Browsing by Author "Wijesinghe, H"

Now showing 1 - 3 of 3

Embargo
EyeVista: An assistive wearable device for visually impaired sprint athletes
(IEEE, 2016-12-16) Peiris, H; Kulasekara, C; Wijesinghe, H; Kothalawala, B; Walgampaya, N; Kasthurirathna, D
On-going progressions of Information Technology increase the scope for computer vision-based interventions to facilitate efficient and promising technology for people with disabilities. This project aims to develop a wearable navigational assistive device, titled EyeVista, to facilitate visually impaired sprint athletes. It is a lightweight, easy-to-use, customizable and low-cost wearable jacket built-in with off-the-shelf based on computer vision techniques. Synthesis of research initially reflects the impact of the main barriers of a human guide and how to break down such barriers. In doing so, we hope to introduce an alternative to the current practice of having a human guide for blind athletes, overcoming the shortcomings of it. The designed system uses Raspberry Pi single board computer to process the real-time image captured by Raspberry Pi camera module to navigate the athletes within the assigned track and to avoid collisions. As a result, we believe the project EyeVista will empower the visually impaired sprint athletes to enhance their performance by easing their mobility by allowing the user to move within their relevant track lanes and avoid collisions without the support of a human guide and enhance the independence, safety along with the quality of life.
Embargo
Multimodal Knowledge Graph for Domain-Specific Intelligence
(Institute of Electrical and Electronics Engineers Inc., 2025) Mohan, K; Munasinghe, M; Bandara, L; Wijesinghe, H; Rathnayake, S; Abeywardhana, L
In the era of information abundance, transforming vast amounts of data into meaningful knowledge remains a critical challenge, especially in domains like medicine, engineering, and education, where visual and multimodal elements play a vital role. Traditional Knowledge Graphs (KGs) excel in organizing structured and textual data but struggle to incorporate multimodal information and implicit relationships, limiting their effectiveness. This paper explores the potential of Multimodal Knowledge Graphs (MMKGs) to address these limitations by integrating text, images, videos, and audio into a unified framework. We investigate how MMKGs enhance knowledge retrieval, comprehension, and interactive learning through advanced techniques, including Natural Language Processing and deep learning. Our findings demonstrate that MMKGs significantly improve knowledge retention and application in specialized fields, offering a foundation for more intuitive and effective domain-specific knowledge ecosystems.
Embargo
Post-Quantum Cryptography for Web Authentication Protocols: A Systematic Review of OAuth 2.0, OpenID Connect, and SAML Migration
(Institute of Electrical and Electronics Engineers Inc., 2026-03-19) Dissanayake, R; Wijesinghe, H; Vindinu, J; Jayasinghe, K; Abeywardena, K; Senarathne, A
OAuth 2.0, OpenID Connect (OIDC), and SAML rely on classical public-key primitives such as RSA and ECDSA, which are vulnerable to quantum attacks via Shor's algorithm. This systematic review examines migration of these protocols to Post-Quantum Cryptography (PQC) following the 2024 NIST standardization of ML-DSA and ML-KEM. We map cryptographic dependencies across all three protocols, evaluate NIST-standardized algorithms for authentication use cases, and analyze practical migration challenges. Token size explosion, with ML-DSA-65 signatures approximately 52 times larger than ECDSA P-256, represents the dominant implementation barrier, compounded by incomplete JOSE standardization and limited ecosystem maturity. Missing formal security proofs and federation migration frameworks are identified as critical priorities before production deployment.