Faculty of Computing

Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/2684

Browse

Filters

20222

Advanced Search

Filter by

Settings

Author: search.filters.author.Kodagoda, N

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    PublicationEmbargo
    Deep Vision-Data Mining To Find Insights and Visualization in Code Repositories
    (Institute of Electrical and Electronics Engineers, 2022-09-16) Ariyarathne, I.G.P.S; Wimalasuriya, M.K; Abesinghe, N.D.N.S; Edirisinghe, E.A.S.H.; Kodagoda, N; Kasthurirathna, D
    Deep Vision is a code mining system for analyzing and visualizing a repository's codebase so that its users may obtain a sense of the repository's insights. This system will examine codebases and support as many languages as feasible. This system visualizes the file structure, vocabulary and length change rates, comprehensibility and defect rates, etc. It is vital to have a comprehensive grasp of the codebase to manage the program's complexity by calculating multiple factors and presenting them in a descriptive and engaging dashboard to enhance the quality of the software process and the project's controllability. Improved code visualization may help improve code understandability while lowering development costs. In addition, our visualization regions and methodologies are one-of-a-kinds. To get rapid and reliable results, we will create new machine learning models and algorithms for analysis and new categories of a code repository. Our dataset for this research will be GitHub open-source code repositories
  • Thumbnail Image
    PublicationEmbargo
    Comparative Study of Parameter Selection for Enhanced Edge Inference for a Multi-Output Regression model for Head Pose Estimation
    (Institute of Electrical and Electronics Engineers Inc., 2022-11-04) Lindamulage, A; Kodagoda, N; Reyal, S; Samarasinghe, P; Yogarajah, P
    Magnitude-based pruning is a technique used to optimise deep learning models for edge inference. We have achieved over 75% model size reduction with a higher accuracy than the original multi-output regression model for head-pose estimation