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

Filters

2018 - 201912020 - 20213

Advanced Search

Filter by

Settings

Has files: YesSubject: search.filters.subject.Reinforcement Learning

Search Results

Now showing 1 - 4 of 4
  • Thumbnail Image
    PublicationEmbargo
    English Language Trainer for Non-Native Speakers using Audio Signal Processing, Reinforcement Learning, and Deep Learning
    (IEEE, 2021-12-02) Jeewantha, H. C. R.; Gajasinghe, A. N; Rajapaksha, T. N; Naidabadu, N. I; Kasthurirathna, D.; Karunasena, A.
    Lack of basic proficiency and confidence in writing and speaking in English is one of the major social problems faced by most non-native English speakers. Although the general adult literacy rate in Sri Lanka is above average by world standards, the English literacy rate is just 22% among the Sri Lankan adult population. Many individuals face setbacks in achieving their career and academic goals due to these language barriers. In a world where English has become a compulsory requirement to pursue higher education, career development, and performing day-to-day activities, "English Buddy" is a software solution developed to enhance the English learning experience of individuals in a more personalized and innovative way. The system provides an all-in-one solution while filling major research and market gaps in existing solutions in the e-learning domain. The system consists of a personalized learning environment, automated pronunciation error detection system, automated essay evaluation process, automated descriptive answer evaluation component based on semantic similarity, and real-time course content rating system. English Buddy is implemented using state-of-the-art technologies such as Audio Signal Processing, Reinforcement Learning, Deep Learning, and NLP. The LSTM, Sentiment Analysis, and Siamese network models have gained accuracy scores of 0.93, 0.92, and 0.81 respectively. Further, the UAT results proved that the personalized recommendations and pronunciation error detection processes are accurate and reliable. This research has been able to overcome the limitations of most existing solutions that follow traditional approaches and provide better results compared to the recent studies in the e-learning research domain.
  • Thumbnail Image
    PublicationEmbargo
    Optimization of Volume & Brightness of Android Smartphone through Clustering & Reinforcement Learning (“RE-IN”)
    (IEEE, 2018-12-21) Abeywardhane, J. S. D. M. D. S; de Silva, E. M. W. N; Gallanga, I. G. A. G. S; Rathnayake, L. N; Wickramaratne, C. J; Sriyaratna, D
    Smartphone has become one of the most significant piece of technology that humans were able to produce in the 21st century. It has become our life companion; hence the features of the smartphones have developed in advance. But, some features may not work as expected. For instance, auto brightness changing feature is now actualized with smartphones, yet we alter the brightness according to our preference. In the same manner, considering the volume of our smartphone it doesn't change according to our preference subsequently. This research will develop a mobile application (“RE-IN”) to overcome this issue for Android smartphones. Since android smartphones allow accessing its hardware layer we can roll out improvements as we need, yet Apple doesn't permit to proceed with its hardware layer thus hard to do this for the iPhone users. By utilizing the RE-IN mobile application users may have to encounter an optimal brightness and volume on their Android smartphones agreeing the present condition of smartphone users are in. RE- IN application will keep running as a background application on an Android smartphone. When the client changes the brightness and volume as his/her preference. At that point, the reinforcement learning algorithm over the time application will distinguish how to control user's smartphone's brightness and volume relying upon the user's circumstance. When client surrounding is loaded with light, the framework will modify brightness for his/her preference. The client doesn't need to do this manually. Moreover when the client is at the too much boisterous place all of a sudden gets a call from someone; client's smartphone amplifier volume will change consequently and solaces the client's discussion. To actualize this framework it is relied upon to reinforcement learning and machine learning as the research area. By finishing the literature review, research group unable to find an Android mobile application which automates the process of volume and brightness of the Android smartphone as per user preference. After using the reinforcement learning algorithm to learn the data set then distribute the process, using client-server model and come up with a clustering algorithm(K-means algorithm) to share common attributes by considering geographical area which they live in and variables like age, gender, how they interact with the device etc. In addition, this system will identify abnormal behaviors of some particular users. RE-IN will identify the users who are keeping volume level to the highest and brightness level to its maximum and notify them in advance.
  • Thumbnail Image
    PublicationEmbargo
    Smart Intelligent Floriculture Assistant Agent (SIFAA)
    (2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT, 2021-12-09) Samaratunge, U.S.S.; Amarasinghe, D.H.L.; Kirindegamaarachchi, M.C.; Asanka, B.L.
    Technology has become a vital aspect for various functional purposes throughout the world and some industries like floriculture have not adapted technology to solve and facilitate currently facing problems and provide the supply to the demand. Consequently, we have identified and implemented a solution that will address major aspects of such industry barriers. To address these major aspects we proposed a system Smart Intelligent Floriculture Assistant Agent (SIFAA), which uses expert knowledge with solutions and guideline such as identify diseases based on deep learning techniques. It also suggests remedies for diseases based on the expert knowledge, recommend best products for customers by using Reinforcement Learning (RL) technique, motivate cultivators by using demand forecasting, and apply feature engineering by using Linear Regression (LR) and ensemble advance LightGBM Regressors techniques.
  • Thumbnail Image
    PublicationEmbargo
    Cognitive Rehabilitation based Personalized Solution for Dementia Patients using Reinforcement Learning
    (IEEE, 2021-04-15) Rathnayaka, M. H. K. R; Watawala, W. K. C. R; Manamendra, M. G; Silva, S. R. R. M; Kasthurirathna, D; Jayalath, T
    Dementia is one of the most challenging health problems faced globally with the increase in the ageing population. The estimated current prevalence of dementia is 47.5 million worldwide. This number will nearly double in every 20 years globally. Dementia is basically, a syndrome which cannot be cured by medicine, but non-pharmacological therapy can be used to treat Dementia patients, this is known as Cognitive Rehabilitation Therapy. According to the recommendations of the doctors, the use of a brain training application could be better than traditional approaches. There are number of Brain training mobile applications in the world that could be useful in improving human concentration, attention and all sorts of brain activities but there isn’t any customized software solution that has games or activities. Patients can be in different stages of Dementia. Therefore, for a better cognitive rehabilitation they need personalized therapies with the games and activities. Accordingly, developing this application is an actual global requirement for dementia patients. The world is evolving with new technologies and this application includes the mind games based on such technologies as Reinforcement Learning which predict the next level for patients based on user behavior. And there are some activities on speech recognition using Deep Neural Network as well. Patients, caregivers and doctors can view the progress reports of the patients. All the games have designed along with the supervision and recommendation from a Consultant Psychiatrist in Sri Lanka. The main objective is to help the Dementia patients in cognitive rehabilitation to improve the quality of life with best suited personalized games and activities.