Research Papers - Dept of Information Technology

Permanent URI for this collectionhttps://rda.sliit.lk/handle/123456789/593

Browse

Filters

2019 - 201912020 - 20224

Advanced Search

Filter by

Settings

Author: search.filters.author.Abeywardhana, LHas files: Yes

Search Results

Now showing 1 - 5 of 5
  • Thumbnail Image
    PublicationEmbargo
    Automated vehicle insurance claims processing using computer vision, natural language processing
    (IEEE, 2022-11-30) Fernando, N; Kumarage, A; Thiyaganathan, V; Hillary, R; Abeywardhana, L
    Traditional insurance claims processing systems are no match for the modern world due to the increasing population of vehicles and the resulting number of accidents. In this paper, the authors present a novel idea to automate the tedious processes in the insurance industry. The presented system consists of three main components namely, re-identify the make and model of the vehicle, identify the damaged automobile component, type, and severity, and compute an accurate repair estimate using damage component identification. Also, automate the documentation process by identifying the relevant fields in the voice input provided by the user. This ensures both the parties involved in this process will be benefited from the proposed system. Presented solutions Were designed using the aid of Artificial Intelligence techniques, mainly CNN models and Natural language processing techniques.
  • Thumbnail Image
    PublicationEmbargo
    Hastha: Online Learning Platform for Hearing Impaired
    (IEEE, 2022-11-30) Wanasinghe, D; Maddugoda, C; Ramawickrama, H; Munasinghe, T; Abeywardhana, L; Mallawarachchi, Y
    Sign language is the primary means of communication for the hearing-impaired community. Introducing a learning platform can result in many ways to make learning more accessible for the hearing-impaired community of Sri Lanka. Although many approaches are being made to build such systems, the learning platform “Hastha” aims to provide a more interactive outcome with a component that converts Youlhbe videos to sign language and a Chatbot component that acts as an intermediary between a hearing-impaired user and a Google Search Engine. Furthermore, it includes a game-based learning platform and a gesture translation component from Sri Lankan to American Sign Language while the results are displayed to the users in the form of an animation. The proposed methodology is achieved by using Natural Language Processing, speech recognition, and machine learning techniques. This web-based application enables increased interaction between the student and the system making it an effective learning environment for the hearing impaired.
  • Thumbnail Image
    PublicationEmbargo
    Enhancing Conversational AI Model Performance and Explainability for Sinhala-English Bilingual Speakers
    (IEEE, 2022-12-09) Dissanayake, I; Hameed, S; Sakalasooriya, A; Jayasinghe, D; Abeywardhana, L; Wijendra, D
    Natural language processing has become essential to modern conversational tools and dialogue engines, including Chatbots. However, applying natural language processing to low-resource languages is challenging due to their lack of digital presence. Sinhala is the native language of approximately nineteen million people in Sri Lanka and is one of many low-resource languages. Moreover, the increase in using code-switching: alternating two or more languages within the same conversation, and code-mixing: the practice of representing words of a language using characters of another language, has become another major issue when processing natural languages. Apart from natural language processing, the explainability of opaque machine learning models utilized in chatbots has become another prominent concern. None of the existing modern chatbot development platforms supports explainability and relies on a performance score such as accuracy or f1-score. This paper proposes a no-code chatbot development platform with a series of built-in novel natural language processing, model evaluation, and explainability tools to tackle the problems of processing Sinhala-English code-switching and code-mixing natural language data and model evaluation in modern chatbot development platforms.
  • Thumbnail Image
    PublicationEmbargo
    An ultra-specific image dataset for automated insect identification
    (Springer Nature, 2022-01) Abeywardhana, L; Dangalle, C; Nugaliyadde, A; Mallawarachchi, Y
    Automated identifcation of insects is a tough task where many challenges like data limitation, imbalanced data count, and background noise needs to be overcome for better performance. This paper describes such an image dataset which consists of a limited, imbalanced number of images regarding six genera of subfamily Cicindelinae (tiger beetles) of order Coleoptera. The diversity of image collection is at a high level as the images were taken from diferent sources, angles and on diferent scales. Thus, the salient regions of the images have a large variation. Therefore, one of the main intentions in this process was to get an idea about the image dataset while comparing diferent unique patterns and features in images. The dataset was evaluated on diferent classifcation algorithms including deep learning models based on diferent approaches to provide a benchmark. The dynamic nature of the dataset poses a challenge to the image classifcation algorithms. However transfer learning models using softmax classifer performed well on the current dataset. The tiger beetle classifcation can be challenging even to a trained human eye, therefore, this dataset opens a new avenue for the classifcation algorithms to develop, to identify features which human eyes have not identifed.
  • Thumbnail Image
    PublicationOpen Access
    New record of Tricondyla gounellii Horn 1900 (Coleoptera, Cicindelinae), an arboreal tiger beetle from Sri Lanka
    (: https://www.researchgate.net/publication/336107511, 2019-09) Abeywardhana, L; Dangalle, C; Mallawarachchi, Y
    Arboreal tiger beetles belong to tribe Collyridini of order Coleoptera, family Carabidae, subfamily Cicindelinae and can be found predominantly in the tropical and subtropical regions of Asian countries mainly in forest habitat types (Toki et al., 2017). Tribe Collyridini is divided in to five genera - Collyris, Neocollyris, Protocollyris, Derocrania and Tricondyla. According to records provided by Fowler (1912) from his studies in the Fauna of British India’ five species of genus Tricondyla reside in Sri Lanka - Tricondyla femorata , Tricondyla tumidula , Tricondyla coriacea , Tricondyla nigripalpis , Tricondyla granulifera ). Three of these species, T. coriacea, T. nigripalpis, T. granulifera are endemic to the country, while the other two species also reside in India. However, the sources of this information is far outdated and unreliable and requires current investigations and revision. Thus, the present study was conducted to investigate the current species of arboreal tiger beetles of Sri Lanka, their morphology, locations, habitats and habitat preferences.