MSc in Information Technology

Permanent URI for this collectionhttps://rda.sliit.lk/handle/123456789/2484

Students enrolled in the MSc in Information Technology programme are required to submit a thesis as a compulsory component of their degree requirements. This collection features merit-based theses submitted by postgraduate students specialising in Information Technology. Abstracts are available for public viewing, while the full texts can be accessed on-site within the library.
CC BY-NC-ND 4.0 License
Theses and Dissertations of the Sri Lanka Institute of Information Technology (SLIIT) are licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License .

Browse

Filters

20211

Advanced Search

Filter by

Settings

Author: search.filters.author.Ahmed Akmal, M. A.Has files: Yes

Search Results

Now showing 1 - 1 of 1
  • Thumbnail Image
    PublicationEmbargo
    Biomedical Waste Sorting & Classification Using Deep Learning
    (2021-05) Ahmed Akmal, M. A.
    Biomedical wastes (BMWs) include potentially infectious, sharps, pharmaceuticals and radioactive wastes probably generated by hospitals, vaccination centers, biomedical laboratories, etc. Handling and disposal of biomedical wastes potentially have multiple risk factors. Currently, hospitals and laboratories use color-coded bins to classify and categorize different types of wastes to ease the handling and the disposal process. Sometimes due to human errors these wastes could be miscategorized or misplaced in different bins. In recycling terms this is known as waste contamination. Contaminating the biomedical waste streams causes a huge potential threat to the people who handle them. Computer vision based biomedical waste classification is one of the best ways to prevent these issues. But applying pure computer vision algorithms is much more suitable for small tasks such as pattern recognition, edge detection etc. In order to classify different kinds of biomedical wastes, then convolutional neural networks (CNN) would be a much more suitable choice. This research proposes a deep learning model which accurately classifies several selected biomedical wastes such as syringes, blades and sample collection tubes with a prediction accuracy around 96% on the test dataset. Further the implemented model approximately localizes the biomedical wastes to serve robotics and smart-bin applications.