Research Publications Authored by SLIIT Staff
Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/4195
This collection includes all SLIIT staff publications presented at external conferences and published in external journals. The materials are organized by faculty to facilitate easy retrieval.
Browse
5 results
Filters
Advanced Search
Filter by
Settings
Search Results
Publication Embargo Automated Spelling Checker And Grammatical Error Detection And Correction Model for Sinhala Language(IEEE, 2022-10-04) Goonawardena, M; Kulatunga, A; Wickramasinghe, R; Weerasekara, T; De Silva, H; Thelijjagoda, SSinhala is a native language spoken by the Sinhalese people, the largest ethnic group in Sri Lanka. It is a morphologically rich language, which is a derivation of Pali and Sanskrit. The Sinhala language creates a diglossia situation, as the language’s written form differs from its spoken form. With this difference, the written form requires more complex rules to be followed when in use. Manually proofreading the content of Sinhala material takes up much time and labor, and it can be a tedious task. Hence, a system is necessary which can be used by different industries such as journalism and even students. At present, there are a handful of systems and research that have automated Sinhala spelling analysis and grammar analysis. In addition, the existing systems are mainly focused on either spelling analysis or grammar analysis. However, the proposed system will cover both aspects and improve upon existing work by either optimizing or re-building the process to provide accurate outputs. The proposed system consists of a suffix list built for verbs and subjects, which helps the system stand out from the current proposed solutions. This research intends to implement a service for spell checking and grammar correctness of formal context in Sinhala. The research follows a rule-based approach with some components adopting a hybrid approach. As per the literature survey, many papers were analyzed, related to different aspects of the proposed system and complete systems. The proposed system would be able to overcome most barriers faced by previous papers whilst it takes a fresh take on providing a solution.Publication Embargo Chess ADC – An Automated Aide-De-Camp(IEEE, 2020) Divulage, A; Bandara, R; Liyanage, T; Ishara, M; Gamage, A. I; Thilakarathna, TVarious types of tools and techniques are used to analyse chess games. The existing most successful and accredited method is, electronic boards where it is able to track and extract the movement data with the help of electronic equipment and pressure detecting sensors [1]. But that solution is expensive. Chess ADC is a comprehensive framework that can be used by anyone for practicing and developing chess skills. It allows users to play chess games on a real chessboard and measure their level of skill. Although chess is a very complicated game that has many different patterns of piece movements, all the number of states that a game can have is finite. We can solve chess with just math if we have unlimited amount of computing power [2]. Deep learning models have already been used in research on various board games such as backgammon, checkers, Go and chess [3]. Chess ADC also utilizes these technologies to give a better user experience for the players. We call this system “Chess ADC – An Automated Aide-De-Camp” because it functions as an aide-de-camp for chess. The system uses a special camera rig to capture different states of the board as images. Players are guided with onscreen instructions to set up the environment at the beginning of each game. At this stage, the position of each chess piece is validated. If the system was able to find any misplaced piece, it notifies the player to correct the position. This process is handled using image processing combined with machine learning. After setting up the board correctly, players can start the game. While in the game, each position of the chess piece is tracked and validated against chess rules. This helps to correct the mistakes of the players. The system asks the players to correct the mistakes if it has detected any mistake. Image processing and chess.js library will be used to achieve this. In difficult situations, players can request hints from the system about the best move they can make. The system will give the best move for that situation using the Stockfish engine. At the same time, the system tries to predict the opponent’s next move based on the generated hint from the engine. The best move and the prediction are displayed on the mobile screen of the player so that the player can decide the next move. An artificial neural network (ANN) developed combining one Convolutional Long Short-term Memory (ConvLSTM) neural network and six different Convolutional neural networks (CNN) is used to make predictions about the opponent. Chess-ADC can recognize the winning probability of every move of the chess pieces. And recognize special moves that have an important impact on the probability of winning. And the player can see those good-bad moves and it is very important for the learning process. We use portable notation files for the storing of game details so that the players will be able to view the past games. The system stores all the matches in a database. This way the players can re-watch the games that they have played before and improve their game strategies while looking at the changes in the win percentage. Gathered data are analyzed and advanced reports are generated. Players can access these reports through user accounts. These reports will help the players to identify the best moves and the worst moves that they have made.Publication Embargo Automated Non-verbal Child Intelligent Assessment Tool(IEEE, 2020-12-10) Madushanka, K. P. D; Hasaranga, U. G. N; Gunasinghe, M. D; Seneviratne, S. M. A. B. B; Samarasingha, P; Dahanayaka, D; Siriwardhana, SThe intelligent assessment tool is very important to identify children with disorders and children having poor IQ level. Though there are many application and research done by developed countries, low and middle-income countries like Sri Lanka cannot afford such systems. To overcome that challenge, in this research an automated tool is developed to measure the intelligence level of children for different aspects. Draw a man test, shape correction test, arithmetic test and number cancellation test measure the child's mental age and IQ level. With our model, the children can use traditional paper and pencil or mobile application their convenience. As this is automated the medical personal can directly get the assessment result and the children who are diagnosed having low-performance level can be directed to the consultant for immediate intervention. In future, we plan to extend this application to link with more assessments.Publication Embargo CIS: an automated criminal identification system(IEEE, 2018-12-21) Rasanayagam, K; Kumarasiri, S. D. D. C; Tharuka, W. A. D. D; Samaranayake, N. T; Samarasinghe, P; Siriwardana, S. E. RThe identification of criminals and terrorists is a primary task for police, military and security forces. The terrorist activities and crime rate had increased abnormally. Combating them is a challenging task for all security departments. Presently, these departments are using latest technologies. But they have not enough efficient and accuracy as they expected This research study is based on the analysis of faces, emotions, Ages and genders to identify the suspects. Face recognition, emotion, age and gender identifications are implemented using deep learning based CNN approaches. Suits identification is based on LeNet architecture. In the implementation phase for the classification purpose, Keras deep learning library is used, which is implemented on top of Tensorflow. IMDb is the dataset used for the whole training purpose. Training is performed using in AWS cloud which is more powerful and capable way of training instead of using local machines. Real-time Video and images are taken for the experiment. Results of the training and predictions are discussed below in brief.Publication Embargo Automated Smart Checkup Portal Network System to Check the Vision and Hearing of the Patients(IEEE, 2019-12-05) Dias, A. A. T. K; Vithusha, J; Liyadipita, L. A. M. T. J; Abeygunawardhana, P. K. WThe human eye and ear are impressive systems in the body. Vision and Hearing are the main functions of those organs. We should regularly check our vision and hearing, It's the most reliable ways to maintain good vision and hearing. Not only that, every patient must keep a medical history and previous checkup records, those related to vision and hearing and those results should be real-time processed. Therefore, we have built an Automated Centralized Smart EE (eye and ear) Checkup Portal Network System. We have designed and developed an automated centralized vision and hearing checkup rooms network, Automated centralized live traffic indicating cloud-based web application to establish in every hospital.