https://ir.kdu.ac.lk/handle/345/9031 Wed, 08 Apr 2026 12:19:29 GMT 2026-04-08T12:19:29Z https://ir.kdu.ac.lk/handle/345/9083 Bridging the Career Readiness Gap: A Structured Review of Interventions for Information Technology Undergraduates in Developing Countries Sepalage, RY; Pradeep, RMM Information technology undergraduate education in developing countries encounters critical challenges in preparing students for professional employment, characterized by fragmented career preparation approaches, persistent skills gaps between academic curricula and industry requirements, and constrained access to realistic interview prac tice. This review aims to synthesize evidence regarding career readiness interventions, identify skill gaps impeding information technology (IT) graduate employment, and evaluate effectiveness of technology-mediated solutions for industry-academy bridging. Systematic searches across IEEE Explore, Elsevier/Science Direct, and supplementary databases yielded 54 initial records; following eligibility screening emphasizing IT undergraduate populations and empirical evidence, 14 studies were preserved for thematic synthesis. Analysis identified six primary themes: Ai-powered mock interview systems (21.4%) exhibiting 85-87% accuracy with 78% confidence enhancement; internship and work-integrated learning (21.4%) confirming 60% elevated employment probability and robust correlations with job readiness, skills gap investigations (14.3%) revealing 2-3 year curriculum delay, career guidance systems (14.3%) attaining 82-91% matching accuracy, employability assessment frameworks (14.3%) indicating soft skills as more reliable predictors than grades, and adaptive learning technologies (14.3%) producing 15-30% learning enhancements. Convergent evidence confirmed internship participation as the principal employability determinant, whereas Ai-driven interventions exhibited technological feasibility for scalable career preparation. Geographic concentration in developed contexts, absence of longitudinal impact assessment, and lack of integrated platform investigations constitute critical gaps. Findings establish evidence-based foundations for developing comprehensive career readiness ecosystems merging mock interviews, adaptive learning, career guidance, and work-integrated learning to address holistic preparation needs of IT undergraduates. Thu, 01 Jan 2026 00:00:00 GMT https://ir.kdu.ac.lk/handle/345/9083 2026-01-01T00:00:00Z https://ir.kdu.ac.lk/handle/345/9082 Agricultural Mobile Apps in Sri Lanka: A Systematic Review Senarath, SPIPK; Pradeep, RMM; De Silva, LDTT The increment of technology becomes very important for the smallholder farmers, helping them to improve the productivity and handle the challenges they face, but still in Sri Lanka, the use of technology tools is not applied, which leads the issues on existing digital platforms not adequately supporting paddy farmers and agricultural officers. Through this systematic review the aim is to examines the environment of mobile- and web-based agricultural solutions in Sri Lanka and assesses their functional coverage, evidence from Sri Lanka-specific documents including peer reviewed articles, theses, government publications, project reports, and official app or platform descriptions published between 2000 and 2025 was synthesized, while using international studies only for comparison but was not included in the core evidence set. By following the PRISMA 2020 guidelines, Searches were conducted across major academic databases using predefined queries, Sri Lankan government and international agency websites, and the Google Play and Apple app stores. Data were extracted based on several factors such as platform developers, target users, delivery channels, and functions. The review reveals a discrete ecosystem of government, private-sector, and hybrid platforms, each addressing only a subset of farmer needs. However, farm level data management, integrated resource requests, and structured two-way digital communication with agricultural officers are not in any single place. No comprehensive, integrated national-level platform was identified that supports the full spectrum of paddy farmers’ information and service requirements. These findings emphasize the need for coordinated digital agriculture strategies, interoperable system design, and supportive policy frameworks to move towards an integrated, farmer-centered platform ecosystem in Sri Lanka. Thu, 01 Jan 2026 00:00:00 GMT https://ir.kdu.ac.lk/handle/345/9082 2026-01-01T00:00:00Z https://ir.kdu.ac.lk/handle/345/9081 A Systematic Review of Deep Learning Approaches for Synthetic Media Detection in Biometric Authentication Systems Mahiti, MMRKB; Pradeep, RMM The recent advancements in synthetic media generation technologies have brought about various challenges in the reliability of facial biometric authentication systems in security sensitive areas. This systematic review explores current studies pertinent to deep learning-based solutions for analyzing compromised facial media, with special attention paid to their adaptability for use in biometric authentication systems. A structured analysis was applied to twenty-eight peer-reviewed studies published from 2020 to 2024, with special focus placed on solutions based on convolutional neural networks, transformer-based networks, and liveness detection methods for facial anti spoofing. Results show that transformer-based solutions demonstrate outstanding detection capability and resistance against intricate manipulation patterns, while convolutional neural network-based solutions possess lower computational complexity and adaptability for real-time authentication applications in biometric systems. Yet both demonstrate shortcomings in generalization capability across varied data sets and susceptibility to ever-advancing synthetic media generation technologies. Liveness detection is recognized as a supplementary mechanism for enhancing security for these systems despite increased complexity in implementation and infrastructure requirements. This systematic review draws attention to existing knowledge gaps in current studies for the development of more secure, efficient, and adaptable deep learning-based facial biometric authentication systems sensitive to novel threats from synthetic media generations. Thu, 01 Jan 2026 00:00:00 GMT https://ir.kdu.ac.lk/handle/345/9081 2026-01-01T00:00:00Z https://ir.kdu.ac.lk/handle/345/9080 The Brain of the Firewall: Enhancing Traditional Security Systems with Artificial Intelligence Yoganathan, A; Sabani, MJA Traditional firewall systems remain the building blocks of network security, but they are proving to be increasingly ineffective against dynamic and sophisticated types of cyberattacks. This weakness is caused by the fact that they use static rule based filtering processes which are pre-defined. This paper presents a concept of the brain of the firewall, which suggests a gradual incorporation of artificial intelligence (AI) into the already established firewall systems. It aims to transform these systems into active, self-learning, and versatile defence systems. The AI component, serving as the "brain" of the system, can monitor big amounts of traffic within the network to detect minor anomalies and predict possible attack by the time it happens, thus avoiding significant harm, before it can happen. This is a machine-learning-based solution which will use historical network information and known patterns of user behavior to identify suspicious behavior automatically and correctly. Such activities involve unauthorized access, data exfiltration, and covert malware communications, thus providing solutions to threats that go beyond the face of conventional firewalls. The system can also read the more intricate security alerts, correlate information among multiple sources, and take autonomous and informed decisions to isolate malicious traffic due to the intelligent combination of Natural Language Processing and detailed threat intelligence feeds. Most importantly, the system constantly evolves and tunes its defenses depending on past incidents, which improves its overall capabilities without human intervention. The brain of the firewall offers unmatched efficiency, a substantial reduction in false positive, and must-have real-time flexibility to emerging threats. Finally, this research shows an active paradigm shift in cybersecurity, which basically involves the integration of old methods of security with new intelligent automation to enhance organizational security. Thu, 01 Jan 2026 00:00:00 GMT https://ir.kdu.ac.lk/handle/345/9080 2026-01-01T00:00:00Z