Anomaly-Detection-in-Time-Series-with-Triadic-Motif-Fields

KO | EN

gitlite — search

#react #typescript #machine-learning #rust #linux #docker #nodejs #java #awesome #kubernetes #awesome-list #pytorch #mcp #open-source

Anomaly-Detection-in-Time-Series-with-Triadic-Motif-Fields

(★ 37)

Anomaly Detection in Time Series with Triadic Motif Fields and Application in Atrial Fibrillation ECG Classification

Anomaly-Detection-in-Time-Series-with-Triadic-Motif-Fields 최신버젼 다운로드

최종 버전 다운로드 (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Anomaly Detection in Time Series with Triadic Motif Fields and Application in Atrial Fibrillation ECG Classification

[![arXiv](https://img.shields.io/badge/arXiv-2012.04936-b31b1b.svg)](https://arxiv.org/abs/2012.04936) [![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/ydup/bokeh/master?urlpath=/proxy/5006/bokeh-app) [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/anomaly-detection-in-time-series-with-triadic/atrial-fibrillation-detection-on-physionet)](https://paperswithcode.com/sota/atrial-fibrillation-detection-on-physionet?p=anomaly-detection-in-time-series-with-triadic)

Author: [Yadong Zhang](https://github.com/ydup) and Xin Chen

Paper: [![arXiv](https://img.shields.io/badge/arXiv-2012.04936-b31b1b.svg)](https://arxiv.org/abs/2012.04936)

Online demo: [![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/ydup/bokeh/master?urlpath=/proxy/5006/bokeh-app)

### Modules

Module | Path | Note | Default Settings
--- | --- | --- | ---
Basic | 1. [_lib_](lib/) 2. [_data_](data/) 3. [_model_](model/) | 1. Basic functions of the project. 2. Dataset processing. 3. Saved tail model weights. | 1. - 2. no filter, z-normalization 3. MLP model
Classification | 1. [_extractor_](extractor/) 2. [_classifier_](classifier/) | 1. Features extraction of TMF images based on transfer learning. 2. Feature vectors classification to AF and non-AF probabilities. | 1. VGG16, map-reduce use ```10``` nodes and ```5``` mpisize. 2. -
Evaluation | 1. [_length\_effect_](length_effect/) | 1. Evaluate the trained model on varying-length ECG signals. | 1. VGG16-MLP, map-reduce use ```10``` nodes and ```5``` mpisize.
App | 1. [_pyQT app_](app/) 2. [_bokeh app_](https://github.com/ydup/bokeh) | 1. Local app for classification and interpretation. 2. Web server for interpretation. | VGG16-MLP

### Structures of Parallel Codes (mpi)

[_extractor_](extractor/) and [_length\_effect_](length_effect/) are parallelized on the linux clustering. (map-reduce)
+ ```.py```: main code.
+ ```.sh```: script for single submission to the pbs queue.
+ ```map*.py```: map the tasks to multi-nodes and mpi. 
+ ```reduce*.py```: collect the results from the finished tasks.

### Guidelines of APP

Features | Classification | Visualization | Interactive | Remote | Local 
--- | --- | --- | --- |--- |--- 
[pyQT app](app/) | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :x: | :heavy_check_mark: 
[bokeh app](https://github.com/ydup/bokeh) | :x: (available in future) | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark:

#### [pyQT app](app/)

1. Start page (click ```start```)
    + Start button
    + Process bar & status
![hello](https://raw.githubusercontent.com/ydup/Anomaly-Detection-in-Time-Series-with-Triadic-Motif-Fields/main/docs/app_start.png)
2. Main page (from top to bottom)
    + Time series with label
    + Symmetrized Grad-CAM of AF and its predicted probability
    + Symmetrized Grad-CAM of non-AF and its predicted probability
    + Sliders of ```time index``` and ```delay``` to adjust the triadic time series motifs
        - Triad (red) in time series is corresponding to the cross (white) in two Symmetrized Grad-CAM images
        - The text with red background indicates the predicted type.
![main](https://raw.githubusercontent.com/ydup/Anomaly-Detection-in-Time-Series-with-Triadic-Motif-Fields/main/docs/app_main.png)
#### [bokeh app](https://github.com/ydup/bokeh)
![bokeh](https://raw.githubusercontent.com/ydup/Anomaly-Detection-in-Time-Series-with-Triadic-Motif-Fields/main/docs/app_bokeh.png)

### [Requirements](./requirements.txt)
Python 3.6:
```
matplotlib
mpi4py==3.0.3
numba==0.50.1
scikit-learn==0.23.0
scipy==1.5.2
tensorflow==1.14.0
opencv-python
tqdm
PyQT5
```

### Citation

Cite our work with:
```latex
@misc{zhang2020anomaly,
      title={Anomaly Detection in Time Series with Triadic Motif Fields and Application in Atrial Fibrillation ECG Classification}, 
      author={Yadong Zhang and Xin Chen},
      year={2020},
      eprint={2012.04936},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}
```

Anomaly-Detection-in-Time-Series-with-Triadic-Motif-Fields

Anomaly-Detection-in-Time-Series-with-Triadic-Motif-Fields 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Anomaly-Detection-in-Time-Series-with-Triadic-Motif-Fields

Anomaly-Detection-in-Time-Series-with-Triadic-Motif-Fields 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README