Browsing by Author "Liyanage, T"

Now showing 1 - 5 of 5

Embargo
Chess ADC – An Automated Aide-De-Camp
(IEEE, 2020) Divulage, A; Bandara, R; Liyanage, T; Ishara, M; Gamage, A. I; Thilakarathna, T
Various 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.
Open Access
Investigating the Effectiveness of Shadowing as a Listening Technique in Enhancing Listening Comprehension of Undergraduate English as a Second Language Learners
(Department of Linguistics, Faculty of Humanities and Sciences, SLIIT, 2025-10-10) Liyanage, T
Shadowing is an advanced language learning technique that learners can use independently to improve their intonation and pronunciation. Through this technique, the learners are allowed to listen to a model (i.e., a video or audio of someone speaking) and repeat what is said in real-time. Unlike in the listenpause- repeat method of yesteryear, here one precisely repeats every utterance, sound by sound, wordby word, immediately after they are heard. Based on an experiment involving shadowing, this study examines the impact of shadowing on enhancing listening comprehension among a group of undergraduate English as a Second Language (ESL) learners in the Faculty of Humanities at the University of Kelaniya. The research employed a mixed-methods approach, combining quantitative and qualitative data through pre- and post-tests and structured interviews to evaluate the efficacy of shadowing in enhancing learners’ listening comprehension skills, while also documenting their perceptions of shadowing as a listening technique. The quantitative findings from the independent sample t-tests indicated a substantial enhancement of the listening comprehension scores during the post-test, with mean scores of 8.10 for the experimental group and 5.50 for the control group. The statistical study validated the importance of these techniques (p = 0.000). The qualitative results gathered from interviews highlighted the students’ initial scepticism and curiosity, increased focus and active engagement in listening, improvement in listening speed and word recognition, enhancement of their pronunciation and intonation, and the positive impact shadowing had on their listening comprehension test performance as the emerging themes. These results underscore the pedagogical value of shadowing as a listening technique under an interactive and cognitively engaging approach to ESL listening instruction. Hence, this study adds to the existing literature on listening instruction and provides practical implications for ESL instructors seeking to integrate the shadowing technique into their teaching practices.
Embargo
Road Navigation System Using Automatic Speech Recognition (ASR) And Natural Language Processing (NLP)
(IEEE, 2019-01-31) Withanage, P; Liyanage, T; Deeyakaduwe, N; Dias, E; Thelijjagoda, S
In a highly evolving technical era, Voice-based Navigation Systems play a major role to bridge the gap between human and machine. To overcome the difficulty in taking and understanding user's voice commands, simulating the natural language, process the route with user's turn by turn directions while mentioning key entities like street names, landmarks, point of interests, junctions and map the route in an interactive interface, we propose a user-centric roadmap navigation mobile application called “Direct Me”. The approach of generating the user preferred route, system will first convert the audio streams into text through Automatic Speech Recognizer (ASR) using Pocket Sphinx Library, followed by Natural Language Processing (NLP) by utilizing Stanford CoreNLP Framework to retrieve the navigation-associated information and process the route in the Map using Google Map API upon the user request. This system is used to provide an efficient approach to translate natural language directions to a machine-understandable format and will benefit the development of voice-based navigation-oriented humanmachine interface.
Open Access
Sustainable food waste management: A cross-country study of Australian and Sri Lankan hotel sector
(Elsevier Ltd, 2025-12) Jayasuriya, N; Wickramaarachchi, C; Wijesundara, H; Sriyananda, U; Rathnayake, V; Liyanage, T
Food wastage constitutes a critical global issue, with an estimated one-third of the food produced worldwide being wasted annually. The hotel sector represents a key contributor to this problem; however, it has received limited attention in the existing body of research. Therefore, this study seeks to undertake a comprehensive analysis of the underlying drivers of food wastage, the challenges encountered, and the strategies implemented to mitigate this issue within the hotel industry. Addressing the different contexts in developed and developing countries, this study has selected hoteliers in Australia and Sri Lanka. Data was collected from 20 hotel employees from both countries who are responsible for food handling and were analyzed thematically. The findings identified transportation waste, kitchen waste, and consumer waste as critical points of food wastage. Additionally, the role of technological equipment, combined with food safety precautions and regulatory measures, emerged as pivotal in managing food waste. These aspects are examined in detail alongside proposed mitigation strategies. Even though hospitality sector is largely contributed to these issues, the studies conducted on this sector in relation to the food wastage is very limited. Thus, this study focuses on filling the void in the literature by conducting an in-depth investigation on this topic.
Embargo
Voice-based Road Navigation System Using Natural Language Processing (NLP)
(IEEE, 2018-12-21) Withanage, P; Liyanage, T; Deeyakaduwe, N; Dias, E; Thelijjagoda, S
In a highly technological era, voice-based navigation systems play a major role in bridging the gap between man and machine. To overcome the difficulty in understanding the user's voice commands and natural language simulations, process the path with the user's turn by turn directions with the mention of key entities such as street names, landmarks, points of interest, connections and path mapping in an interactive interface, we propose a user-centric roadmap navigation mobile application called “Direct Me”. To generate the user's preferred path, the system will first convert audio streams to text through ASR using the Pocket Sphinx library, followed by Natural Language Processing (NLP) by taking advantage of Stanford CoreNLP Framework to retrieve navigation-related information and handle the path in the map using the Google Map API at the user's request. This system is used to provide an effective approach to translating natural language commands into a format that can be fully understood by machine and will benefit in the development of human-machine-oriented interface.