insights into the intersection of AI and digital trade, but a holistic, unified analytical framework remains missing. This article offers a comprehensive international review of AI-enabled digital trade and introduces the AI-Driven Digital Trade Integration Framework (AIDTIF), which conceptualizes AI’s role across digital infrastructure, regulatory governance, enterprise adoption, cybersecurity, and global value chain participation. The framework is validated through comparative literature triangulation, theoretical reasoning, and scenario-based assessments grounded in existing empirical work. Findings demonstrate that AI significantly enhances digital trade performance by reducing transaction friction, enabling scalable analytics, improving cross-border logistics, supporting small-market inclusion, and strengthening digital compliance. However, risks related to algorithmic bias, cybersecurity, legal fragmentation, and unequal absorption capacity remain persistent. The article concludes by outlining strategic policy, industry, and research recommendations to build an interoperable, equitable, and sustainable AI-enabled global trade ecosystem.

Person Reidentification Using Facial and Fabric Feature Extraction

Vanitha Sivagami S — 2026-02-06

Purpose: Person identification across surveillance cameras with non-overlapping fields of view has emerged as a highly challenging and intriguing area of study in smart surveillance. Though numerous approaches have been carried out, proposed, and developed, unresolved issues and limitations persist.

Methods: Existing re-identification methodologies generally, involve extracting feature vectors from images or video frames and applying various similarity or dissimilarity measures to compare these vectors. Some approaches rely on models based on fabric colour or facial features information, the ultimate objective of all these methods is to attain higher matching accuracy and at the same time lower computational costs. This work involves the study of person re-identification, using the classification of feature vectors for facial and fabric images, represented as a visual word dictionary, and person matching is carried out using different baseline methods. The primary novelty of this work lies in a selective and context-aware fusion of facial and fabric features within a Bag of Visual Words (BoVW) framework enhanced by Spatial Pyramid Matching (SPM) for person re-identification in non-overlapping camera environments. Unlike existing approaches that rely solely on either global appearance features or deep learning–based representations, the author's method explicitly separates and independently models facial and fabric regions, enabling robust re-identification under clothing variations and pose changes.

Results: Experiments are done with various benchmark datasets, and comparisons are done with various baseline methods, which show that the method gives 99% accuracy for the ETHZ dataset.

Conclusion: Person ReID using facial and fabric feature extraction has been carried out using Bag of Visual Words (BoVW) features. Also, to include spatial information of features, BoVW features are grouped using spatial pyramid matching, and the performance of the system has been improved.

Adaptive Replication Strategies for Latency Reduction in Geo-Distributed Databases

Mission Franklin — 2026-05-16

Geo-distributed databases are fundamental to modern cloud-based and globally distributed applications, enabling data availability and fault tolerance across geographically dispersed regions. However, these systems frequently suffer from high access latency due to physical distance between data centers, fluctuating network conditions, and the overhead introduced by strict consistency guarantees. Traditional static replication strategies, which rely on fixed replica placement and replication factors, are poorly suited to such dynamic environments and often result in inefficient resource utilization and increased response times, particularly for latency-sensitive applications. This study proposes an adaptive replication strategy designed to minimize latency in geo-distributed database systems by dynamically adjusting both replica placement and replication factor in response to changing workload conditions. The approach continuously monitors real-time workload characteristics, including data access frequency, regional demand distribution, and network latency metrics. Predictive models are employed to identify frequently accessed (hot) data items and anticipate future access patterns, enabling proactive replication or relocation of data closer to regions with high demand. By aligning replication decisions with observed and predicted workload behaviour, the proposed strategy seeks to balance performance gains with consistency and resource overhead. The effectiveness of the proposed approach is evaluated through comprehensive simulation and experimental analysis. Key performance metrics, including read and write latency, system throughput, and consistency-related overhead, are measured and compared against conventional static replication schemes. The results demonstrate significant reductions in access latency and improved system responsiveness without incurring excessive consistency costs. These findings highlight the potential of adaptive replication as a practical and scalable solution for latency optimization in geo-distributed database deployments, offering valuable insights for the design of performance-aware distributed data management systems.

AI-Driven Inclusive Design Optimization of Musical Instruments for Musicians with Disabilities

Rittwik Mahmud — 2026-06-10

This research investigates the role of Artificial Intelligence (AI) in optimizing the inclusive design of musical instruments for musicians with disabilities. Traditional musical instruments are primarily designed for able-bodied performers and often present significant physical, sensory, and cognitive barriers for individuals with disabilities. As a result, many musicians face limitations in musical participation, creative expression, and professional performance. To address these challenges, this study proposes an AI-driven inclusive design framework that integrates adaptive technologies, machine learning algorithms, sensor-based interaction systems, and participatory design approaches to create accessible and personalized musical instruments. A mixed-method research methodology was adopted, involving 30 participants with diverse disabilities, including motor impairments, visual impairments, and hearing-related challenges. Data were collected through wearable sensors, gesture-recognition devices, electromyography (EMG), and user feedback systems to evaluate interaction efficiency and accessibility requirements. The proposed framework employed neural networks for gesture recognition, reinforcement learning for adaptive response optimization, and generative AI techniques for customized instrument design and interface development. The AI system dynamically adjusted parameters such as pitch mapping, sensitivity, control layout, and haptic feedback according to individual user abilities and preferences. The experimental findings demonstrate that AI-optimized instruments significantly improve accessibility, usability, and user satisfaction compared to traditional instruments. Accessibility scores increased from 45% to 88%, while user satisfaction improved from 52% to 91%. In addition, learning time and performance error rates were substantially reduced due to adaptive interaction mechanisms and personalized control systems. The participatory design process further enhanced usability by actively involving musicians with disabilities in the design and evaluation stages. The study concludes that AI-driven inclusive design has strong potential to democratize musical creativity and support equitable participation in music performance. The proposed framework contributes to the advancement of accessible digital musical instruments and provides a foundation for future research on intelligent assistive music technologies, including brain-computer interfaces, emotion-aware systems, and low-cost adaptive musical solutions.

AI-powered Health Care System using Machine Learning and Deep Learning

Chapa Krishnaveni — 2026-06-12

The web app is a Health Assistance Web Application that helps people get healthcare advice in a way that makes it easier to find, trust, and use. The first step is a safe sign-up and login process in which the user enters their name, phone number, email address, and password to create an account. The user additionally provides an email address and password to prove who they are. When a user logs in to their own personalized user interface (UI), they are directed through the process of registering their location step by step. First, they choose the state, and then they click on it to choose the district for their profile and to provide a “Hospitals Near Me” option. After establishing the location, the user is taken to an AI-powered Symptom Chatbot that takes the symptoms as input and forecasts likely diseases. This is done utilizing integrated machine learning and AI APIs like Google Gemini. The chatbot is well thought out, and it goes a step further by showing the results in clickable bubbles, like precautions and medicines. This makes it easier for the user to find safety tips or typical medical advice. To help users get expert medical treatment when they need it, the app also gives them a list of nearby hospitals with their names, phone numbers, and addresses. The goal of the system is to be an early medical guidance app, not a replacement for doctors. Its goal is to help people figure out any probable health problems, any possible delays in taking action, and the best ways to get to the hospital when required. The idea is like a digital health companion that helps people take charge of their health and find their way through health problems if they need to. The healthcare system has evolved because of AI, deep learning, and machine learning. These technologies make it easier to diagnose, predict, and keep an eye on patients. In healthcare, the most frequent models are convolutional neural networks (CNNs), support vector machines, transformers, and recurrent neural networks (RNNs). They aid with genomes, medical imaging, and predicting diseases. The CNN is more accurate when it comes to medical imaging. Long and Short-term Memory and RNN look at a lot of organized and unstructured data to detect chronic diseases. Transformers assist in processing a lot of genomic datasets and clinical texts to improve tailored treatment. The model looks at how the disease spreads before the symptoms get worse. It improves patient outcomes, operational efficiency, and access to healthcare, which is excellent for both patients and healthcare systems. New technologies like explainable AI and federated learning could revolutionize the healthcare system in the future to make it easier for doctors to understand, be honest about, and trust the choices they make.