Research Papers - Dept of Computer Systems Engineering
Permanent URI for this collection https://rda.sliit.lk/handle/123456789/1253
Browse
13 results
Filters
Advanced Search
Filter by
Settings
Search Results
Publication Embargo An evolutionary prototype of a self-care application for type 2 diabetes(IEEE, 2022-12-26) Widanarachchi, K; Mayadunne, S; Disanayake, K; Gunathilake, V; Kahandawaarachchi, C; Kasthurirathna, D; Jayasekera, PDiabetes Mellitus or Diabetes is a chronic health condition. As there is no cure for both type 1 and 2 diabetes yet, the only solution is to manage the condition by improving lifestyle activities like eating and exercising and seeking medical advice. There are applications for diet planning, to analyze meals for nutrients, to suggest diabetic-friendly recipes and devices like blood glucose trackers to support type 2 diabetic patients. But there is no application or a device that can support a patient by addressing the diabetes condition. So, the plan is to conduct applied research on developing a mobile app for type 2 diabetes, capable of not only monitoring the patient’s physical activities but also for diet planning, monitoring diabetic peripheral neuropathy and diabetic foot ulcer (DFU) complications. This application provides point-of-care monitoring features that can help diabetic patients to understand their condition and to identify complication in advance and get necessary treatments. There are 3 main components focusing on patients’ diet, physical conditional, the possibility of diabetic peripheral neuropathy and DFUs. In order to implement these components, the intention is to use classification, clustering techniques in machine learning and CNN techniques for image processing. While the accuracies of the selected models built upon each feature (component) is more than 90%, the models have then been tested and concluded that each feature works accurately on patients.Publication Embargo Predictive Analytics Platform for Airline Industry(IEEE, 2020-12-10) Tissera, P. H. K; Waduge, K. T; Perera, M. A. l; Nawinna, D. P; Kasthurirathna, DThe research is to develop accurate demand forecasting model to control the availability in Airline industry. The primary outcome of the model is that the Airline organization can maximize the revenue by controlling the availability. The product in airline industry is the seat, which is an expensive, unstock able product. The demand for the seats is almost uncertain, the capacity is constraint and difficult to increase and the variable costs are very high. Hence the priority of the expected demand forecast is very high for airline industry. An accurate mechanism to predict the revenue for future months of ODs (Origin destinations) is done using fare and passenger data. The revenue is derived by the number of passengers and the fares they pay which vary for each flight. Airline travel is very susceptible to the social, political and economic changes. Therefore, passenger buying patterns change quite dynamically. Hence, it is challenging to develop an accurate method to project the revenue for each route. To overcome this, we are going to use semi-supervised learning mechanism. We have the current ticketed revenue plus we have the current booked passengers. We also have the ticketed passenger details of previous flights. Hence most of the information is available, however changing market conditions is an unknown variable which can have a significant impact on passenger travel patterns. Through this research We are going to design and develop the best fit model to forecast flight OD level passenger demand based on the historical data.Publication Open Access Sri Lankan Currency Detector for Visually Impaired People(Department of Computing and Information Systems, Faculty of Applied Sciences, Sabaragamuwa University of Sri Lanka, 2021-02-24) Abimani, R. M. K. C; Thalagahagedara, T. M. S. S. B; Thilakarathna, H. P. M. U; Wickramasingha, S. D. S. B; Nawinna, D. P; Kasthurirathna, DBlind people face more difficulties in day to day life. One pressing problem is they also want to use physical currency (notes and coins) as others. They always have a hard time when trying to recognize the value of a currency, we intend to address this matter by developing a mobile application for blind people. We are going to implement this currency recognition mobile application along with counting and voice command compatibility and also this application is having user-friendly interfaces, therefore easy to negotiate. By using this mobile application blind people can give voice commands to navigate and the start intended to function as a currency recognition or counting as a pleased. We are going to use the user’s mobile phone camera to get input into the app then classify the currency as a note or a coin. After that extract the features of the currency note and coin by using Convolutional Neural Network and predicting the value of the currency note and coin. This mobile application can extract the value of the coins and notes without any issue. Finally, we used Artificial Neural Network for the classification of notes and coins. Processing it and get the real value of the notes. Finally, train the Sinhala and English voice command using the CNN model and get them out as a voicePublication Embargo Mobile-based Malware Detection and Classification using Ensemble Artificial Intelligence(IEEE, 2019-12-05) Somasundaram, S; Kasthurirathna, D; Rupasinghe, LThe Android operating system is one of the most used operating systems in the world and has become a target to malware authors. Traditional malware detection methods such as signatures find it impossible to deal with detecting complex and intelligent malware which are capable of obfuscating and repackaging to avoid being detected. There is therefore an increase in the need to have more efficient and intelligent forms of malware detection. Artificial intelligence has now been brought to the field of malware detection and classification. Due to its accuracy and intelligence it has become an ideal solution to bridge the gap between traditional classifiers and the intelligent malware. Currently, research is mainly being conducted using either machine learning or deep learning techniques to target all or a given malware family. This paper proposes a methodology which brings an ensemble solution between the Support Vector Machine algorithm and the Convolutional Neural Network to create a solution that provides a higher accuracy than available techniques.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 Smart Plant Disorder Identification using Computer Vision Technology(IEEE, 2020-11-04) Manoharan, S; Sariffodeen, B; Ramasinghe, K. T; Rajaratne, L. H; Kasthurirathna, D; Wijekoon, JThe soil composition around the world is depleting at a rapid rate due to overexploitation by the unsustainable use of fertilizers. Streamlining the availability of nutrient deficiency and fertilizer related knowledge among impoverished farming communities would promoter environmentally and scientifically sustainable farming practices. Thus, contributing to several Sustainable Development Goals set out by the United Nations. The most direct solution to the inappropriate fertilizer usage is to add only the necessary amounts of fertilizer required by plants to produce a significant yield without nutrition deficiencies. To this end this paper proposes a Smart Nutrient Disorder Identification system employing computer vision and machine learning techniques for identification purposes and a decentralized blockchain platform to streamline a bias-less procurement system. The proposed system yielded 88% accuracy in disorder identification, while also enabling secure, transparent flow of verified information.Publication Embargo Plus Go: Intelligent Complementary Ride-Sharing System(IEEE, 2019-11-21) Wickramasinghe, V; Edirisinghe, A; Gunawardena, S; Gunathilake, A; Kasthurirathna, D; Wijekoon, JCurrently the world population is gathering to the cities making huge traffic congestion throughout the day. This has drawn serious attention to the society incurred to implement smart solutions for traffic management. One of the prominent problems for traffic congestion is the number of vehicles entering the cities is high. It is a popular fact that the solitary travelers coming to a defined destination make the vehicles underutilized. Therefore, this study proposes a solution to implement a new ride-sharing platform: Plus Go, to reduce this underutilization. Plus Go matches the travelers by considering the designation, traveler preferences, shortest path details, and the ratings of the users. Moreover, Plus Go intelligently estimates the traveling cost based on the fuel consumption of the vehicle, distance traveled, and the time taken to reach the destination. The proposed solution matches the travelers with 98% accuracy ensuring that ride-sharing is an effective solution to reduce the number of vehicles entering the cities.Publication Embargo On The Effectiveness of Using Machine Learning and Gaussian Plume Model for Plant Disease Dispersion Prediction and Simulation(IEEE, 2020-05-29) Miriyagalla, R; Samarawickrama, Y; Rathnaweera, D; Liyanage, L; Kasthurirathna, D; Nawinna, D; Wijekoon, JAgriculture plays a vital role in the economic development of the entire world. Similarly, in Sri Lanka, 6.9% of the national GDP is contributed by the agricultural sector and more than 25% of Sri Lankans are employed in the field of agriculture. But the frequent fluctuations of climate conditions have caused the spread of diseases such as late blight which eventually has led to the devastation of entire plantations of Sri Lankans. To this end, this paper proposes to forecast the possible dispersion pattern and assist the farmers in identifying the possibility of the disease getting dispersed to nearby crops to provide early warning. Eventually, it leads the farmers to take precautions to save the plants before reaching a critical stage. The yielded results show that the proposed method successfully performed disease diagnosis and disease progression level identification with 90-94 % accuracy and dispersion pattern analysis.Publication Embargo Mobile-based Malware Detection and Classification using Ensemble Artificial Intelligence(IEEE, 2019-12-05) Somasundaram, S; Kasthurirathna, D; Rupasinghe, LThe Android operating system is one of the most used operating systems in the world and has become a target to malware authors. Traditional malware detection methods such as signatures find it impossible to deal with detecting complex and intelligent malware which are capable of obfuscating and repackaging to avoid being detected. There is therefore an increase in the need to have more efficient and intelligent forms of malware detection. Artificial intelligence has now been brought to the field of malware detection and classification. Due to its accuracy and intelligence it has become an ideal solution to bridge the gap between traditional classifiers and the intelligent malware. Currently, research is mainly being conducted using either machine learning or deep learning techniques to target all or a given malware family. This paper proposes a methodology which brings an ensemble solution between the Support Vector Machine algorithm and the Convolutional Neural Network to create a solution that provides a higher accuracy than available techniques.Publication Embargo Information Theoretic Approach for Modeling Bounded Rationality in Networked Games(IEEE, 2019-12-06) Gunawardana, L; Ratnayake, p; Piraveenan, M; Kasthurirathna, DBounded rationality of networked interactions lead to non-optimal equilibria. The rationality of a self-interested player is determined by the incoming information from the opponents on their strategies and pay-offs. In this work, we attempt to model the heterogeneously distributed bounded rationality of networked players using the directed information flow, measured using the transfer entropy. In order to compute the non optimal equilibrium, we use the Quantal Response Equilibrium (QRE) model that entails a rationality parameter, which we define as a function of transfer entropy. We then compute the average divergence of the network of strategic interactions from that of the Nash Equilibrium, which we term as the `system rationality', in order to compare and contrast the varying network topologies on their influence on the rationality of players. We observe that the networks demonstrate higher system rationality when the rationality values of players are derived from on the average information flow from neighboring nodes, compared to when the rationality is computed based on the specific information flow from each opponent. Further, we observe that the scale-free and hub-and-spoke topologies lead to more rational interactions compared to random networks, when the rationalities of the interactions are computed based on the average incoming information flow to each node. This may suggest that the networks observed in the real-world may adopt scale-free and hub-and-spoke topologies, in order to facilitate more rational interactions among networks of strategic players.