Research Publications
Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/4194
This main community comprises five sub-communities, each representing the academic contribution made by SLIIT-affiliated personnel.
Browse
60 results
Filters
Advanced Search
Filter by
Settings
Search Results
Publication Open Access COVID-19 symptom identification using Deep Learning and hardware emulated systems(Elsevier, 2023-06-28) Liyanarachchi, R; Wijekoon, J; Premathilaka, M; Vidhanaarachchi, SThe COVID-19 pandemic disrupted regular global activities in every possible way. This pandemic, caused by the transmission of the infectious Coronavirus, is characterized by main symptoms such as fever, fatigue, cough, and loss of smell. A current key focus of the scientific community is to develop automated methods that can effectively identify COVID-19 patients and are also adaptable for foreseen future virus outbreaks. To classify COVID-19 suspects, it is required to use contactless automatic measurements of more than one symptom. This study explores the effectiveness of using Deep Learning combined with a hardware-emulated system to identify COVID-19 patients in Sri Lanka based on two main symptoms: cough and shortness of breath. To achieve this, a Convolutional Neural Network (CNN) based on Transfer Learning was employed to analyze and compare the features of a COVID-19 cough with other types of coughs. Real-time video footage was captured using a FLIR C2 thermal camera and a web camera and subsequently processed using OpenCV image processing algorithms. The objective was to detect the nasal cavities in the video frames and measure the breath cycles per minute, thereby identifying instances of shortness of breath. The proposed method was first tested on crowd-sourced datasets (Coswara, Coughvid, ESC-50, and a dataset from Kaggle) obtained online. It was then applied and verified using a dataset obtained from local hospitals in Sri Lanka. The accuracy of the developed methodologies in diagnosing cough resemblance and recognizing shortness of breath was found to be 94% and 95%, respectively.Publication Embargo Effects of the Organizational Knowledge Management Systems on Psychological Well-Being Among Employees in Private Large-Scale IT Organizations in Sri Lanka(IEEE, 2023-06-12) Aratthanage, K; Wijekoon, JThe goal of this study basically focuses on evaluating the Organizational Knowledge Management Systems (KMS) and their impact on psychological well-being among employees in selected large-scale private IT organizations in Sri Lanka. It evaluates Knowledge Management Systems quality dimensions, KMS adoption of users, and psychological well-being. Knowledge Management is an essential part in IT industry. Gaining domain knowledge from one starting point to sharing knowledge among organizations is a very complex process, therefore, different types of Knowledge Management systems are implemented within IT organizations. There are several quality dimension factors introduced to determine better knowledge management systems. This research evaluates eight quality dimensions against four psychological aspects. In this study, statistical analysis was used to determine the statistically significant levels, correlations and relationships between the independent and dependent variables. Ultimately the results can be used to improve the Human-centered Knowledge Management System's design approach with balanced employee psychological well-being. For further improvements, the results can be used to build interactive knowledge management software-based solutions.Publication Embargo Effectiveness of Using Radiology Images and Mask R-CNN for Stomatology(IEEE, 2022-12-09) Jayasinghe, H; Pallepitiya, N; Chandrasiri, A; Heenkenda, C; Vidhanaarachchi, S; Kugathasan, A; Rathnayaka, K; Wijekoon, JDental health-related disorders have proliferated worldwide due to the excessive intake of fast food and sugary foods, which was followed by bad oral hygiene practices. The cost of dental examinations may change based on how critical the condition is, regardless of whether they are not regular. For a person, diagnosing an oral health problem, particularly locating the disease’s underlying cause, can be challenging. To properly diagnose and treat such conditions, advanced dental diagnostic techniques may be necessary. By offering convenience and enhancing their oral health knowledge, the system seeks to serve as a prediction tool that regular people can utilize to detect potential tooth illnesses at an early stage. It is encompassed as a mobile application where a Mask R-CNN model is used in the core that accepts a dental radiograph as the input. The trained model will be able to identify diseases related to the bone and teeth. Based on the performance evaluations, the accuracy of the results that are obtained in tooth type, restoration quality, dental caries, and periodontal disease identification falls in the range of 75%-80%.Publication Embargo Smart Driver Assistance for Traffic Sign, Pothole, Vehicle Malfunction, and Accident Detection(IEEE, 2022-11-30) Vithanage, W; Madushan, H; Madushanka, T; Lokuliyana, T; Wijekoon, J; Chandrasiri, SReducing ever-increasing road accidents is a big concern worldwide. Sri Lanka had the highest rate of road fatalities in the past few years, rapidly increasing daily. Among many factors, traffic signs, potholes, and vehicle mechanical malfunctions significantly impact road safety. Most accidents result from a lack of awareness, ignorance, and negligence of drivers. While many high-end vehicles are equipped with technologies such as intelligent road sign recognition systems and air suspension systems, most cars in the market only come with basic driving instruments. Therefore, there is a need for a universal driver assistance system that can be plugged into any vehicle to assist drivers in minimising road casualties. To this end, this study discusses Neural Networks, Machine Learning and IoT technologies to develop an intelligent system that is capable of detecting and analysing road signs, road potholes, vehicles’ internal system malfunctions, and road accidents and notifying drivers in real-time and inform authorities such as hospitals and police stations to be aware of accidents to minimise further casualties. This portable device is based on a Raspberry Pi microprocessor. It uses a web camera, an onboard diagnostic tool (OBD) and an accelerometer to process traffic sign footages, vehicle sensor data and movement data of the vehicle. Yielded results showed that the proposed system was 90% accurate.Publication Embargo IoT-Based Disease Diagnosis and Knowledge Dissemination System for Coconut Plants(IEEE, 2022-12-09) Ekanayaka, S; Anawaratne, A; Ayeshmanthi, T; Dilanka, M; Aratchige, N.S.; Wijekoon, J; Lunugalage, DThe coconut plant plays a significant role in the Sri Lankan domestic and export industries. It is a major livelihood crop of which more than 65% is consumed locally. However, most coconut trees suffer from various pest and disease outbreaks, which have an impact on the economy of coconut production. Out of them, infestations of Whiteflies, Plesispa Beetle, and Red Palm Weevil are destructive to the coconut plant at different stages, so early detection of those infections is a major task. To this end, the paper describes an IoT-based prediction system for detecting and classifying infections in the coconut industry.; Internet of Things (IoT), image processing, audio processing, and deep learning were used as techniques to utilize for the detection of those infestations. Audio and Image-capturing devices are developed to collect audio and image data. Additionally, there’s a knowledge dissemination system to identify the main coconut pests in Sri Lanka and share this knowledge with farmers. With the audio and image datasets gathered from the mentioned diseases, performance evaluation of the Deep Learning (DL) models revealed that the accuracy of the identifications of Red Palm Weevil infestation Plesispa beetle and Whitefly infestations is 88, 96, and 98% respectively.Publication Embargo AI-Based Child Care Parental Control System(IEEE, 2022-12-09) Jayasekara, U; Maniyangama, H; Vithana, K; Weerasinghe, T; Wijekoon, J; Panchendrarajan, RDue to the prevalence of the COVID-19 epidemic around the globe, children were compelled to engage in remote learning through online platforms, hence mobile phone has become one of their predominant devices. Mobile device with Internet access offers a major outlet for education, entertainment, and social connection, but this combination can lead to several significant bad sequences such as online exploitation, harmful addictions, and other negative impacts of online social networking. To address harmful effects, parental controls are becoming more crucial, yet Sri Lankan parents are less aware of this. Consequently, this study proposes a parental control system to monitor their child’s activities. Android, Microsoft Azure, Java, Python, OpenCV, MySQL, and FastAPI are among the most prominent technologies utilized in the proposed application’s development. The suggested approach focuses primarily on the Sri Lankan context and aims to enhance parental digital literacy while safeguarding children from cyber threats. Yielded results showed the proposed mobile application for the identification of toxic words, drugs & alcohol content, game character images, and Instagram Sinhala comments severity as 94%, 95%, 97%, and 55% respectively in controlled experiments.Publication Embargo A Geophone Based Surveillance System Using Neural Networks and IoT(IEEE, 2020-12-10) Hettigoda, S; Jayaminda, C; Amarathunga, U; Thaha, S; Wijesundara, M; Wijekoon, JSecuring our assets and properties from intruders and thieves has become increasingly challenging as intruders become technology aware. The most common approach to monitor physical assets is CCTV. However, this approach has a number of technical limitations in addition to the cost. The CCTV camera location is visible to the intruder and intruder can also identify possible blind spots in the CCTV coverage area. In this paper, we introduce a novel method to secure physical assets using Geophones, Neural Networks, and IoT Platforms. This can either be used stand alone or to complement existing CCTV systems. In this approach, the system monitors vibrations on ground to detect intruders. We have achieved up to 93.90% overall accuracy for person identification. The system is invisible to intruders and covers a large area with a smaller number of nodes, thereby reducing the cost of ownership.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 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.