Research Papers - Dept of Software Engineering

Permanent URI for this collectionhttps://rda.sliit.lk/handle/123456789/1022

Browse

Filters

2021 - 20223

Advanced Search

Filter by

Settings

Subject: search.filters.subject.Natural Language Processing

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    PublicationEmbargo
    Assistant Zone – Homeschooling Assistance System based on Natural Language Processing
    (IEEE, 2022-12-09) Premendran, K; Bopearachchi, S.B.D.D.; Senevirathna, S.D.M.; Giridaran, S; Archchana, K; Ganegoda, D; Thelijjagoda, S
    As a developing country, most people give their highest priority to education. When focusing on building an e-learning platform to improve the knowledge of students and teacher-student interactivity, the pandemic season can be mentioned as the main blocker which highly impacted the education field. Not only by considering the pandemic situation but also by addressing the concerns when it comes to teacher and student evaluation and psychological levels of students who are undergoing different difficulties, the “Home Schooling Assistance System” (Assistant Zone) has been introduced as a solution. The Assistant Zone has been initiated with three unique features which are valuable for both students and teachers. This system analyzes the strengths, weaknesses and evaluates the student performance, suggests study materials to improve themselves, provides solutions to the problems faced by the students, teachers, and parents and measures the performance of teachers based on their students, and recommends learning materials for the low-performing teachers. The Assistant Zone fulfills the targeted problems and introduces the above-mentioned three unique features with the use of Natural Language Processing (NLP) such as the BERT algorithm and Machine Learning models such as the Recurrent Neural Network, Forward Neural Network, and Gaussian Model.
  • Thumbnail Image
    PublicationEmbargo
    WoKnack – A Professional Social Media Platform for Women Using Machine Learning Approach
    (2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT, 2021-12-09) Shanmugarajah, S.; Praisoody, A.; Rakib Uddin, M.D.
    Today’s generation is heavily influenced by social media. However, most users decline to post their abilities on these platforms for a variety of reasons, including security, a lack of basic skills, and a lack of knowledge about the various skill sets. It's understandable that women face many security risks on these platforms. WoKnack is a professional social networking platform dedicated to women. This opens opportunities for women to demonstrate their abilities and teach other women. This paper targets onfunctionalities like registration limited to female users, skill categorization, post verification and privacy preservation. Facial image, identification document and Voice related gender verification done using machine learning approaches to identify thegender before registration. Accuracy of 91% gained during the process. Skills have been categorized using Natural language processing and post verification done based on these categories. Usage of the best accurate algorithm gives an accuracy of 94% during this process. In order to preserve the privacy of users Data anonymization, skill and location clustering have been added to the system.
  • Thumbnail Image
    PublicationEmbargo
    Predicting Diabetes Mellitus Using Machine Learning and Optical Character Recognition
    (IEEE, 2021-04-02) Silva, W. A. J. R; Shirantha, H. M. K; Balalla, L. J. M. V. N; Ranasinghe, R. A. D. V. K; Kuruwitaarachchi, N; Kasthurirathna, D
    Diabetes Mellitus is recognized as a chronic metabolic disease that is characterized by hyperglycemia. As stated by the International Diabetes Federation, the statistics reveal that the incidence of diabetes among adults in Sri Lanka is 8.5%. In hindsight, this indicates that an average of one in every twelve adults in Sri Lanka is at risk of being diagnosed with the disease. However, presently, due to the lack of knowledge or mediums concerning the disease and its symptoms, diabetes often goes undetected which has resulted in 1/3 rd of the constituent population being unaware that they possess the disease. The proposed system aims to implement an application to read and analyze medical reports which will generate data that predicts the probabilities of the contraction and onset of diabetes, with insurance of maximum system efficiency and data credibility. Machine learning classification algorithms and optimization techniques have been used to predict diabetes status with maximum accuracy. To extract data from medical reports Optical Character Recognition, Image Processing, and Natural Language Processing have been used