A Mobile Application Development for Recognising Unused Medical Equipment Using Deep Learning Models
Poor waste management in medical equipment has impacted the environment. It needs a proper management system to reuse and recycle the medical equipment. Hence, a mobile application to recognise images of medical equipment for three entities: NGO/medical centre, member and admin is developed. The pub...
| Main Author: | |
|---|---|
| Format: | Final Year Project / Dissertation / Thesis |
| Published: |
2021
|
| Subjects: | |
| Online Access: | http://eprints.utar.edu.my/4100/ http://eprints.utar.edu.my/4100/1/1701483_FYP_report_%2D_SHI_TING_WONG.pdf |
| _version_ | 1848886076472557568 |
|---|---|
| author | Wong, Shi Ting |
| author_facet | Wong, Shi Ting |
| author_sort | Wong, Shi Ting |
| building | UTAR Institutional Repository |
| collection | Online Access |
| description | Poor waste management in medical equipment has impacted the environment. It needs a proper management system to reuse and recycle the medical equipment. Hence, a mobile application to recognise images of medical equipment for three entities: NGO/medical centre, member and admin is developed. The public can donate their unused medical equipment to NGOs/medical centres. NGOs/medical centres that need medical equipment can request medical equipment from the public through this platform. The admin is responsible for ensuring that the donation process is safe and legal. Three deep learning models, i.e., Inception-v3, ResNet-50, and VGG-16 are trained using transfer learning technique to recognise the medical equipment. These models are also used to overcome limitations faced by traditional machine learning models. The limitations include difficulties in training a new model from scratch, complexity of the image’s features, low recognition accuracy when the size of a data set becomes bigger, and limited cost and time resources. Image data sets for 10 medical equipment, including commodes, wheelchairs, walking frames, blood pressure monitors, breast pumps, thermometers, rippled mattresses, oximeters, crutches, and therapeutic ultrasound machines, are collected for training and testing of the deep learning models. Besides, a grid search method is used to find the best combination of hyperparameters such as optimizer, batch size, epoch number, dropout rate, and learning rate. The deep learning models have successfully addressed and solved the limitations faced by traditional machine learning models. Inception-v3 outperformed the other two models with the highest accuracy of 0.9372 when testing with photos uploaded by the users. |
| first_indexed | 2025-11-15T19:32:45Z |
| format | Final Year Project / Dissertation / Thesis |
| id | utar-4100 |
| institution | Universiti Tunku Abdul Rahman |
| institution_category | Local University |
| last_indexed | 2025-11-15T19:32:45Z |
| publishDate | 2021 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | utar-41002021-06-11T18:14:36Z A Mobile Application Development for Recognising Unused Medical Equipment Using Deep Learning Models Wong, Shi Ting QA76 Computer software Poor waste management in medical equipment has impacted the environment. It needs a proper management system to reuse and recycle the medical equipment. Hence, a mobile application to recognise images of medical equipment for three entities: NGO/medical centre, member and admin is developed. The public can donate their unused medical equipment to NGOs/medical centres. NGOs/medical centres that need medical equipment can request medical equipment from the public through this platform. The admin is responsible for ensuring that the donation process is safe and legal. Three deep learning models, i.e., Inception-v3, ResNet-50, and VGG-16 are trained using transfer learning technique to recognise the medical equipment. These models are also used to overcome limitations faced by traditional machine learning models. The limitations include difficulties in training a new model from scratch, complexity of the image’s features, low recognition accuracy when the size of a data set becomes bigger, and limited cost and time resources. Image data sets for 10 medical equipment, including commodes, wheelchairs, walking frames, blood pressure monitors, breast pumps, thermometers, rippled mattresses, oximeters, crutches, and therapeutic ultrasound machines, are collected for training and testing of the deep learning models. Besides, a grid search method is used to find the best combination of hyperparameters such as optimizer, batch size, epoch number, dropout rate, and learning rate. The deep learning models have successfully addressed and solved the limitations faced by traditional machine learning models. Inception-v3 outperformed the other two models with the highest accuracy of 0.9372 when testing with photos uploaded by the users. 2021 Final Year Project / Dissertation / Thesis NonPeerReviewed application/pdf http://eprints.utar.edu.my/4100/1/1701483_FYP_report_%2D_SHI_TING_WONG.pdf Wong, Shi Ting (2021) A Mobile Application Development for Recognising Unused Medical Equipment Using Deep Learning Models. Final Year Project, UTAR. http://eprints.utar.edu.my/4100/ |
| spellingShingle | QA76 Computer software Wong, Shi Ting A Mobile Application Development for Recognising Unused Medical Equipment Using Deep Learning Models |
| title | A Mobile Application Development for Recognising Unused Medical Equipment Using Deep Learning Models |
| title_full | A Mobile Application Development for Recognising Unused Medical Equipment Using Deep Learning Models |
| title_fullStr | A Mobile Application Development for Recognising Unused Medical Equipment Using Deep Learning Models |
| title_full_unstemmed | A Mobile Application Development for Recognising Unused Medical Equipment Using Deep Learning Models |
| title_short | A Mobile Application Development for Recognising Unused Medical Equipment Using Deep Learning Models |
| title_sort | mobile application development for recognising unused medical equipment using deep learning models |
| topic | QA76 Computer software |
| url | http://eprints.utar.edu.my/4100/ http://eprints.utar.edu.my/4100/1/1701483_FYP_report_%2D_SHI_TING_WONG.pdf |