https://github.com/simula-complex/medet
Medical Devices Digital Twins with Meta-Learning
https://github.com/simula-complex/medet
digital-twins healthcare iot-applications meta-learning
Last synced: 5 months ago
JSON representation
Medical Devices Digital Twins with Meta-Learning
- Host: GitHub
- URL: https://github.com/simula-complex/medet
- Owner: Simula-COMPLEX
- Created: 2023-09-30T09:46:52.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2024-09-08T15:13:51.000Z (almost 2 years ago)
- Last Synced: 2025-09-04T19:46:48.194Z (9 months ago)
- Topics: digital-twins, healthcare, iot-applications, meta-learning
- Language: Python
- Homepage:
- Size: 40 KB
- Stars: 4
- Watchers: 2
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Citation: CITATION.cff
Awesome Lists containing this project
README
# MeDeT: Medical Devices Digital Twins Generation with Meta-learning
The MeDeT approach focuses on building, adapting, and operating high-fidelity digital twins (DTs) of medical devices, employing few-shot meta-learning techniques. These medical devices DTs are designed to streamline testing automation for healthcare IoT applications.
MeDeT works in six phases: (i) _Data Generation_ - generates raw data for medical devices, (ii) _Data Preparation_ - preprocesses raw data for training, (iii) _Meta-learning_ - creates meta dataset & taskset, determines model architecture, and trains/fine-tunes with MAML algorithm, (iv) _Build DTs_ - creates model clones, storage, APIs, and JSON objects, (v) _DT Request Handler_ - processes requests from a healthcare IoT application during testing, and (vi) _DTs to Device
Communication_ - establishes DTs communication with medical devices.
This work is a part of the Welfare Technology Solution (WTT4Oslo) project (#309175) funded by the Research Council of Norway.
[//]: # (The repository contains open-source implementation)
## Basic Requirements
* Machine: minimum 16GB RAM and 8-core processor
* OS: MacOS or Windows 10
* IDE: PyCharm
* Python: 3.8 or higher
## Dependencies
* PyTorch: 2.0.1
* learn2learn: 0.2.0
* scikit-learn: 1.3.0
* Pandas: 2.0.3
* Flask: 2.2.3
* Flask-RESTful: 0.3.9