Sri Lanka Institute of Information Technology

The poultry industry has become one of the fastest-growing agricultural sectors in Asia, driven by rising incomes, and shifting food preferences. Therefore, this study aims to examine the relationship between chicken meat production and key determinants, including chicken meat consumption, gross domestic product, and trade openness, over 30 years (1993-2022) across 28 Asian countries. This study's foundation was based on the theories of consumer demand and international trade. Wavelet coherence and Granger causality analysis were utilised to identify the direction of causality of the variables. The Wavelet results reveal that chicken consumption and GDP become most significant with the production in the Asian continent, while Granger results reveal that most Asian countries showed unidirectional causal flows from trade openness to chicken meat production and from chicken meat production to gross domestic product and consumption. Furthermore, this study provides novel insights that inform policy considerations for policymakers, international and domestic organisations, and governments, aligning with the Sustainable Development Goals established by the United Nations.

Purpose: The COVID-19 pandemic triggered a major shift in higher education, necessitating a move to fully online teaching and learning. While this transition was essential, it raised significant concerns about student engagement and the overall effectiveness of online education. Our research explores the elements that determine the success of remote learning from both student and educator perspectives. Design/methodology/approach: The study adopted a quantitative approach with a survey of 200 students and 50 faculty members in Sri Lanka, which serves as a representative sample for the South Asian higher education context. Findings: From the students' perspective, four factors were identified as critical determinants of online learning effectiveness: Students’ desire for physical class attendance, the efficacy of face-to-face lectures, the adaptation of higher educational institutions, and the ability of academic staff. And according to educators' perspectives, several factors significantly influence online teaching-learning effectiveness. Originality: No prior research has been done on the impact of online learning on students’ overall learning experiences and the extent to which online education can effectively support learning and assessment in higher education contexts Implications: The model developed in this study holds promise for evaluating online education effectiveness, especially in developing countries.

The COVID-19 pandemic - and the inconsistent government responses it revealed - has made the institutionalisation of robust Science Advice to Policymakers (SAP) an urgent imperative. Barring exceptions such as initiatives by the International Network for Governmental Science Advice, very few training programmes aim to develop capacity of policy makers, especially in the Global South. In response to these needs, the National Academy of Sciences of Sri Lanka and the Association of Academies and Societies of Sciences in Asia (AASSA), conducted a project titled Institutionalising Science Advice to Governments. Its key objectives was to develop an appropriate framework to understand the process of institutionalisation of SAP. The Colombo Framework so developed integrated four clusters: the SAP process; guiding values and principles; supporting institutional and legislative structures; and evaluating SAP. It was validated by experts and used for designing a questionnaire to assess current SAP practices across AASSA member countries which enabled data gathering on the diversity of models of SAP, their challenges and best practices. The framework also helped structure an international workshop to share country-level situation analyses, formulate roadmaps for implementation and build consensus on the relevance of institutionalising SAP. The latter culminated in the Colombo Declaration, urging governments to strengthen science-policy engagements. Short-term and long-term feedback from participants indicated high utility of the framework for understanding and operationalising SAP in diverse contexts. The framework offers a systematic approach for countries, especially in the Asia-Pacific region, to institutionalise SAP and for scientists to gain in-depth understanding of the process.

Abstract. This research aims to develop and apply a structured technology selection framework for initial data acquisition for Heritage Building Information Modeling (HBIM) and Digital Twin creation in Sri Lankan heritage sites. The study addresses the challenge of selecting appropriate 3D documentation technologies by proposing a transparent and systematic decision-making process. The study employs an Analytic Hierarchy Process (AHP) as its foundational framework. An AHP model was developed, defining a set of criteria (Cost, Geometric Accuracy, Texture Quality, Ground and Aerial Accessibility, Scale) and alternatives (various terrestrial and drone-based scanning and photogrammetry technologies). The framework’s effectiveness was validated through a detailed case study of Lankathilake Pilimage, followed by hypothetical applications for four other representative heritage sites. The AHP model successfully provided a ranked list of technology alternatives. For the Lankathilake Pilimage case study, the AHP results prioritized Drone Photogrammetry as the most suitable method, followed by Terrestrial Photogrammetry and then a combined Drone Lidar and Drone Photogrammetry approach. The application of the framework to other sites demonstrated how project- specific requirements, translated through pairwise comparisons, lead to different optimal technology choices. The AHP framework provides a robust and repeatable methodology for selecting primary data acquisition technology. It effectively incorporates multiple, often conflicting, criteria to arrive at a data-driven decision. This framework is a valuable tool for heritage conservation professionals and researchers, offering a clear path forward for HBIM and Digital Twin projects in Sri Lanka.

This research examines the impact of video game addiction on aggressive behaviour of tertiary students in Sri Lanka. Video game addiction, with its potential adverse impacts has raised concerns among the public, especially regarding its link to aggressive behaviour. Data was gathered from a sample of 382 undergraduates of local non-state universities selected employing cluster sampling technique to examine the correlation between video game addiction and aggression. The survey was conducted to collect data on video game addiction and aggression. Research findings reveal how gaming addiction leads to aggressive behaviour in addicted gamers indicating a strong positive relationship between video game addiction and aggressive behaviour. Therefore, researchers recommend balanced time management practices between game usage and other daily essential activities and promoting awareness about negative behavioural implication of game addiction. It is expected that this study provides insights to stakeholders including teachers, parents, and administrators to better understand the effects of video game addiction, and mitigation strategies to minimise the negative impact on students’ behaviour.

Learning disabilities, particularly Dyscalculia and Dysgraphia, significantly hinder students' academic, social, and future occupational outcomes. Deaf and mute primary students face amplified challenges due to limited availability of specialized educational resources and tools that cater to their unique communication needs. This research presents an innovative, intelligent learning environment designed specifically to identify and mitigate Dyscalculia and Dysgraphia among deaf and mute primary students. Leveraging advanced artificial intelligence, computer vision, and machine learning (ML) technologies, the developed system incorporates Sinhala Sign Language (SLSL) and interactive, adaptive learning methodologies. The identification process employs Convolutional Neural Networks (CNNs) to analyze handwritten numerical inputs and sign language gestures, categorizing students based on the severity of their conditions. Subsequently, personalized, engaging instructional activities facilitate gradual skill development and continuous improvement. Robust data privacy measures ensure ethical standards, while automated tracking provides actionable insights for educators and parents. Initial findings indicate significant improvements in student performance and engagement, demonstrating the system's efficacy in delivering inclusive, culturally relevant, and accessible educational interventions tailored for deaf and mute students.

This paper presents a predictive maintenance system for commercial blast freezers using custom IoT sensors and deep learning. The system employs ESP32-based data collection devices to monitor three-phase current, multi-axis vibration (X, Y, Z), and thermal data from blast freezer compressors over five months. Custom hardware was designed with weatherproof enclosures for industrial deployment. Data preprocessing included temporal synchronization, normalization, and balanced dataset preparation. Long Short-Term Memory (LSTM) neural networks were implemented to predict equipment health by learning from time-series sensor patterns. The LSTM models achieved exceptional accuracy, with 99% for current prediction, 98.9% for temperature, and 98.5% for vibration monitoring. Comparative evaluation against Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Temporal Convolutional Networks (TCN) confirmed LSTM's superior performance in handling sequential data and temporal dependencies. The system includes a real-time web dashboard for equipment monitoring and predictive alerts, enabling proactive maintenance decisions and reducing unplanned downtime.

This paper presents SmartSphere, an intelligent, secure, and wire-free home automation system that synergizes artificial intelligence, multi-factor access control, and resonant wireless power transmission. Built on an edge-computing architecture using ESP32 and Arduino Mega 2560 microcontrollers, SmartSphere integrates facial recognition, fingerprint authentication (96.7% accuracy), and IR-based presence detection to reduce false activations by 75%. The system employs OpenCV and TensorFlow Lite for real-time anomaly detection and environmental personalization, including weather-responsive adjustments and emotion-aware lighting via facial expression analysis. A key innovation is the incorporation of a Tesla coil-based wireless power transmission module, which eliminates conventional wiring constraints and reduces installation cabling by 86%. Experimental validation demonstrates a 14% improvement in energy efficiency, 75% faster response time (0.3 s), and seamless compatibility with 92% of tested IoT devices. Through comprehensive testing and validation, this research establishes SmartSphere as a secure, intelligent, and sustainable solution for next-generation smart homes, addressing the limitations of traditional wired systems while enhancing the user experience through AI-driven personalization.