Research Papers - Department of Electrical and Electronic Engineering
Permanent URI for this collectionhttps://rda.sliit.lk/handle/123456789/679
Browse
8 results
Search Results
Publication Open Access Dempster–Shafer information filtering framework: Temporal and spatio-temporal evidence filtering(IEEE, 2015-06-04) Weeraddana, D. M; Kulasekere, E. C; Walgama, K. SThis paper presents an information processing framework for distributed sensor networks. The framework is capable of directly processing temporally and spatially distributed multimodality sensor data to extract information buried in the noise clutter. Moreover, we introduce distributed algorithms to implement spatio-temporal filtering applications in grid sensor networks within the context of the framework. The proposed framework is based on the belief notions in Dempster-Shafer (DS) evidence theory and evidence filtering method. Further analysis is done by exploiting a fire propagation scenario when high noise is present in the sensed data. We compare intuitively appealing results against DS fusion method to grant further credence to the proposed framework.Publication Open Access IMAGE PROCESSING BASED GIRTH MONITORING AND RECORDING SYSTEM FOR RUBBER PLANTATIONS(Academy & Industry Research Collaboration Center (AIRCC), 2015-02-01) Thilakarathne, C; Bhanusri, P; Randeny, T; Rupasinghe, H; Kulasekere, E. CMeasuring the girth and continuous monitoring of the increase in girth is one of the most important processes in rubber plantations since identification of girth deficiencies would enable planters to take corrective actions to ensure a good yield from the plantation. This research paper presents an image processing based girth measurement & recording system that can replace existing manual process in an efficient and economical manner. The system uses a digital image of the tree which uses the current number drawn on the tree to identify the tree number & its width. The image is threshold first & then filtered out using several filtering criterion to identify possible candidates for numbers. Identified blobs are then fed to the Tesseract OCR for number recognition. Threshold image is then filtered again with different criterion to segment out the black strip drawn on the tree which is then used to calculate the width of the tree using calibration parameters. Once the tree number is identified & width is calculated the girth the measured girth of the tree is stored in the data base under the identified tree number. The results obtained from the system indicated significant improvement in efficiency & economy for main plantations. As future developments we are proposing a standard commercial system for girth measurement using standardized 2D Bar Codes as tree identifiersPublication Embargo Blended induction program for electronic engineering freshmen(Sage Publications, 2018-10) Dayawansa, I; Wijenayake, C; Edussooriya, C; Samarasekara, T; Karunasekara, C; Dias, D; Samarasinghe, K; Kulasekere, E. C; Rodrigo, R; Dayananda, NThis paper presents learning and teaching experiences gathered from an induction program conducted at the Department of Electronic and Telecommunication Engineering, University of Moratuwa, Sri Lanka for newly enrolled undergraduate students. The induction program, named as the pre-academic term, was an experimental effort to explore the applicability of blended leaning concepts to enhance the learning experience of Engineering freshmen, while enabling smooth transition from high school to university education. In addition to standard lectures, an integral part of the program was in-class demonstrations, where electronic circuits were assembled from scratch on a printed circuit board and demonstrated using a projected camera during the lectures. Organization, learning objectives, brief description of the example projects are presented along with a summary of formal student feedback. More than 85% of the freshmen indicated that the induction program helped them to smoothly begin the university education. A qualitative assessment in the laboratory work indicated that about 98% of the students successfully completed the assigned hands-on activities.Publication Open Access Cluster density of dependent thinning distributed clustering class of algorithms in ad hoc deployed wireless networks(Hindawi, 2012-01-01) Gamwarige, S; Kulasekere, E. CDistributed clustering is widely used in ad hoc deployed wireless networks. Distributed clustering algorithms like DMAC, HEED, MEDIC, ANTCLUST-based, and EDCR produce well-distributed Cluster Heads (CHs) using dependent thinning techniques where a node’s decision to be a CH depends on the decision of its neighbors. An analytical technique to determine the cluster density of this class of algorithms is proposed. This information is required to set the algorithm parameters before a wireless network is deployed. Simulation results are presented in order to verify the analytical findings.Publication Embargo Energy expenditure of global reclustering and local delegation in Wireless Sensor Networks(IEEE, 2010-09-06) De Silva, H. J; Gamwarige, S; Kulasekere, E. COne of the most important aspects in a clustering algorithm in a wireless sensor network is the cluster head (CH) rotation mechanism. Global reclustering is the common and established method used for this purpose in many existing algorithms. This research proposes an analytical framework to investigate the average energy expenditure of the global reclustering method and a local delegation strategy in which the CH role is delegated to a member of the cluster without changing the initial cluster boundary. Further we investigate a strategy of partial local delegation within global reclustering rounds to achieve energy efficiency. Simulations are used to visualize the analytically derived results using the simulation environment MATLAB.Publication Open Access Dempster-Shafer Information Filtering in Multi-Modality Wireless Sensor Networks(publications.waset.org, 2013-07-27) Weeraddana, D. M; Walgama, K. S; Kulasekere, E. CA framework to estimate the state of dynamically varying environment where data are generated from heterogeneous sources possessing partial knowledge about the environment is presented. This is entirely derived within Dempster-Shafer and Evidence Filtering frameworks. The belief about the current state is expressed as belief and plausibility functions. An addition to Single Input Single Output Evidence Filter, Multiple Input Single Output Evidence Filtering approach is introduced. Variety of applications such as situational estimation of an emergency environment can be developed within the framework successfully. Fire propagation scenario is used to justify the proposed framework, simulation results are presented.Publication Embargo Developing online tutors and mentors in Sri Lanka through a community building model: Predictors of satisfaction(IEEE, 2012-12-12) Gunawardena, C. N; Jayatilleke, B. G; Fernando, S; Kulasekere, E. C; Lamontagne, M. D; Ekanayake, M. B; Thaiyamuthu, TThis paper discusses the results of a tutor mentor development program that utilized a community building model to train online tutors and mentors in higher education institutions and professional organizations in Sri Lanka. Based on WisCom; an instructional design model for developing online wisdom communities, this tutor mentor development program which utilized a blended format of face-to-face and online activities in MOODLE, attempted to build a learning community between trainees, both academics and professionals who represented diverse disciplines and organizations. A regression model examined predictors of learner satisfaction, using four independent variables: Community Building, Interaction, Course Design, and Learner Support. Interaction emerged as a strong predictor of Learner Satisfaction explaining 50.2% of the variance in Learner Satisfaction. This finding shows the importance of designing interactive learning activities to support learning online, and contradicts the general belief that Sri Lankan participants would be less likely to interact online because they come from a traditional education system that encourages passivity and reception of ideas from a more learned teacher. Qualitative analysis showed evidence of several types of learning online as a result of collaborative group interaction, as well as issues that contributed to non-participation. Factors that motivated participants to stay engaged in learning could be classified into three categories: (1) general enjoyment, interest and motivation; (2) collaborative learning and community building; and (3) knowledge building. These results suggest that the online learning design based on WisCom led to learner satisfaction and supported interaction and collaborative learning in the Sri Lankan socio-cultural context.Publication Embargo Dempster–Shafer information filtering framework: Temporal and spatio-temporal evidence filtering(IEEE, 2015-06-04) Weeraddana, D. M; Kulasekere, E. C; Walgama, K. SThis paper presents an information processing framework for distributed sensor networks. The framework is capable of directly processing temporally and spatially distributed multimodality sensor data to extract information buried in the noise clutter. Moreover, we introduce distributed algorithms to implement spatio-temporal filtering applications in grid sensor networks within the context of the framework. The proposed framework is based on the belief notions in Dempster-Shafer (DS) evidence theory and evidence filtering method. Further analysis is done by exploiting a fire propagation scenario when high noise is present in the sensed data. We compare intuitively appealing results against DS fusion method to grant further credence to the proposed framework.