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 Assessment of System Reliability in Presence of Cyber Attack Risk on PMU Data(IEEE, 2018-12-21) Hettiarachchige-Don, A. C. S; Manoharan, A. K; Pedaprolu, L. G; Pedaprolu, VThis paper provides an assessment of the effect of Synchrophasor Measurement Units in improving power system reliability. First, an overview of cyber threats to PMU networks is given where the possible vulnerabilities of the network to malicious data manipulation are studied. The addition of PMUs to the power system infrastructure would offer greater observability in the system and thus mitigate the risk of transmission line failure due to thermal overloading. However, the addition of PMUs opens the system to cyber threats that might, in fact, lower system reliability. The analysis in this work looks at the effect of these threats on the overall system reliability of a real system layout based on real PMU data obtained from a utility. The benefit to a utility in including PMUs under the varying levels of cyber threat is also studied.Publication Embargo Machine Learning Based Emotion Level Assessment(IEEE, 2021-12-09) Wickremesinghe, L; Madanayake, D; Karunasena, A; Samarasinghe, PWith recent advancements of technology, identification of emotions of humans via facial recognition is done with the application of numerous methods including machine learning and deep learning. In this paper, machine learning techniques are applied for identifying different levels of emotions of individuals for unannotated video clips using Facial Action Coding System. In order to archive the above, first, two methods were experimented to obtain a labeled image data set to train classification models where in the first method, clustering of images was done using Action Units(AU) identified from literature and the emotion levels of the images were determined through the resulted clusters and images are labeled according to the cluster they belonged to. In the second method, the image set is analyzed explicitly to identify AUs contributing to emotions rather than relying on those identified in literature and then the clustering of image set was done using those identified AUs to label the images similar to the first method. The two labeled data sets were used to train classification models with Random Forest, Support Vector Machine and K-Nearest Neighbour algorithms separately.Classification models showed better accuracy with data set produced using the second method. An overall F1 score, accuracy, precision and recall of 87% was obtained for the best classification model which is developed using the Random Forest algorithm to identify levels of emotions. Identifying the AU combinations related to emotions and developing a classification model for identifying levels of emotions are the major contributions of this paper. The results of this research would be especially useful to identify levels of emotions of individuals who are having issues in verbal communication.Publication Embargo Power Profiling: Assessment of Household Energy Footprints(IEEE, 2021-03-06) Wijesinghe, V; Perera, M; Peiris, C; Vidyaratne, P; Nawinna, D. P; Wijekoon, JReduced energy footprint is considered an indicator of efficiency around the world. Having insights into electricity consumption behavior of individuals or families across the day is very useful in efficient management of electricity. In this paper, we present s study that focused on identifying patterns in the monthly electricity consumption profiles of a single household with the K-means clustering algorithm. The data required for this study was collected through a survey in the Sri Lankan context. The survey mainly captured the factors affecting electricity consumption. After proving the demand of electricity is dependable on the data that has been collected, they will be keyed into data models/ profiles that will be built using clustering algorithms. A load profile will be designed using K-means to identify usage patterns of a household on a monthly basis. The parameters that affect the electricity consumption were tested and trained using the SVM algorithm. The outcomes of this study include; identifying the factors contributing to the electricity consumption, identifying electricity consumption patterns, identifying the energy footprint of individuals or families and predicting the future electricity requirements. The results of this study provide many advantages for both consumers and suppliers in efficient management of electricity. It also provides significant impacts in both micro and macro levels through enabling efficient decision-making regarding management of electricity.Publication Open Access A case study on identification and assessment of postharvest losses of tomato (Lycoperisicon escuentum Mill)(Postgraduate Institute of Agriculture, University of Peradeniya: Peradeniya, 1992) Rupasinghe, H. P. V; Peiris, C. N; Wijeratnam, R. S. WA study was undertaken to quantify and identify the causes of the postharvest losses of tomato during the Malta season of 1991. In the first phase of the study a suivey was earned out using random samples to collect information on the present system of posthaivest handling of tomato. Four major stages of the posthaivest marketing sequence were identified, namely; fann gate, collection agent, Manning wholesale market (Colombo) and exporter respectively. Loss assessments were conducted at these stages. Tlie survey revealed that pest and diseases such as pod borrer (Heliolhis zea) attack and blight (Altemuiia solani and Pliyiopluliora infestans) are the major contributions for posthaivest losses at the fann gate. Over maturity at hanest, bird attack and losses due to sun scorch were also obseived. Cultivating small extents of land (66% of farmers possess less than half acre) increases the liaircsting interval which resulted in a high percentage of over maturity. Tlie above factors subsequently made considerable losses at the collection agents when soiling the product for transportation. Significant losses were observed al the Manning market due to long distance of transportation with improper handling and transportation. Tlte main problem with exporters was the lack of uniformity of product with respect to maturity and size. Cumulative loss at the Manning wholesale market was obseived to be close to 54%. Contributions to the major causes of loss were as follows; mechanical damage due to over ripening 17.3%, pod borrer attack 23%, blight 4.8% and mechanical damage due to other factors 15%. Tlie cumulative loss and rejections after export quality selection was as high as 96%. Rejects due to non conformity to export specifications with respect to maturity, size and shape were 27.52% and 7.34%, respectively.Publication Embargo Power Profiling: Assessment of Household Energy Footprints(IEEE, 2021-03-06) Wijesinghe, V; Perera, M; Peiris, C; Vidyaratne, P; Nawinna, D; Wijekoon, JReduced energy footprint is considered an indicator of efficiency around the world. Having insights into electricity consumption behavior of individuals or families across the day is very useful in efficient management of electricity. In this paper, we present s study that focused on identifying patterns in the monthly electricity consumption profiles of a single household with the K-means clustering algorithm. The data required for this study was collected through a survey in the Sri Lankan context. The survey mainly captured the factors affecting electricity consumption. After proving the demand of electricity is dependable on the data that has been collected, they will be keyed into data models/ profiles that will be built using clustering algorithms. A load profile will be designed using K-means to identify usage patterns of a household on a monthly basis. The parameters that affect the electricity consumption were tested and trained using the SVM algorithm. The outcomes of this study include; identifying the factors contributing to the electricity consumption, identifying electricity consumption patterns, identifying the energy footprint of individuals or families and predicting the future electricity requirements. The results of this study provide many advantages for both consumers and suppliers in efficient management of electricity. It also provides significant impacts in both micro and macro levels through enabling efficient decision-making regarding management of electricity.