NSPACE

Welcome to NSBM Green University e-Repository!

One Platform for NSBM Publications

Photo by @inspiredimages

Communities in DSpace

Select a community to browse its collections.

Now showing 1 - 5 of 5

Recent Submissions

NeuroLens: A Cognitive-aware Assistive Navigation Framework for the Visually Impaired using EEG and 3D Spatial Perception
(NSBM Green University, 2025-11-12) Weerabahu, W.M.A.J.; Wijesinghe, D.
Globally, over 250 million people live with moderate to severe visual impairments, facing significant barriers to safe and independent navigation. While assistive tools such as canes, guide dogs, and smartphone-based apps exist, these solutions often require physical interaction, lack environmental awareness, and fail to adapt to user intent or cognitive state. This conceptual research proposes a high-level architecture for "NeuroLens," a brain-computer interface (BCI)-driven navigation framework that integrates noninvasive EEG signals with real-time 3D spatial perception using depth cameras. The goal is to enhance hands-free mobility for visually impaired users by inferring navigation intent and delivering contextual feedback via audio and haptic channels. Unlike existing AR or BCI-based tools, NeuroLens introduces a dual-input decision mechanism and continuous real-time deviation monitoring through an FSM controller. Although no prototype has been implemented, the system design is grounded in prior literature and optimized for mobile platforms. Future work will focus on prototype development, performance benchmarking, and real-world usability evaluation to validate the framework’s feasibility and effectiveness.
Environmental Hazards Prediction using Real-Time IoT Sensor Data and Edge-Deployed Machine Learning for Smart Residential Contexts
(NSBM Green University, 2025-11-12) Wickramage, T.; Sewmini, N.
The rapid urbanization and increasing environmental concerns necessitate innovative solutions for smart home security that extend beyond traditional humancentric threats. This paper presents an Internet of things (IoT) based smart home security system designed to monitor and mitigate environmental hazards such as gas leaks, extreme temperatures, humidity fluctuations, and fire risks. The system integrates multiple sensors (gas, temperature, humidity, motion) and a pan-tilt camera module connected to a Firebase cloud backend for real-time data processing and storage. A dedicated mobile application enables users to access live sensor readings, camera feeds, historical data visualization, and instant hazard alerts. Machine learning algorithms implemented through Random Forest and Isolation Forest models analyze sensor patterns to detect anomalies and predict hazardous conditions. Experimental evaluation over a 30-day period across 15 households achieved 91.2% hazard classification accuracy, 98.7% data transmission reliability, and an average response latency of 320 miliseconds, while reducing cloud data load by 62% through edge inference. The system demonstrates robust real-time monitoring, early hazard prediction, and user satisfaction ratings averaging 4.3/5 for usability. This research contributes to advancing smart home technologies by addressing critical environmental security gaps through an integrated, data-driven, and edge-enabled IoT framework.
Real-Time Human Motion Capture and Animation in Blender 3D Models using AI-based Pose Estimation
(NSBM Green University, 2025-11-12) Sathsarani, D.S.
Traditional human motion capture systems often require expensive hardware and complex setups, limiting accessibility and lacking the ability to animate human models in real-time without additional equipment. Animating characters in real-time with accurate motion demands seamless integration between pose recognition and animation systems. This paper presents a real-time human motion capture and animation system using AI-based pose estimation. Leveraging Media Pipe Pose Landmark detection, the proposed system identifies 33 body landmarks from a mobile app built in Java and Kotlin. The app calculates various poses using the detected landmarks and sends them to a Firebase Realtime Database. A Python addon in Blender retrieves the pose data in real-time, adjusting the 3D model’s bones and rotations based on the detected poses, enabling live character animation. The integration of Firebase for real-time synchronization and Blender’s armature system offers a cost effective and flexible approach to motion capture. This solution eliminates the need for expensive hardware, providing a portable method for high-quality animation creation. Significant potential for applications in gaming, virtual reality, and animation studios. Experimental evaluation demonstrated an average pose estimation accuracy of 80% and a real-time latency of approximately 120 ms, confirming the system’s efficiency for smooth motion transfer. While the current implementation is optimized for single-user motion tracking, future work will focus on multi person tracking and integration with advanced 3D environments for improved realism.
Modern Era Mythmaking: AI, Conspiracies and The Digital Age
(NSBM Green University, 2025-11-12) Wijesinghe, W.M.C.S.; Wijesinghe, D.
As society becomes increasingly interconnected and algorithmically mediated, myth-making has not diminished but evolved. In this digital age, generative artificial intelligence (AI) plays a pivotal role in amplifying misinformation and conspiracies, contributing to the construction of persuasive modern myths. This paper explores how AI technologies facilitate the creation and dissemination of misinformation, examining psychological factors, algorithmic influence, and the socio-technical systems that enable belief formation. Employing a qualitative methodology with empirical support from two case studies—Meta's Galactica model and GPT-2's news article generation experiments—the paper identifies critical vulnerabilities in public perception and trust in digital information. Drawing on updated literature and theoretical frameworks, we propose a multi-level strategy encompassing digital literacy, regulatory interventions, and machine-learning based detection tools to mitigate the risks posed by AI-driven myth-making. The findings offer vital insights for policymakers, technologists, and educators aiming to safeguard truth in an increasingly AI-mediated society.
Bridging Nutrition Gaps in Urban Workforces: Evaluation of an AI-Enhanced Meal Subscription System for Corporate Employees in Colombo
(NSBM Green University, 2025-11-12) Senarathna, R.G.I.S.; Nayanamini, K.L.D.; Premalal, K.G.K.P.
The rapid urbanization of developing economies has fundamentally altered dietary patterns among corporate workforces, with non-communicable diseases accounting for 83% of premature deaths in Sri Lanka. This paper presents a comprehensive evaluation of user acceptance and prototype validation for an AI-enhanced meal subscription system targeting corporate professionals in Colombo. Through a mixed-methods approach combining user surveys (n=100) and prototype testing using Figma-based mockups, we investigated the effectiveness and acceptance of technology-enhanced nutritional interventions. Our findings reveal that 86.7% of corporate employees struggle with maintaining healthy diets, while 90% express interest in personalized meal delivery services. The prototype validation demonstrates high acceptance rates for key features including AI driven personalization (88%), subscription management (85%), and nutrition tracking (74%). Pricing analysis reveals optimal acceptance for three-tier subscription models: Week Saver Plan (1 week, LKR 2,900, 78% acceptance), Fortnight Feast (2 weeks, LKR 5,500, 64% acceptance), and Monthly Munch (1 month, LKR 10,500, 54% acceptance). The study contributes practical insights for developing culturally appropriate, technology-enabled nutrition solutions in developing economies, with AI recommendations identified as a critical enhancement for optimizing user experience and health outcomes.