Research Papers - Dept of Information Technology

Permanent URI for this collectionhttps://rda.sliit.lk/handle/123456789/593

Browse

Filters

2019 - 201912020 - 20224

Advanced Search

Filter by

Settings

Author: search.filters.author.Kasthurirathna, D

Search Results

Now showing 1 - 5 of 5
  • Thumbnail Image
    PublicationEmbargo
    Smart Device and Tracer to Overcome COVID-19 Using Digital Technology for Better Protection
    (IEEE, 2022-12-09) Avinash, K; Dithmal, C; Wijerathne, P; Kaushan, N; De Silva, H; Kasthurirathna, D
    A number of nations have experienced challenging circumstances as a result of the coronavirus disease (COVID-19), which has turned into a global pandemic. As a result of the social changes it has caused, this crisis will also have an impact on future generations. With the help of this technology, health organizations can quickly locate individuals who are infected with COVID-19 and provide them with medical care. The objective of this work is to develop a COVID-19 Tracer that is capable of COVID-19 detection and mitigation. The goal of this research is to reduce the number of COVID-19-related fatalities in Sri Lanka while also enabling users who are infected with the disease to access appropriate care and hospitalization. This software uses digital technologies to acquire accurate data and provide precise interpretations based on that data. Through the proposed method, patients can be treated using the application to get a precise diagnosis of their disease, maintaining social distance, stabilizing the mental level of the patient through AI, predicting the epidemic, providing COVID-19 vaccinations, as well as ambulance services through this application. Using every preventative measure available, this mobile application has now been developed to safeguard against COVID-19.
  • Thumbnail Image
    PublicationEmbargo
    Graph Neural Network based Child Activity Recognition
    (IEEE, 2022-08-25) Mohottala, S; Samarasinghe, P; Kasthurirathna, D; Abhayaratne, C
    This paper presents an implementation on child activity recognition (CAR) with a graph convolution network (GCN) based deep learning model since prior implementations in this domain have been dominated by CNN, LSTM and other methods despite the superior performance of GCN. To the best of our knowledge, we are the first to use a GCN model in child activity recognition domain. In overcoming the challenges of having small size publicly available child action datasets, several learning methods such as feature extraction, fine-tuning and curriculum learning were implemented to improve the model performance. Inspired by the contradicting claims made on the use of transfer learning in CAR, we conducted a detailed implementation and analysis on transfer learning together with a study on negative transfer learning effect on CAR as it hasn’t been addressed previously. As the principal contribution, we were able to develop a ST-GCN based CAR model which, despite the small size of the dataset, obtained around 50% accuracy on vanilla implementations. With feature extraction and fine tuning methods, accuracy was improved by 20%-30% with the highest accuracy being 82.24%. Furthermore, the results provided on activity datasets empirically demonstrate that with careful selection of pre-train model datasets through methods such as curriculum learning could enhance the accuracy levels. Finally, we provide preliminary evidence on possible frame rate effect on the accuracy of CAR models, a direction future research can explore.
  • Thumbnail Image
    PublicationOpen Access
    Agro-Genius: Crop Prediction Using Machine Learning
    (https://ijisrt.com/agrogenius-crop-prediction-using-machine-learning, 2019-10) Gamage, M. P. A. W; Kasthurirathna, D; Paresith, M. M; Thayakaran, S; Suganya, S; Puvipavan, P
    This paper present a way to aid farmers focusing on profitable vegetable cultivation in Sri Lanka. As agriculture creates an economic future for developing countries, the demand of modern technologies in this sector is higher. Key technologies used for this problem are Deep Learning, Machine Learning and Visualization. As the product, an android mobile application is developed. In this application the users should input their location to start the prediction process. Data preprocessing is started when the location is received to the system. The collected dataset divided into 3 parts. 80 percent for training, 10 percent for testing and 10 percent for validation. After that the model is created using LSTM RNN for vegetable prediction and ARIMA for price prediction. Finally, for given location profitable crop and predicted future price of vegetables are shown in the application. Other than the prediction, optimizing for multiple crop sowing according to the user requirements and visualizing cultivation and production data on map and graphs are also given in the application. This paper elaborates the procedure of model development, model training and model testing.
  • Thumbnail Image
    PublicationEmbargo
    Evolution of Push-Communication Towards the Rich Web-Based Applications
    (Springer, Cham, 2020-11-05) Dissanayake, N. R; Kasthurirathna, D; Jayalal, S
    Push Communication is an integral requirement in modern RichWebbased Applications, to implement the features like push notifications or real-time updates. Aspects like push-communication related concepts and their development technologies – focusing on the roots of them and the rationale behind their advancements – are not collectively discussed in any available forum. An intensive literature survey was conducted on identifying the very roots of the push-communication and its evolution towards understanding the abstract architectural formalism of the push-communication in Rich Web-based Applications, also focusing on the aforementioned aspects. We collected and documented the literature regarding the evolution of the push-communication, for archiving and also for reviewing and comparing the reasoning behind the improvements of them over time. We also tried to capture the knowledge to answer some important questions like is push-communication important and how difficult to integrate push-communication into the Rich Web-based Applications? We expect to study the artefacts identified through the survey to identify the abstract characteristics of the push-communication to realize the integration of the push-communication into the Rich Web-based Applications in the form of Delta-Communication.
  • Thumbnail Image
    PublicationEmbargo
    Computer Vision and NLP based Multimodal Ensemble Attentiveness Detection API for E-Learning
    (IEEE, 2021-04-21) Wijeratne, M. D; Lakmal, R. H. G. A; Geethadhari, W. K. S; Athalage, M. A; Gamage, A; Kasthurirathna, D
    Attention is the fundamental element of effective learning, memory, and interaction. Learning however, with the evolvement of technologies in the modern digital age, has surpassed traditional learning systems to more convenient online or e-learning systems. Nevertheless, unlike in the traditional learning systems, attention detection of a student in an e-learning environment remains one of the barely explored areas in Human Computer Interaction. This study proposes a multimodal ensemble solution to detect the level of attentiveness of a student in an e-learning environment, with the use of computer vision, natural language processing, and deep learning to overcome the barriers in identifying user attention in e-learning. The proposed multimodal captures, processes, and predicts user attentiveness levels of individual students, which are subsequently aggregated through an ensemble model to derive an overall outcome of better accuracy than individual model outcomes. The final outcome of the ensemble model produces a range of percentages, within which the attentiveness level of the student lies during a single online lesson. This range is consequently delivered to the users through an Application Programming Interface.