Browsing by Author "Jayawardena, A"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemEmbargo
    Advancing Speech Therapy for Sinhala-Speaking Children with Autism Spectrum Disorder Through an Intelligent Dialog System
    (Institute of Electrical and Electronics Engineers Inc., 2025) Jayawardena, A; Pulasinghe, K; Rajapakshe, S
    This paper presents a dialog system integrated with a NAO socially assistive robot, designed to support Sinhala-speaking children with Autism Spectrum Disorder (ASD). The system leverages a pipeline-based architecture implemented using the RASA framework, consisting of Natural Language Understanding (NLU), Dialog Management (DMU), and Natural Language Generation (NLG) units. The NLU unit processes user input by identifying intents, entities, and dialogue acts, incorporating custom tools like the SpokenSinhalaVerbTokenizer for handling spoken Sinhala. The DMU includes a Dialog State Tracker (DST) to maintain conversation context and a Dialog Policy Generator, which employs rule-based, TED, and UnexpecTED policies to adapt conversation flows dynamically. The NLG unit generates natural responses to foster interactive and goal-oriented conversations. Integrated with the NAO robot, the system engages children through meaningful dialogues, such as discussing toy preferences, aiming to enhance social interaction and communication skills. This work highlights the potential of conversational AI and robotics in therapeutic interventions for ASD in low-resource languages.
  • Thumbnail Image
    PublicationEmbargo
    Rubber Buddy: A Mobile Application to Empower Rubber Planters of Sri Lanka
    (IEEE, 2022-12-09) Jayawardena, A; Ganegoda, K; Imbulana, S; Gunapala, G; Kodagoda, N; Jayasinghe, T
    This research was conducted to develop a mobile application that provides expert solutions for the common problems faced by rubber planters in Sri Lanka. The application developed consists of four components, namely, identification of pests in immature rubber plantations and rubber nurseries; leaf disease identification; cover crop identification; and weed identification. Images taken using the mobile phone cameras are recognized using machine learning models developed using several convolutional neural network (CNN) architectures such as mobile net version 2 (MobileNet v2), VGG 16, VGG19, and residual networks (ResNet). After the images were recognized, the application will provide expert solutions and management strategies to the rubber planters. As most of the rubber plantations are located in areas with low network coverage, the application was designed to be operated in offline mode using TensorFlow lite technology.