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
44 results
Filters
Advanced Search
Filter by
Settings
Search Results
Publication Embargo Learning platform for visually impaired children through artificial intelligence and computer vision(IEEE, 2018-02-19) Balasuriya, B. K; Lokuhettiarachchi, N. P; Ranasinghe, A. R. M. D. N; Shiwantha, K. D. C; Jayawardena, CThe topic Visual Disabilities and Computer Vision are the most researched topics of recent years. Researchers have been trying to combine two topics to create most usable systems to the visually disabled to aid them in their day to day tasks. In this research, we are trying to create an application which is targeting children between the age of 6-14 who suffers from visual disabilities to aid them in their primary learning task of learning to identify objects without a supervision of a third-party. We are trying to achieve this task by combining latest advancements of Computer Vision and Artificial Intelligence technologies by using Deep Region Based Convolutional Networks (R-CNN), Recurrent Neural Networks (RNN) and Speech models to provide an interactive learning experience to such individuals. The paper discusses.Publication Embargo TreeSpirit: Illegal logging detection and alerting system using audio identification over an IoT network(IEEE, 2018-02-19) Kalhara, P. G; Jayasinghearachchi, V. D; Dias, A. H. A. T; Ratnayake, V. C; Jayawardena, C; Kuruwitaarachchi, NIllegal logging has been identified as a major problem in the world, which may be minimized through effective monitoring of forest covered areas. In this paper, we propose and describe the initial steps to build a new three-tier architecture for Forest Monitoring based on Wireless Sensor Network and Chainsaw Noise Identification using a Neural Network. In addition to detection of chainsaw noises, we also propose methodologies to localize the origin of the chainsaw noise.Publication Embargo Comparative analysis of the application of Deep Learning techniques for Forex Rate prediction(IEEE, 2019-12-05) Aryal, S; Nadarajah, D; Kasthurirathna, D; Rupasinghe, L; Jayawardena, CForecasting the financial time series is an extensive field of study. Even though the econometric models, traditional machine learning models, artificial neural networks and deep learning models have been used to predict the financial time series, deep learning models have been recently employed to do predictions of financial time series. In this paper, three different deep learning models called Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN) and Temporal Convolution Network (TCN) have been used to predict the United States Dollar (USD) to Sri Lankan Rupees (LKR) exchange rate and compared the accuracy of the models. The results indicate the superiority of CNN model over other models. We conclude that CNN based models perform best in financial time series prediction.Publication Embargo Comparative analysis of the application of Deep Learning techniques for Forex Rate prediction(2019-12-05) Nadarajah, D; Aryal, S; Kasthurirathna, D; Rupasinghe, L; Jayawardena, CForecasting the financial time series is an extensive field of study. Even though the econometric models, traditional machine learning models, artificial neural networks and deep learning models have been used to predict the financial time series, deep learning models have been recently employed to do predictions of financial time series. In this paper, three different deep learning models called Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN) and Temporal Convolution Network (TCN) have been used to predict the United States Dollar (USD) to Sri Lankan Rupees (LKR) exchange rate and compared the accuracy of the models. The results indicate the superiority of CNN model over other models. We conclude that CNN based models perform best in financial time series prediction.Publication Embargo Lounging with robots–social spaces of residents in care: a comparison trial(Wiley Online Library, 2015-12-02) Peri, K; Kerse, N; Broadbent, E; Jayawardena, C; Kuo, T; Datta, C; Stafford, R; MacDonald, BTo investigate whether robots could reduce resident sleeping and stimulate activity in the lounges of an older persons care facility.Publication Embargo Posture control of robot manipulators with fuzzy voice commands using a fuzzy coach–player system(Taylor & Francis Group, 2007-01-01) Jayawardena, C; Watanabe, K; Izumi, KThis paper presents a method of controlling robot manipulators with fuzzy voice commands. Recently, there has been some research on controlling robots using information-rich fuzzy voice commands such as 'go little slowly' and learning from such commands. However, the scope of all those works was limited to basic fuzzy voice motion commands. In this paper, we introduce a method of controlling the posture of a manipulator using complex fuzzy voice commands. A complex fuzzy voice command is composed of a set of fuzzy voice joint commands. Complex fuzzy voice commands can be used for complicated maneuvering of a manipulator, while fuzzy voice joint commands affect only a single joint. Once joint commands are learned, any complex command can be learned as a combination of some or all of them, so that, using the learned complex commands, a human user can control the manipulator in a complicated manner with natural language commands. Learning of complex commands is discussed in the framework of fuzzy coach–player model. The proposed idea is demonstrated with a PA-10 redundant manipulator.Publication Open Access A navigation model for side-by-side robotic wheelchairs for optimizing social comfort in crossing situations(North-Holland, 2018-02-01) Nguyen, V. T; Ardekani, I; Jayawardena, COne challenge in designing side-by-side robotic wheelchairs is to improve the comfort of the users, caregivers and surrounding people in crowded environments. Among different scenarios that a side-by-side robotic wheelchair has to deal with, crossing pedestrians is a common situation. Yet techniques developed for tackling the problem of passing pedestrians have still failed to take into account enough factors related to human walking behavior, therefore the navigation plan is not natural. To tackle this problem, this paper proposes a novel navigation model for side-by-side robotic wheelchairs that considers the Friendly Link factor and Preferred Walking Velocity related to the comfort of wheelchair users, caregivers and pedestrians. The model is carried out based on an experimental observation and data collection. The developed model is then validated by comparing the distance errors between the moving solutions of the new model and previous methods with the real solutions of humans based on a natural walking scenario. The experimental results show that the performance of the proposed technique is significantly better than that of previous techniques.Publication Open Access Multidisciplinary Design Approach for Implementation of Interactive Services(Springer Netherlands, 2011-10-14) Kuo, I. H; Jayawardena, C; Broadbent, E; MacDonald, B. AIn the design of service robots, a key research focus has been on Human Robot Interaction (HRI) required in service applications. HRI is one of the critical factors that determines the acceptability of a service robot. The user acceptance of a service robot and its applications is highly related to HRI, as HRI affects the user perception and user experience related to the robot. In this paper, a new design approach is proposed for designing and implementing HRI for service robot applications designed for real scenarios in the real-world environment. The objective of this design approach is to facilitate inter-disciplinary collaborations, which are essential for HRI research and for developing successful products. The proposed design approach was used in the design of the healthcare service robot “Cafero” developed at the University of Auckland in collaboration with the Electronic and Telecommunication Research Institute (ETRI) and Yujin Robot Company Ltd. of Korea. Vital signs measurement, medication management, entertainment and falls detection were implemented as service applications of Cafero. In the design process, UML and UMLi modelling diagrams were used to model the robot’s multi-modal and interactive behaviour. Interaction design patterns were defined to represent recurring interactions or social cues in HRI using UMLi notations. The proposed design approach emphaI- sises an iterative process to allow discovery of additional HRI requirements in the early design stage and to implement through Component-Based Software Engineering (CBSE). The design of communication initiation and user identification by Cafero is presented as a case study, in order to evaluate the proposed design approach. In this case study, enabling a service robot to act proactively to the presence of a potential user and identifying the user prior to providing healthcare services is presented. For the implementation, Open-RTM component-oriented framework was used.Publication Open Access Controlling a robot manipulator with fuzzy voice commands using a probabilistic neural network(Springer-Verlag, 2006-07-06) Jayawardena, C; Watanabe, K; Izumi, KNatural language commands are generated by intelligent human beings. As a result, they contain a lot of information. Therefore, if it is possible to learn from such commands and reuse that knowledge, it will be a very efficient process. In this paper, learning from such information rich voice commands for controlling a robot is studied. First, new concepts of fuzzy coachplayer system and sub-coach are proposed for controlling robots with natural language commands. Then, the characteristics of the subjective human decision making process are discussed and a Probabilistic Neural Network (PNN) based learning method is proposed to learn from such commands and to reuse the acquired knowledge. Finally, the proposed concept is demonstrated and confirmed with experiments conducted using a PA-10 redundant manipulator.Publication Open Access Feasibility study of a robotic medication assistant for the elderly(Academia, 2011-01-17) Tiwari, P; Warren, J; Day, K; MacDonald, B; Jayawardena, C; Kuo, I.H; Igic, A; Datta, CManagement of complex medication regimens by older people poses a significant challenge wherein use of information technology could play a role in improving clinical efficacy and safety of treatment. The use of computing devices, however, presents a special challenge to older people given their physical and cognitive limitations. Robotic platforms show promise for extending the functionality of the user interface to make personalized interaction engaging and empowering, and for proactively reaching out to older users to support their healthcare delivery. We believe that a robot combining a touch screen and voice based interface could offer an effective platform to meet these requirements. This paper reports on a feasibility study of such a system for helping older people with their medications. We exposed 10 relatively independent residents of an aged care facility to our robot running a medication reminding application while they took their medications. The interaction was followed by a questionnaire and structured interview to elicit their opinions and feedback. We found the application to be well received as all users could successfully complete the session, and most subjects found it easy to use, appropriately designed and felt confident using it. A number of technical errors were uncovered, and the results suggest opportunities to refine the equipment and dialog design to provide a better robotic medication assistant.