Asian Journal of Research in Computer Science
Not a member yet
792 research outputs found
Sort by
Evaluating UI/UX Design and Applicant Behaviour in Jahangirnagar University\u27s Undergraduate Admission Process
No full textA user-friendly interface plays a critical role in information systems, as it directly influences users’ ability to perform tasks accurately and efficiently. In the context of digital university admissions, effective UI/UX design and evaluation are essential for ensuring accessibility, usability, and student autonomy. This study investigates the Jahangirnagar University undergraduate admission portal to understand why a significant proportion (65.3%) of digitally literate students rely on third-party assistance to complete applications, despite the system achieving a positive mean usability satisfaction score of 4.31/5. The primary reason identified was student apprehension about making mistakes. Utilising a multi-method approach—Likert-scale surveys, heuristic evaluations, and Jaccard similarity analysis—we assessed interface quality and user behaviour across a dataset of 308,606 applications. Analysis of 10,120 reported issues revealed the most frequent problems: payment failures (32.34%), image/signature upload difficulties (13.25%), and language selection challenges (14.74%). These findings highlight critical friction points undermining user confidence and independence. Our goal is to contribute to the improvement of the user interface design methodology of a student-friendly platform so that any student can complete the application process without anyone’s assistance
Optimized DenseNet Architecture for Efficient Classification of Encrypted Internet Traffic
No full textThe increasing reliance on Internet-based services has rendered secure and efficient network traffic classification critical. Conventional methods for categorising traffic, such as port and payload methods, often struggle with the challenges posed by encrypted traffic. Deep learning techniques have emerged as a predominant method for traffic classification given their success in domains such as image recognition, document analysis, and genomics. This research proposes an enhanced DenseNet architecture that leverages deep learning to accurately classify encrypted Internet traffic categories. This approach introduces a compression layer into the DenseNet architecture to address the co-adaptation problem as a result of the information flow and optimise the accuracy of the CNN. An Intrusion detection dataset from the Canadian Institute of Cybersecurity was used to evaluate the architecture. The optimised DenseNet architecture was evaluated using metrics such as precision, recall, accuracy, F1-Score, False Positive Rate and Area under the ROC Curve. Experimental results show that the approach can distinguish various encrypted Internet traffic categories
Enhancing Network Performance: A Comprehensive Analysis of Hybrid Routing Algorithms
No full textRecent years have seen the proposal of numerous routing algorithms for potential use in a variety of application areas. In many network types, such as Wireless Sensor Networks (WSNs), Mobile Ad Hoc Networks (MANETs), and other dynamic contexts, routing is a crucial difficulty. By fusing the benefits of proactive (table-driven) and reactive (on-demand) routing techniques, hybrid routing algorithms have become a notable breakthrough.
Researchers have focused on hybrid routing algorithms since traditional ones frequently fail to adjust to the changing network conditions present in MANETs. These novel methods strive to maximize speed while reducing overhead by combining the best features of proactive and reactive routing strategies. It provided a thorough analysis of these algorithms in this work, emphasizing their mechanisms, benefits, limitations, and security features. Also focused especially on the analysis of hybrid routing algorithms in a range of applications
A Review of Graph Traversal Algorithms: Techniques and Applications in Network Analysis
No full textThis review identifies graph traversal methods as fundamental steps in network analysis that facilitate easy examination of relations within the network. In this review, we plan to discuss multiple graph traversal approaches like depth first search (DFS), breadth first search (BFS), their varieties and indicate how these techniques can be used in practice when analyzing networks. The following is a review methodology covering 10 articles for years 2019 – 2024. The study responds to the question of how to select algorithms for various types of networks with reference to their computational cost and speed. Thus, the authors describe the advantages and drawbacks of the reported techniques, and the topics serve as recommendations for the further advancement of technology. In this respect, the present review also serves to help to close the divide between theory and practice
The Synergistic Role of Machine Learning, Deep Learning, and Reinforcement Learning in Strengthening Cyber Security Measures for Crypto Currency Platforms
No full textThis study explores the role of artificial intelligence (AI)-driven cybersecurity models in mitigating fraud, smart contract vulnerabilities, and regulatory challenges in cryptocurrency platforms. Utilizing datasets such as the Elliptic Bitcoin Dataset, SolidiFI-Benchmark, CryptoScamDB, and CipherTrace AML Reports, this research employs Logistic Regression, Random Forest, and Reinforcement Learning (RL) for fraud detection and anomaly identification. The AI-based security model demonstrates a 5.2% increase in fraud detection accuracy over traditional rule-based methods while reducing false positives by 19.3%. However, the model exhibits a false negative rate of 98.9%, indicating challenges in fully capturing sophisticated fraud techniques. Regression analysis shows a strong inverse correlation (R² = 0.927) between AI adoption and fraud cases, where each 1% increase in AI adoption corresponds to a reduction of approximately 37 fraud cases.In real-world applicability, the proposed AI-driven models enhance scalability and real-time threat detection but require substantial computational resources, particularly for deep learning and RL-based techniques. Computational efficiency is optimized through federated learning and quantum-resistant AI security, ensuring robust yet privacy-preserving fraud detection. Despite its advantages, challenges such as adversarial AI attacks, regulatory inconsistencies, and scalability under high transaction loads persist.The study recommends self-supervised learning for fraud detection, improving interpretability in deep learning models, and developing AI-driven compliance frameworks to address ethical concerns. By integrating Machine Learning (ML), Deep Learning (DL), and Reinforcement Learning (RL), this study provides a novel approach to securing cryptocurrency transactions, offering actionable insights for researchers, financial institutions, and policymakers
Artificial Intelligence in E-commerce and Digital Marketing: A Systematic Review of Opportunities, Challenges, and Ethical Implications
No full textThe transformative power of AI has only just begun to redefine how businesses function and relate to their customers within e-commerce and digital marketing. In fact, AI really does help firms adjust to changes in consumer preference and market fluctuations by improving operational efficiencies. Big data analytics, aided by artificial intelligence, really boosts the understanding of the customer journey-hence, optimizing and finally allowing for tailor-made marketing campaigns in real time. This leads to great growth for the business. The COVID-19 pandemic pushed companies into adopting AI-driven solutions in the quest for their resilience; this consequently led to an increase in the need for effective digital marketing strategies. E-commerce activities are integrated with artificial intelligence in order to better understand consumer behavior, support market dynamics forecasting, and enhance risk management strategies. Hence, it becomes an indispensable aspect. It is relevant that ethical frameworks and further research address the problems of data privacy and scalability in order to optimize the intrinsic potential of AI. A focus on innovative applications of AI, alongside interdisciplinary collaboration, can empower an organization to develop genuinely inclusive and effective marketing strategies. Embracing the AI-driven initiatives, this will result in long-term relationship building with the customer for growth in a sustainable manner and maintaining competitiveness at an exponential pace in changing digitization
Smart Infrastructure Systems: A Review of IoT-Enabled Monitoring and Automation in Civil and Agricultural Engineering
No full textThe Internet of Things (IoT) significantly influences the advancement of smart infrastructure systems in civil and agricultural engineering. IoT technologies have reshaped the management of urban infrastructure and agricultural operations through real-time monitoring, predictive maintenance, and automated control. In civil engineering, IoT sensors help monitor structural integrity, environmental conditions, and urban utilities, enhancing safety and efficiency in areas like traffic and waste management. IoT enhances agriculture through precision farming methods, including automatic irrigation, monitoring of crop and soil health, and resource optimization, leading to sustainable practices and increasing yields. This study analyzes IoT applications in rural and remote areas, focusing on the integration and challenges of IoT deployment. This also employs a case study approach to analyze IoT applications, highlighting key technological, economic, and policy challenges in remote and rural regions where connectivity and integration are critical. The findings suggest that IoT-driven infrastructure improves efficiency, sustainability, and resilience, but require more comprehensive analysis and integration in remote and rural areas. Future possibilities for IoT are discussed, focusing on advancements in edge computing, the use of renewable energy, and the development of smart rural infrastructure that meets both urban and agricultural needs. The paper urges for ongoing research and supportive policies that optimize the potential of IoT-integrated infrastructure systems, which are expected to improve efficiency, sustainability, and resilience in both sectors
Ant Colony Optimization (ACO) for Traveling Salesman Problem: A Review
No full textThe traveling salesman problem (TSP) is a fundamental combinatorial optimization problem with applications in resource management, logistics, and communications. In order to address TSP and its differences, this paper discusses developments in Ant Colony Optimization (ACO), a biologically inspired algorithm. Inspired by the foraging activity of ants, ACO\u27s decentralized and recursive methodology has proven successful in solving difficult routing problems. ACO\u27s scalability, convergence speed, and solution quality have been greatly enhanced over time through innovations including hybridization with algorithms such as Firefly, genetic algorithms, parallel computing frameworks, and adaptation mechanisms. These developments have given the ACO the flexibility and efficiency to handle dynamic situations, such as real-time vehicle guidance and underwater navigation. Despite its progress, issues remain such as scalability in resource-limited contexts, processing overhead, and reliance on parameter modification. This work summarizes current developments in ACO, noting how revolutionary the TSP solution is, pointing out its drawbacks, and suggesting areas for further study. Leveraging emerging technologies like machine learning and quantum computing, ACO has huge potential to progressively address challenging real-world problems. This review provides a comprehensive framework for developing uses of ACOs and reaffirms their status as a key component of improvement research
Reliability of the Type System in TypeScript in Software Development
No full textThe article examines the TypeScript type system as a critical element influencing its use in software development. The primary objective of the study is to analyze the characteristics of the type system and identify methods for improving the accuracy of type checking. The article explores the principles underlying the type system, its vulnerabilities such as the use of the any type, type assertions, issues with object and array indexing, and proposes approaches to enhancing system reliability.
The methodology includes an analysis of TypeScript\u27s structure, the principles of its compiler, and the application of tools for static code analysis. The study references academic articles available in open-access online repositories, providing a broad perspective on the topic. Additionally, examples of code presented in the work illustrate key concepts and methods for working with type systems. Results demonstrate that configuring the compiler, avoiding the any type, and leveraging libraries for data validation improve the quality of type safety.
The findings, based on the analysis of relevant sources, will be useful for programmers and corporate professionals. This review paper is a guide for software developers to understand the essence and the reliability of the Type System in TypeScript. This is a requirement to the scientific community as it guides software developers with the understanding and methods for efficiency in Type Checking. Principles, vulnerabilities and practice in code analysis are explicitly enumerated
Performance Analysis of 4G Technology Across Mobile Network Operators in Nigeria Using Evolve Radio Access Bearer Channel Drop Rate
No full textThis study aims to evaluate the performance and reliability of 4G technology across mobile network operators in Nigeria by analyzing the Evolved Radio Access Bearer (ERAB) channel drop rate. Covering a 36-month period from January 2021 to December 2023, the research seeks to provide insights into how well these networks meet the Nigerian Communications Commission (NCC) benchmark of 2% for drop rates, thereby reflecting their capacity to deliver quality service. Data obtained from the NCC were analyzed using graphical and statistical methods to identify trends, strengths, and areas for improvement. Results reveal that all networks consistently maintained ERAB drop rates within the NCC threshold, demonstrating compliance with regulatory standards. MTN consistently emerged as the top performer, followed by Airtel, while 9mobile and Globacom showed relatively higher, but still compliant, drop rates. This study underscores the importance of network optimization and offers actionable recommendations for further enhancing reliability and user experience in Nigeria\u27s mobile networks