Asian Journal of Research in Computer Science
Not a member yet
792 research outputs found
Sort by
Design and Implementation of a Homomorphic Cryptosystem Model for Electronic Voting in the DRC Cloud Environment
No full textThis article focuses on the design and implementation of a homomorphic cryptosystem model, specifically designed for a private cloud, to protect sensitive data in the context of electronic voting in the Democratic Republic of the Congo (DRC). The homomorphic cryptosystem represents a promising solution for combining data security and functionality. The main objective is to develop a system capable of performing calculations on encrypted data without compromising its confidentiality, thereby ensuring the security of the information.
The study addresses several crucial issues, including ensuring the security and confidentiality of sensitive data, the integrity and transparency of electoral processes, and the adaptation of advanced technologies to the local realities of the DRC.
The proposed model adopts a multi-layered architecture, encompassing physical infrastructure, virtualisation, to create isolated environments, and orchestration and automation tools to enhance efficiency.
The results demonstrate the technical feasibility of this model, capable of ensuring the confidentiality, integrity, and verifiability of electoral processes. However, challenges remain, such as algorithmic complexity and system interoperability. increased awareness among political actors and civil society is essential to promote the adoption of this innovative technology. This article presents a model of a cryptosystem homomorphic suitable for a private cloud to protect data sensitive during electronic voting in the DRC. The results show the technical feasibility of this approach, capable of guaranteeing confidentiality, integrity and process verifiability in elections
IoT and Edge Computing Integration for Intelligent Fault Diagnosis and Self-Healing in 132 kV Transmission Networks
No full textTraditional SCADA and relay-based protection, with typical latencies of 2–10 seconds, are inadequate for the resilience required in modern 132kV transmission networks. This paper reviews the integration of Internet of Things (IoT) sensor fabrics, including Phasor Measurement Units (PMUs) and distributed sensors, with a hierarchical Edge Computing infrastructure to enable autonomous fault diagnosis and self-healing. The authors analysed the deployment of computational intelligence across device, substation, and fog layers, emphasising how local processing mitigates cloud latency. The review examined optimised AI/ML models (such as wavelet-based Support Vector Machines and pruned 1D-CNNs) for real-time fault detection, classification, and location at the network edge. Furthermore, the study explored the role of IEC 61850 GOOSE protocols, with < 4ms latency, in enabling closed-loop actuation for autonomous isolation. This synthesis demonstrates a viable architecture for sub-second self-healing. This paper\u27s primary contribution is its holistic synthesis of these technologies into a single, cohesive framework, highlighting critical research challenges in cybersecurity, interoperability, and data integrity that must be addressed for industrial applications
A Systematic Review of Machine Learning and Deep Learning Approaches for Heart Disease Prediction
No full textMachine learning (ML) and deep learning (DL) approaches have shown increasing promise for heart disease prediction, but comprehensive evidence regarding their effectiveness compared to traditional clinical methods, implementation challenges, and real-world deployment readiness remains fragmented. Healthcare systems require systematic evaluation of these approaches to make informed decisions about clinical adoption, yet current literature lacks comprehensive synthesis of performance outcomes, generalizability challenges, and practical implementation considerations. This systematic review evaluates studies published between 2020 and 2025 to: (1) evaluate ML and DL approaches applied to heart disease prediction and assess their effectiveness compared to traditional clinical methods; (2) examine commonly used datasets and evaluation metrics; (3) compare algorithm performance and generalization capabilities between ML and DL approaches; (4) investigate how interpretability and explainability influence model selection and clinical adoption; and (5) identify challenges and gaps remaining for real-world deployment. A systematic search was conducted across multiple databases for peer-reviewed studies published between 2020–2025. Studies were included if they applied ML/DL algorithms to heart disease prediction using clinically relevant data, included comparative analysis with traditional methods, reported quantitative performance metrics, and provided sufficient methodological details. Data extraction focused on ML/DL approaches, performance results, validation methods, study limitations, and effectiveness findings using structured extraction forms. Thirty-one studies met inclusion criteria, representing diverse global applications. Traditional ML methods appeared in 19 studies (Random Forest n=10, XGBoost n=8, Logistic Regression n=8, overlap present). Deep learning appeared in 16 studies, with CNNs dominant in imaging-based prediction. ML/DL approaches demonstrated superior performance in 17 of 31 studies, while an additional 7 studies reported non-inferior or equivalent performance, indicating that most applications performed at least as well or better than clinical baselines. AUC improvements ranged from 0.01–0.21 across validated models. XGBoost excelled in structured tabular data, while deep learning dominated imaging-based tasks. However, only ~50% of studies performed external validation, with several reporting performance degradation on external datasets. Critical gaps included limited interpretability evaluation, persistent algorithmic bias, incomplete prospective validation, and minimal reporting of real-world clinical integration — reflecting challenges that must be addressed before widespread deployment is feasible
E-business and Digital Marketing Strategies: Innovations, Challenges, and Emerging Trends
No full textE-business and digital marketing evolution has revolutionized business communication with clients and markets through sales channels to establish deeper relationships for enhanced competitive position. This review combines knowledge from 20 recent studies to analyze the dual nature between e-business models and digital marketing approaches with a focus on combined operations supported by new technology and their revolutionary characteristics. The main assessment goal focuses on understanding how artificial intelligence (AI), Machine learning (MC) and big data analytics drive digital transformation of e-business methods and customer relations.
Several studies document how businesses gain superior user interactions through AI-based personalization and predictive analysis and influencer marketing which leads to better user conversion rates and market performance. The scalability of E-business faces barriers because data privacy threats combined with cybersecurity risks and vigorous technological adoption. This analysis tracks upcoming industry shifts through block-chain adoption for protected deals and meta-verse services alongside ethical AI management that present opportunities to reshape digital domains of the future.
The business landscape requires a changed approach to develop data-based agile strategies for maintaining competitive positions. Policy directors need to create data protection regulations and friendly innovation frameworks. Research analysts can utilize this data exploration to study unexamined topics about immersive technology effects on customer actions throughout extended periods. This review connects theoretical models with real-world operations thereby delivering a strategic guide for researchers to handle marketing challenges in the emerging digital world
Quantum-enhanced Federated Learning for Ethical Medical Image Analysis
No full textQuantum-Enhanced Federated Learning for Real-Time Medical Image Analysis with Ethical AI Governance is a nascent approach combining the principles of federated learning and quantum computing to transform the medical image analysis sector with due regard to the most critical ethical principles. Reflecting on the definition, federated learning is an approach that allows several institutions to jointly train machine learning models without the need to share any patient\u27s data. Therefore, FL is the industry-institution strategic tool that allows for a higher level of privacy security in healthcare. On the other hand, by embracing quantum computing, the developed approach includes more sophisticated computational skills, permitting improved data performance and enhanced model accurateness, a pivotal factor for real-time medical diagnosis. Consequently, the significance of the approach lies in the potential to boost the medical image analysis sector. Quantum-enhanced FL will help comply with the most rigid ethical requirements by involving decentralized data performance and exploiting various datasets characteristic of healthcare providers. This will be particularly pivotal since the current state deems quick and precise medical decisions as of the essence, precisely when imaging tools are developed for early disease detection and recognition.
Additionally, the integration presents an opportunity to address the challenges naturally associated with FL, i.e., model accurateness and data heterogeneities. Therefore, quantum algorithms are incorporated to perform training in much more optimized ways than classical alternatives. However, ethical AI governance will remain challenging with the current FL-quantum integration. As the type continues developing, the issues will concern AI consideration, algorithmic perfidies, and accountable decision types so that proper directives are in line.
Research continues to advance, but stakeholders must address these ethical considerations to fully leverage the promise of quantum-enhanced federated learning to revolutionize medical image analysis.
Thus, a quantum-fed network of neural networks can lead the way in developing solutions that combine the efficiency of quantum computing and the importance of ethical approaches in data management. Responsible and effective utilizing this technology requires continued collaboration between researchers, healthcare providers, and policymakers.
"Simulations show our quantum FL model improves tumor segmentation accuracy by 12% (Dice score) over classical federated learning while maintaining stronger privacy guarantees.
Ensemble Learning Techniques for Breast Cancer Prediction
No full textBreast cancer is predominantly diagnosed in women and remains a leading cause of rising health concerns among females. Manual identification of the disease is often time-consuming and limited in accessibility. To address this, automated diagnostic systems using machine learning (ML) have become increasingly valuable for early detection and classification of cancer. This paper explores the use of machine learning and ensemble learning techniques for classifying tumors. Specifically, it evaluates the performance of Logistic Regression, Support Vector Machines (SVM), Decision Trees, and Random Forests on a breast cancer dataset. The study compares models based on key performance metrics, including False Positive Rate, Accuracy, Precision, and Recall. The effectiveness of ensemble learning methods is also analyzed and benchmarked against individual models. Statistical analysis reveals that the ensemble model combining Decision Tree and Random Forest algorithms achieves an accuracy of 89.3%, while the ensemble of Logistic Regression and SVM reaches an accuracy of 90.4%. These ensemble models outperform their counterparts, demonstrating the advantages of combining multiple algorithms for improved diagnostic accuracy
Natural Language Processing Based on Movie Rating System Using Microblogging
No full textMovie recommendation systems help users quickly find movies that match their preferences, similar to platforms like Netflix, which personalize suggestions based on individual viewing habits. As digital content grows exponentially with technological advancements, users face challenges in discovering movies that align with their taste, sentiment, and genre. To address this issue, various software solutions have been developed to improve movie recommendations. However, traditional recommendation methods, such as content-based and collaborative filtering, often struggle to deliver highly personalized suggestions. To enhance accuracy, this system leverages advanced sentiment analysis techniques to evaluate user reviews and align recommendations with individual preferences. By incorporating multiple algorithms, the system improves personalization and ensures an intuitive, user-friendly interface for a seamless movie discovery experience
Revolutionizing Alzheimer’s Diagnosis Cutting-Edge Handwriting Analysis Technology
No full textAlzheimer’s disease (AD) is a progressive and incurable neurological disorder that affects both cognitive and motor functions, including fine motor skills such as handwriting. Early diagnosis is crucial to slow the progression and improve patient outcomes, especially as current treatments are largely palliative. In this study, we present a non-invasive and cost-effective approach for early AD detection using handwriting analysis combined with machine learning (ML) techniques. The DARWIN dataset, comprising 174 samples and over 25 kinematic and dynamic handwriting features, was used to train and evaluate classification models. Feature selection was performed using Analysis of Variance (ANOVA) and Recursive Feature Elimination with Cross-Validation (RFECV). Multiple ML classifiers were applied, and their performance was validated using repeated K-Fold and Monte Carlo Cross-Validation strategies. A voting ensemble classifier achieved 100% accuracy with ANOVA-selected features and 88.6% with RFECV-selected features. While these results are promising, the exceptionally high accuracy may indicate potential overfitting due to the limited dataset size, warranting further external validation. This research highlights the potential of handwriting-based screening tools as accessible, low-cost aids for early AD diagnosis in both clinical and remote healthcare environments
Enhancing Customer Experience through AI-Enabled Journey Mapping in Luxury Travel Enterprises
No full textCurrently, the trend within the luxury travel market is to be client-focused by offering a quality and unique experience. As more and more clients’ demand personalization investing in customer journey mapping and tailor-made travel experiences while growing competition in the luxury travel market more travel agencies turn to artificial intelligence. This research focus on the uses of AI to monitor and analyze customers throughout the travel processes and to provide them with personalized solutions. The study aims are as follows: The first is the determination of the role AI can play in the recognition of the customers’ needs, desires, and purchase patterns and how luxury travel agencies can apply this knowledge to improve the services they offer.
For this, a research method of the qualitative type is used, being focused on the analysis of the experience of the world’s leading travel-related companies that use AI platform, including HubSpot, to work and process the customer data. By examining the customer’s journey and analyzing patterns in behaviors, which include; the customer’s most visited destinations, special request or non-tolerances such as long working hours or no access to leisure time, these agencies will be able to offer valued added services such as suggesting leisure activities after extended working hours or arranging current or future working schedules to ensure they do not cause unnecessary drudges.
The study establishes that AI plays an important role in optimizing customer experience and smooth elimination of bottlenecks and thereby enhancing customer satisfaction. Moreover, the study shows that AI improves not only the personalization of the services provided but also the customer loyalty as the clients are more likely to return to the company that offered them exactly what they need and want. The study also showcases the that AI can offer in luxury travel and offers a template for other players in the sector to emulate when it comes to using AI for journey mapping and personalization. The study also demonstrated that AI should become a strategic marketing resource aimed at improving customer loyalty and raising the quality of services provided in the segment of luxury travel
The Benefit of Artificial Intelligence (AI) on Operational Efficiency in Hotel Management: A Case of Selected Hotels South West Nigeria
No full textThis study examines the impact of artificial intelligence (AI) on operational efficiency in hotel management, focusing on selected hotels in Southwest Nigeria. The study investigated four objectives: the extent to which AI adoption enhances personalized guest experiences, the benefits of chatbots and virtual assistants, the influence of AI on revenue management, and its overall effect on guest satisfaction. A survey design was employed, involving 381 staff members from 20 hotels. Data were collected using structured questionnaires and analyzed using Chi-square statistical tests via SPSS software. Results revealed that AI adoption significantly improves operational efficiency and guest satisfaction, particularly through chatbots and virtual assistants. The findings address critical gaps in understanding AI’s impact on hospitality management in under-researched regions like Southwest Nigeria, offering insights into global applications of AI in hotel operations. Balancing AI integration with human interaction is highlighted as essential for achieving optimal guest experiences. Additionally, the study emphasizes the need to explore generative AI concepts in hospitality, identifying areas where their application is most and least effective