Faculty of Computing-Scopus

Permanent URI for this collectionhttps://rda.sliit.lk/handle/123456789/4892

Browse

Filters

20252

Advanced Search

Filter by

Settings

Author: search.filters.author.Weerathunga, I

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemEmbargo
    Genetic Algorithm-Based Unmanned Aerial Vehicle (UAV) Path Planning in Dynamic Environments for Disaster Management
    (Institute of Electrical and Electronics Engineers Inc., 2025) Wijerathne V.R; Theekshana W.G.P; Prabhanga K.G.B.; De Silva K.P.C; Wijayasekara, S; Weerathunga, I; Hansika, M. M.D.J.T
    Unmanned Aerial Vehicles (UAVs) hold immense potential in disaster management by enabling rapid response, real-time aerial reconnaissance, and improved situational awareness without endangering human lives. This research proposes a real-time UAV path-planning system based on a Hierarchical Recursive Multiagent Genetic Algorithm (HR-MAGA). Unlike traditional methods that struggle with adaptability in dynamic 3D environments, our system employs localized waypoint updates to reduce the computational cost of full-path recalculations. A multi-objective fitness function guides the optimization process by balancing safety, energy efficiency, altitude smoothness, turbulence resistance, and travel time. Additionally, the system integrates a decoupled real-time collision avoidance module for immediate response to sudden threats. While obstacle detection is abstracted in this study, the framework is designed to be easily integrated with real-time sensing technologies such as LiDAR for dynamic obstacle awareness. Experimental evaluations show a 20-30% improvement in path efficiency and a 40% increase in convergence speed compared to conventional genetic algorithms, highlighting the system's adaptability and robustness in disaster response scenarios.
  • Thumbnail Image
    ItemEmbargo
    "articulearn": An Integrative, AI-Driven Speech Therapy System for Children With Speech Disorders
    (Institute of Electrical and Electronics Engineers Inc., 2025) Ranasinghe, K; Zoysa, S.P.D; Annasiwatta, S; Fernando, P; Thelijjagoda, S; Weerathunga, I
    "ArticuLearn", a personalized speech therapy system for children with speech sound disorders that integrates advanced machine learning techniques and interactive digital tools to provide targeted intervention across four key domains: phonological disorder detection, fluency disorder identification and intervention, therapy for childhood apraxia of speech, and personalized speech activity filtering for articulation disorders. By leveraging dedicated LSTM-based classifiers and feature extraction techniques such as Mel-frequency cepstral coefficients (MFCCs), this approach automatically identifies specific error types, including phoneme substitutions, omissions, and vowel mispronunciations. In addition, a hierarchical deep learning framework employing attention mechanisms and dynamic time warping is applied to quantify motor planning deficits associated with childhood apraxia of speech, while a reinforcement learning agent adapts therapy prompts based on individual performance. Data were collected from eight children per disorder category along with a normative sample of twenty typically developing children, providing a basis for personalized intervention and progress monitoring. ArticuLearn is designed to complement traditional therapy methods by offering an accessible, scalable solution that supports remote intervention and enhances clinical decision-making. Pilot evaluations suggest that the system can facilitate targeted speech exercises, improve self-monitoring, and foster adaptive learning in young users. This research underscores the potential of combining AI-driven analysis with interactive therapy to transform speech rehabilitation, particularly in resource-limited settings where access to specialized care is challenging.