https://github.com/spacesick/tolong-project
A travel emergency app within the scope of Indonesia for Bangkit Academy 2023 capstone project.
https://github.com/spacesick/tolong-project
android expressjs flask native tensorflow
Last synced: 3 months ago
JSON representation
A travel emergency app within the scope of Indonesia for Bangkit Academy 2023 capstone project.
- Host: GitHub
- URL: https://github.com/spacesick/tolong-project
- Owner: spacesick
- License: mit
- Created: 2023-05-31T04:06:25.000Z (about 3 years ago)
- Default Branch: main
- Last Pushed: 2023-07-04T07:37:32.000Z (almost 3 years ago)
- Last Synced: 2025-01-09T05:45:32.466Z (over 1 year ago)
- Topics: android, expressjs, flask, native, tensorflow
- Language: Jupyter Notebook
- Homepage:
- Size: 58.9 MB
- Stars: 2
- Watchers: 1
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# C23-PC725 Capstone Project
## Members
- (MD) A346DKX4282 - Fernandico Geovardo
- (ML) M049DSX0588 - Dhuha Ardha Saputra
- (ML) M181DSX3641 - Vincent Yovian
- (CC) C368DSX2892 - I Ketut Teguh Wibawa Lessmana P. T.
- (CC) C220DSY0626 - Audy Revi Nugraha
- (CC) C303DKY3970 - Vanessa Evlin
## Machine learning model
We create a deep neural network for classifying seven types of injuries that often happen in accidents.
### Dataset info
We collected our Dataset various wound type from kaggle. We got 431 wound type image data in total and there is the distribution.
- Abrasions: 85
- Bruises: 122
- Burns: 59
- Cuts: 50
- Ingrown Nails: 31
- Lacerations: 61
- Stab Wounds: 23
### Architecture
We use the technique of transfer learning by adding multiple layers of fully connected networks on top of an InceptionV3 model pre-trained on the imagenet dataset. We freeze all the layers in the pre-trained InceptionV3 except for the last 12. We saved our best performing model in .h5 format and its weights in a .ckpt file, which so far has reached a validation accuracy of over 0.83 for the injury classification task and over 0.89 for the accident classification task. The dataset, latest checkpoints, and various model formats can be found [here](https://drive.google.com/drive/folders/1JRxoLPASzwMdFGjUG7gDhSLfg6zoRx-t?usp=sharing). Legacy versions of the model can be found [here](https://github.com/dhuhaardha/Model_Capstone).
## Cloud computing and deployment
https://github.com/vanessaevlin/tolong-capstone
## Mobile app
https://github.com/fernandicogeo/mobile-tolong