Research Papers - Dept of Computer Systems Engineering
Permanent URI for this collection https://rda.sliit.lk/handle/123456789/1253
Browse
10 results
Search Results
Publication Embargo Data-driven Online Decision Support for Hotel Site Selection(IEEE, 2021-12-22) Kumarage, I; Weerakeshara, N; Chamika, T; Rathnapala, H; Nawinna, D. P; Gamage, NLocation is one of the fundamental factors that determine hotel success. The location, once selected, cannot be changed without a significant investment. This research aims to identify the location-specific factors that affect Sri Lankan coastal hotels. The factors that affect the location rating have been assessed under location attraction, accessibility, and popularity. An ensemble learning model has been trained to predict the location score of a hypothetical location, assess the manner accessibility affects hotel performance, and predict location popularity based on the surrounding competition. The results show that this method can assess hotel location and performance, with significant accuracy and the identified location-related factors that contribute to a hotel's success can be used by hoteliers and investors to improve decision making.Publication Embargo Digital Tool for Prevention, Identification and Emergency Handling of Heart Attacks(IEEE, 2021-09-30) Mihiranga, A; Shane, D; Indeewari, B; Udana, A; Nawinna, D. P; Attanayaka, BHeart attack is one of the most frequent causes of death in adults. The majority of heart attacks lead to death before any treatment is given to patients. The conventional mode of healthcare is passive, whereby patients themselves call the healthcare services requesting assistance. Consequently, if they are unconscious when heart failure occurs, they normally fail to call the service. To prevent patients from further harm and save their lives, the early and on-time diagnosis important. This paper presents an innovative web and mobile solution designed using it as Internet of Things (IoT) technology and Machine learning concepts to effectively manage heart patients, the ‘CARDIIAC’ system. This system can predict potential heart attack based on a set of identified risk factors. The system also can identify an actual heart attack using the readings from a wearable IoT device and notify the patient. The system is also equipped with emergency event coordination functionalities. Therefore, ‘CARDIIAC’ provides a holistic care for heart patients by effectively monitoring and managing emergencies related to heart diseases. This would be a socially important system to reduce the number of heart patients who die due to the inability to get immediate treatment.Publication Embargo CoviDefender: Digital Personal Guard For Defending Against COVID19(IEEE, 2021-09-30) Dayarathna, p; Kumara, I; Ranaweera, D; Nawinna, D. P; Karunaratne, G; Wijekoon, JIn late 31 December 2019, a cluster of unexplained pneumonia cases was reported in Wuhan, China [1]. A few days later, the causative agent of this mysterious pneumonia was identified as the new COVID-19 virus. Currently, it has been spreading for more than one and a half years and has lost a huge number of lives all over the world. Most people faced this disaster because of their ignorance, carelessness and lack of updates. By the way most people are in lack of knowledge regarding COVID-19 pandemic, symptoms and what should do to survive from that. Those issues are great problems nowadays. “CoviDefender” is set to offer a solution to this worldwide COVID-19 pandemic problem. This is a new technological solution from a mobile application. “CoviDefender” is a Smart Assistant for Defending against COVID-19 Pandemic. This can be described as a solution to the ignorance and carelessness of the people who have been the main cause of the spread of this epidemic.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 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 Embargo Smart Agriculture Prediction System for Vegetables Grown in Sri Lanka(IEEE, 2021-10-27) Gamage, R; Rajapaksa, H; Sangeeth, A; Hemachandra, G; Wijekoon, J; Nawinna, D. PAgriculture planning plays a dominant role in the economic growth and food security of agriculture-based countries such as Sri Lanka. Even though agriculture plays a vital role, there are still several major complications to be addressed. Some of the major complications are lack of knowledge about yield and price resulting in the farmers selecting crops based on experience. Machine learning has a great potential to solve these complications. To this end, this paper proposes a novel system comprises of a mobile application, SMS (Short Message Service), and API (Application Programming Interface) with yield prediction, price prediction, and crop optimization. Several machine learning algorithms were used for yield and price predictions while a generic algorithm was used to optimize crops. The yield was predicted considering the environmental factors while the price was predicted considering supply and demand, import and export, and seasonal effect. To select the best suitable crops to cultivate, the output of yield and price prediction have been used. Yield prediction has been implemented using elastic net, ridge, and multilinear regression. R2 of yield prediction is varied from 0.74 to 0.89 while RMSE value is between 15.69 and 35.05. Price prediction has been implemented using the algorithms of Gradient Boosting Tree, Random Forest, Facebook Prophet, and R2 is varied from 0.72 to 0.92 while RMSE value is between 26.81 and 140.72. Crop optimization has been implemented using the genetic algorithm.Publication Embargo Data-driven Business Intelligence Platform for Smart Retail Stores(IEEE, 2021-12-09) Eheliyagoda, D. R. M. R. R. D. R. S; Liyanage, T. K. G; Jayasooriya, D. C; Nilmini, D. P. Y. C. A; Nawinna, D. P; Attanayaka, BThe following research paper presents the design and development of a data-driven decision support platform for the effective management of contemporary retail stores in Sri Lanka. This research has four core components, as a solution to the identified shortcomings. These components are Customer Relationship Management (CRM), Supplier Relationship Management (SRM), Price and Demand estimation, and Branch and Employee Performance Monitoring and Rating. The developed system has features such as product replenishment levels, decrease capital movement, reduced material wastage, better item assortment, provide supplier service efficiency, improve employee and branch-level efficiency, and elevated client delivery.This decision support system used Machine Learning (ML) technologies such as LSTM (Long short-term memory) and ARIMA (Autoregressive integrated moving average) models, Regression, Classification, and Associate Rule Mining Algorithms as key technologies. Data were obtained from websites such as Kaggle and other free platforms for the analysis of datasets. The resulting platform was able to perform with an accuracy of over 90% for all four core components with the tested data sets. The system presented would be particularly beneficial for the top management in retail stores to make effective and efficient decisions based on predictions and analyzes provided by the system.Publication Embargo IoT-based Monitoring System for Oyster Mushroom Farming(IEEE, 2021-12-09) Surige, Y. D; Perera, W. S; Gunarathna, P. K; Ariyarathna, K. P; Gamage, N; Nawinna, D. PAgriculture plays a major segment in the economy of Sri Lanka, a developing country. Mushrooms, farming is a popular option among the farmers as it consumes less space and less time for growing while offering a high nutritional value, but most farmers fail to obtain the best yield from their cultivations due to the defects and inefficiencies in the manual methods that are being presently used. This paper presents an ICT solution to avoid inefficiencies in the mushroom farming process. The system is developed focusing one of the popular mushroom type ‘Oyster Mushrooms’. The system offers four functionalities to perform mushroom farming precisely The system offers four functionalities to perform mushroom farming precisely. The Environmental Monitoring function is built with the support of a Long Short Term Memory (LSTM), Harvest time detection function is developed with the support of Convolutional Neural Networks (CNN) with Mobile Net V2 model, The Disease detection and control recommendation function is based on the support of CNN with mobile Net V2 model and the Yield prediction function is developed using the support of Long Short Term Memory (LSTM), The farmer is connected to the system through a mobile application. The system can monitor the environmental factors with an accuracy of 89% and the harvest time can be detected with an accuracy of 92%. Also, the system detects the mushroom diseases with an accuracy of 99% and predicts the monthly yield of a mushroom cultivation with an accuracy of 97%. The intense use of precise farming will eventually lead to high mushroom yields.Publication Open Access IOT-based Monitoring System for Oyster Mushroom Farms in Sri Lanka(KDU IRC, 2022-01-10) Surige, Y. D; Perera, W. S. M; Gunarathna, P. K. M; Ariyarathna, K. P. W; Gamage, N. D. U; Nawinna, D. POyster Mushrooms are a type of a fungus which is very sensitive to the environmental factors and vulnerable to diseases and pest attacks which directly effects local trade and export strength. Mushroom is a climacteric type of food which continues its cycle even after harvesting. The mushroom farming process still uses manual mode such as the identification of diseases uses a farmers eye visually, harvesting of mushrooms are decided based on the visual appearance while the environmental factors are decided based on gut feelings. These methods has its limitations which requires more potential to improve both the quality and capacity of mushroom production. With the advancements of technology, this farming process can be performed with the aid of an IoT device and deep learning model. This research applies Convolutional Neural Networks (CNN) with Mobile Net V2 model to detect mushroom harvest time and any disease spread with an accuracy of 92% and 99% respectively. Long Short-Term memory (LSTM) to analyze the detected environmental factors with an accuracy of 89% and this system predicts the yield of mushroom production with the support of LSTM model with an accuracy of 97%. This developed system which aids mushroom farming activities is connected with the farmers through s mobile applicationPublication Embargo Singlish Sentiment Analysis Based Rating For Public Transportation(IEEE, 2021-01-27) Sharounthan, B; Nawinna, D. P; De Silva, RAs the primary transportation mode in Sri Lanka, Public transportation is tightly attached with the daily life of the people. The important factor in transportation is providing a door to door mobility. This paper presents a study focused on measuring the service quality of public transportation based on the comments and feedbacks provided by the passengers with the aim of producing a better service for users. Comments were gained from social media and were used to produce a comprehensive rating mechanism to rate the transportation service providers. This tool was developed using natural language processing techniques using the data from the Sri Lankan context. With the popularity of Social Media in Sri Lanka, many people use Singlish (Sinhala written using English scripts) for online communication. The rating engine presented in this paper is capable of performing Sentiment analysis on comments given in Singlish Language in the Transportation domain.