Git Product home page Git Product logo

ecg-tcn's Introduction

Copyright (C) 2021 ETH Zurich, Switzerland. SPDX-License-Identifier: Apache-2.0. See LICENSE file for details.

Authors: Thorir Mar Ingolfsson, Xiaying Wang, Michael Hersche, Alessio Burrello, Lukas Cavigelli, Luca Benini

EEG-TCN

This project provides the experimental environment used to produce the results reported in the paper ECG-TCN: Wearable Cardiac Arrhythmia Detection with a Temporal Convolutional Network available on arXiv. If you find this work useful in your research, please cite

@INPROCEEDINGS{9458520,
  author={Ingolfsson, Thorir Mar and Wang, Xiaying and Hersche, Michael and Burrello, Alessio and Cavigelli, Lukas and Benini, Luca},
  booktitle={2021 IEEE 3rd International Conference on Artificial Intelligence Circuits and Systems (AICAS)}, 
  title={ECG-TCN: Wearable Cardiac Arrhythmia Detection with a Temporal Convolutional Network}, 
  year={2021},
  volume={},
  number={},
  pages={1-4},
  doi={10.1109/AICAS51828.2021.9458520}}

Getting started

Prerequisites

Also the dataset ECG5000 needs to be downloaded and put into the /data folder. It is available on here

Installing

Navigate to ECG-TCN's main folder and create the environment using Anaconda:

$ conda env create -f ECG-TCN.yml -n ECG-TCN

Usage

We provide the code to quantize the ECG-TCN model in the file nemo_quantization.py there we train, quantize and deploy the network to be used by DORY. We also provide code to quantize the same model with Tensorflow in the file tensorflow_quantization.py there we train, quantize and deploy the network to be used either straight on an MCU using TFlite as a library or using X-CUBE-AI.

Under /utils you find the data loading and model making files. Please note that because of the stochastic nature of training with GPUs it's very hard to fix every random variable in the backend. Therefore to reproduce the same or similar models one might need to train a couple of times in order to get the same highly accurate models we present.

License and Attribution

Please refer to the LICENSE file for the licensing of our code.

ecg-tcn's People

Contributors

thoriri avatar

Stargazers

Jason Yan avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.