Asian Journal of Research in Computer Science
Not a member yet
792 research outputs found
Sort by
Skin Cancer Detection: A Review Using Machine Learning Techniques
No full textSkin cancer is a serious health concern, and early detection is crucial for effective treatment. Machine learning algorithms have shown promise in detecting skin cancer, but there is still much to be explored in terms of their effectiveness and efficiency. This paper presents a comparative analysis of different machine learning algorithms for skin cancer detection, including Support Vector Machines, VGG16, VGG19, Inception, Xception , and Convolutional Neural Networks. The study uses a dataset of 30,000 skin images, from which 21000 images are provided as training data and the rest 9000 are put in testing dataset. In the case of skin cancer detection, machine learning can be used to analyze images of skin lesions and identify those that are likely to be cancerous. This can help doctors to make more accurate diagnoses and provide earlier treatment. The results show that the neural network algorithm outperforms the other algorithms in terms of accuracy and speed. The CNN model came up with an accuracy of 74% being the highest from the rest of the five models performance. The study underscores the potential of machine learning in enhancing early detection capabilities, thereby aiding medical professionals in more accurate diagnoses and timely intervention for improved patient outcomes. Continued research in this domain is essential for refining algorithms, incorporating more extensive datasets, and advancing the integration of AI into clinical practices for enhanced cancer diagnostics
Hybrid Approach to Classification of DDoS Attacks on a Computer Network Infrastructure
No full textThe advancement in technology, its ease of use, and the competitive nature of its deployment in business operations have led to the wide spread of networking systems globally, and Ghana is not an exception. Most business operations and even personal activities are now conducted online leading to increased network connectivity, access to networked resources, and the corresponding cyber-attacks on these network systems. Distributed Denial-of-Service (DDoS) is one of the sophisticated attacks in the cyberspace. In DDOs, the attacker floods the network with massive and unsolicited traffic, causing the network infrastructure to exhaust all its resources in responding to the attacker’s request, thereby denying access to legitimate users of such resources. In this study, we designed and implemented a hybrid deep learning model (CRNN-Infusion) for detection and classification of DDoS attacks. Our model utilized the CNN, and RNN models, with the CICDDoS2019 dataset obtained from the Canadian Institute of Cybersecurity (CIC) for its training, with Random Search Hyperparameter Tuning (RSHT) and Feature Selection (FS) techniques for model efficiency and dimensionality reduction. Cybersecurity (CIC) for the model’s training, with Random Search Hyperparameter Tuning (RSHT) and FS techniques for model efficiency and dimensionality reduction. The results showed that, our proposed model is a better classifier for DDoS attacks compared to other deep learning (DL) models trained on the same dataset. With the highest accuracy of 98.92%, hybrid deep learning models are suitable for detecting and classifying DDoS attacks on network infrastructures. The findings point out that, with the appropriate choice of feature selection and hyperparameter tuning techniques, hybrid deep learning models perform optimally, with 98.92% accuracy, 99.02% precision, 98.92% recall, and 98.93% F1 score for our proposed model
Evolving Access Control Paradigms: A Comprehensive Multi-Dimensional Analysis of Security Risks and System Assurance in Cyber Engineering
No full textThis study evaluates the effectiveness of traditional access control paradigms—Role-Based Access Control (RBAC), Policy-Based Access Control (PBAC), and Attribute-Based Access Control (ABAC)—against ransomware threats in critical infrastructures and examines the potential benefits of integrating machine learning (ML) and artificial intelligence (AI) technologies. Utilizing a quantitative research design, the investigation collected data from 383 cybersecurity professionals across various sectors through a systematically structured questionnaire. The questionnaire, which demonstrated excellent internal consistency with a reliability score of 0.81, featured Likert scale questions aimed at assessing perceptions and experiences concerning the efficacy of different access control models in combating ransomware. Employing multiple regression analysis, the study explored the relationship between access control paradigms and their capability to mitigate ransomware risks, while also considering the impact of cybersecurity awareness among employees. The findings indicate that traditional access control methods are less effective against the dynamic nature of ransomware attacks, primarily due to their static configurations. In contrast, the integration of ML and AI into access control systems significantly enhances their adaptability and effectiveness in detecting and preventing ransomware incidents. Additionally, the study highlights the crucial role of cybersecurity awareness and training among employees in fortifying critical infrastructures against cyber threats. The adoption of a layered security strategy, incorporating advanced technological solutions and comprehensive cybersecurity practices, was found to markedly improve the resilience of critical infrastructures against ransomware attacks. Based on these insights, the study recommends the embrace of ML and AI technologies in access control systems, the prioritization of cybersecurity training for all organizational members, and the implementation of a multifaceted security approach to better defend against the evolving threat of ransomware. These strategies are essential for safeguarding the continuity and reliability of essential services in an increasingly digital and interconnected world
Leveraging AI for Enhanced Quality Assurance in Medical Device Manufacturing
No full textThe medical device sector adheres to strict regulatory frameworks, requiring precise adherence to quality assurance (QA) processes during the production process. Conventional quality assurance (QA) approaches, although successful, sometimes require substantial time and resource allocations, resulting in possible obstacles and higher expenses. The emergence of Artificial Intelligence (AI) in recent years has completely transformed quality assurance (QA) methods in different sectors, providing unparalleled prospects for improved productivity, precision, and scalability. This research examines the possibility of using AI technologies to enhance quality assurance processes in the manufacturing of medical devices. Manufacturers may improve product quality and streamline production workflows by utilising AI techniques like machine learning, computer vision, and natural language processing to automate and optimize important QA procedures. Artificial intelligence systems can analyse large amounts of data to find abnormalities, uncover flaws, and anticipate any problems in real-time. This allows for proactive intervention and reduces the chances of non-compliance hazards. In addition, AI-powered QA systems provide adaptive learning capabilities, constantly enhancing performance through feedback and adapting to changing regulatory needs. The incorporation of artificial intelligence (AI) into current quality management systems enables smooth and efficient sharing of data and compatibility, promoting a comprehensive approach to quality control throughout the whole production process
The Comprehensive Review: Internet Protocol (IP) Address a Primer for Digital Connectivity
No full textThe Internet Protocol (IP) is the rule book that governs how data is addressed and routed across networks on the internet. Think of it as the postal system for the digital world. This addressing system allows routers, the digital mail carriers, to efficiently transfer packets between devices and networks until they reach their destination. It ensures data reaches the right place by assigning addresses and enabling efficient routing. IP also encompasses various protocols and services, such as ICMP (Internet Control Message Protocol) for error reporting and diagnostics, and DHCP (Dynamic Host Configuration Protocol) for automatic IP address assignment. Additionally, IP can be configured to support different transmission modes, including uni-cast, multicast, and broadcast, catering to diverse communication requirements. Adopting technology that has been researched and developed commercially offers the military a cost-effective method of implementation. IP systems enable the forces to share a common network that supports voice, video, and data sharing. This systematic review article initially highlighted the basics on IP and lastly the brief discussion regards data gram format, NAT, IPv4, IPV6 IP fragmentation, CIDR, TCP and UDP individually
A Comparative Analysis of Traditional versus Agile Project Management Methodologies on IT Project Outcomes
No full textAgile project management approaches have gained popularity over the last two decades for managing IT projects. However, there remains an ongoing debate on which approach, agile or traditional plan-driven, yields more successful projects in terms of on-time and on-budget delivery, customer satisfaction, and team engagement. This study consolidates quantitative data from over 50 sources, encompassing over 1,250 IT projects implementing traditional waterfall or agile methodologies like Scrum and Kanban. The results show that agile approaches resulted in a 21% higher rate of project success compared to traditional methods. Projects using agile exhibited a 20% increase in customer satisfaction ratings as measured by Net Promoter Scores. Team members engaged in various agile projects reported higher motivation, empowerment, and better work-life balance compared to traditional projects. Statistical analysis found these differences were very unlikely to occur by chance the iterative nature of agile, its emphasis on continuous customer feedback, and autonomous team structure provide more flexibility to evolving IT projects. Traditional plan-driven methods remain effective for large, complex infrastructure projects requiring extensive pre-planning
Evaluating the Top Application Security Tools: From Static Analysis to Runtime Protection
No full textThis review article evaluates the effectiveness of application security tools, including static analysis techniques and runtime protection mechanisms, against the backdrop of the growing global cybersecurity market and evolving cyber threats. Through a comprehensive review, the study aims to assist developers, security professionals, and organizations in selecting the most effective tools to enhance application security. Employing a mix of theoretical analysis and empirical benchmarking, the paper analyzes static application security testing (SAST), dynamic application security testing (DAST), and runtime application self-protection (RASP) technologies. Findings indicate that while SAST tools are essential for early vulnerability detection, they may generate false positives and overlook runtime vulnerabilities. DAST tools, in contrast, effectively identify runtime issues but lack insight into internal application processes. RASP technologies offer real-time protection but face integration and performance challenges. The paper concludes with a recommendation for a layered security approach, combining SAST, DAST, and RASP tools to achieve comprehensive application security, thus contributing a novel perspective to the discourse on cybersecurity tool efficacy
Computing the Minimum Polynomial, the Function and the Drazin Inverse of a Matrix with Matlab
No full textAims/ Objectives: In this note we will discuss the known (but not well known) problem of finding the minimum polynomial and the function of a matrix providing the simplest proofs for undergraduate students. We will try to explain with fairly simple arguments how to compute the minimum polynomial of a matrix giving also the matlab code for its symbolic computation. Next we will describe the (symbolic) computation of the matrix of a function via the Hermite interpolation method which seems to be the simplest method for undergraduate students. Finally we shall see how we can compute the Drazin inverse given the nth power of a matrix A
A Systematic Performance Review of Security Methods for the Cyberworld
No full textGovernments and organisations globally increasingly recognise the importance of cybersecurity as a critical measure against cyber threats in our highly interconnected society. Establishing robust security measures has become paramount in safeguarding sensitive information and infrastructure. Biometric systems have emerged as critical components in various sectors, including industry, civilian applications, and rhetoric, to enhance security measures. This paper provides an overview of diverse security approaches in the cyber world and examines several research works, highlighting their strengths and weaknesses in implementation. We critically analyse existing methodologies and address potential shortcomings, aiming to improve the effectiveness of security measures. Additionally, we explore emerging trends and novel research directions in the field of biometric and rhetorical security. The study delves into contemporary biometric toolkits, examining their functionalities and applications across domains. Furthermore, we discuss digital ornamental models, evaluating their efficacy in enhancing cybersecurity measures. Through comparative analysis, we identify key differences and areas for improvement in existing security frameworks. In conclusion, this paper proposes a generic computer security model tailored to address the evolving challenges of cybersecurity. We highlight potential applications of this model in society, emphasising the importance of proactive measures to mitigate cyber threats effectively. Through comprehensive analysis and innovative approaches, we aim to contribute to advancing cybersecurity practices in contemporary society
Ballots and Padlocks: Building Digital Trust and Security in Democracy through Information Governance Strategies and Blockchain Technologies
No full textThis research explores the integration of Information Governance (IG) strategies and Blockchain Technologies (BT) in enhancing digital trust and security within democratic processes. Amid concerns about the integrity and vulnerability of electoral systems in the digital era, this study examines how these technologies can collectively safeguard democracy. Utilizing Partial Least Squares Structural Equation Modeling (PLS-SEM), bootstrapping analysis for mediation effects, and the Fornell-Larcker Criterion for discriminant validity, the analysis was conducted on data from 934 participants involved in the electoral process. Key findings demonstrate that IG strategies significantly impact digital trust, indicating the importance of robust data management, legal compliance, and privacy measures for public confidence in electoral systems. Blockchain Technologies positively affect the security of democratic processes due to their decentralized and immutable characteristics. Furthermore, digital trust is identified as a critical mediator between IG strategies, BT, and the security of democratic processes, highlighting the importance of trust in the effectiveness of these technologies. Based on the insights gained, three actionable recommendations are proposed: Electoral authorities should adopt comprehensive IG frameworks to enhance data integrity and transparency; Pilot blockchain projects should be expanded to refine and understand the broader implementation implications for election security; Efforts should be increased to foster digital literacy and trust among the electorate, emphasizing the role of these technologies in securing electoral integrity