ECG-Heartbeat-Classes / Git / Diff of /README.md

Models:

ReneeD/

ECG-Heartbeat-Classes

Downloads: 1

Diff of /README.md [bb35f8] .. [80cc86]

Switch to unified view


# Inter- and intra- patient ECG heartbeat classification for arrhythmia detection: a sequence to sequence deep learning approach

# Paper
 Our paper can be downloaded from the [arxiv website](https://arxiv.org/pdf/1812.07421v2)
 * The Network architecture
 

## Requirements
* Python 2.7
* tensorflow/tensorflow-gpu
* numpy
* scipy
* scikit-learn
* matplotlib
* imbalanced-learn (0.4.3)

## Dataset
We evaluated our model using [the PhysioNet MIT-BIH Arrhythmia database](https://www.physionet.org/physiobank/database/mitdb/)
* To download our pre-processed datasets use [this link](https://drive.google.com/drive/folders/19bDrAqlSGQuNLRmA-7pQRU9R81gSuY70?usp=sharing), then put them into the "data" folder.
* Or you can follow the instructions of the readme file in the "data preprocessing_Matlab" folder to download the MIT-BIH database and perform data pre-processing. Then, put the pre-processed datasets into the "data" folder.

## Train

* Modify args settings in seq_seq_annot_aami.py for the intra-patient ECG heartbeat classification
* Modify args settings in seq_seq_annot_DS1DS2.py for the inter-patient ECG heartbeat classification

* Run each file to reproduce the model described in the paper, use:

```
python seq_seq_annot_aami.py --data_dir data/s2s_mitbih_aami --epochs 500
```
```
python seq_seq_annot_DS1DS2.py --data_dir data/s2s_mitbih_aami_DS1DS2 --epochs 500
```


## Citation
If you find it useful, please cite our paper as follows:

```
@article{mousavi2018inter,
  title={Inter-and intra-patient ECG heartbeat classification for arrhythmia detection: a sequence to sequence deep learning approach},
  author={Mousavi, Sajad and Afghah, Fatemeh},
  journal={arXiv preprint arXiv:1812.07421},
  year={2018}
}
```

## References
 [deepschool.io](https://github.com/sachinruk/deepschool.io/blob/master/DL-Keras_Tensorflow)
 
## Licence 
For academtic and non-commercial usage 


	a/README.md		b/README.md
1	# Inter- and intra- patient ECG heartbeat classification for arrhythmia detection: a sequence to sequence deep learning approach	1	# Inter- and intra- patient ECG heartbeat classification for arrhythmia detection: a sequence to sequence deep learning approach
2		2
3	# Paper	3	# Paper
4	Our paper can be downloaded from the [arxiv website](https://arxiv.org/pdf/1812.07421v2)	4	Our paper can be downloaded from the [arxiv website](https://arxiv.org/pdf/1812.07421v2)
5	* The Network architecture	5	* The Network architecture
6	![Alt text](/images/seq2seq_b.jpg)	6
7
8	## Requirements	7	## Requirements
9	* Python 2.7	8	* Python 2.7
10	* tensorflow/tensorflow-gpu	9	* tensorflow/tensorflow-gpu
11	* numpy	10	* numpy
12	* scipy	11	* scipy
13	* scikit-learn	12	* scikit-learn
14	* matplotlib	13	* matplotlib
15	* imbalanced-learn (0.4.3)	14	* imbalanced-learn (0.4.3)
16		15
17	## Dataset	16	## Dataset
18	We evaluated our model using [the PhysioNet MIT-BIH Arrhythmia database](https://www.physionet.org/physiobank/database/mitdb/)	17	We evaluated our model using [the PhysioNet MIT-BIH Arrhythmia database](https://www.physionet.org/physiobank/database/mitdb/)
19	* To download our pre-processed datasets use [this link](https://drive.google.com/drive/folders/19bDrAqlSGQuNLRmA-7pQRU9R81gSuY70?usp=sharing), then put them into the "data" folder.	18	* To download our pre-processed datasets use [this link](https://drive.google.com/drive/folders/19bDrAqlSGQuNLRmA-7pQRU9R81gSuY70?usp=sharing), then put them into the "data" folder.
20	* Or you can follow the instructions of the readme file in the "data preprocessing_Matlab" folder to download the MIT-BIH database and perform data pre-processing. Then, put the pre-processed datasets into the "data" folder.	19	* Or you can follow the instructions of the readme file in the "data preprocessing_Matlab" folder to download the MIT-BIH database and perform data pre-processing. Then, put the pre-processed datasets into the "data" folder.
21		20
22	## Train	21	## Train
23		22
24	* Modify args settings in seq_seq_annot_aami.py for the intra-patient ECG heartbeat classification	23	* Modify args settings in seq_seq_annot_aami.py for the intra-patient ECG heartbeat classification
25	* Modify args settings in seq_seq_annot_DS1DS2.py for the inter-patient ECG heartbeat classification	24	* Modify args settings in seq_seq_annot_DS1DS2.py for the inter-patient ECG heartbeat classification
26		25
27	* Run each file to reproduce the model described in the paper, use:	26	* Run each file to reproduce the model described in the paper, use:
28		27
29	```	28	```
30	python seq_seq_annot_aami.py --data_dir data/s2s_mitbih_aami --epochs 500	29	python seq_seq_annot_aami.py --data_dir data/s2s_mitbih_aami --epochs 500
31	```	30	```
32	```	31	```
33	python seq_seq_annot_DS1DS2.py --data_dir data/s2s_mitbih_aami_DS1DS2 --epochs 500	32	python seq_seq_annot_DS1DS2.py --data_dir data/s2s_mitbih_aami_DS1DS2 --epochs 500
34	```	33	```
35	## Results	34
36	![Alt text](/images/results.jpg)
37	## Citation	35	## Citation
38	If you find it useful, please cite our paper as follows:	36	If you find it useful, please cite our paper as follows:
39		37
40	```	38	```
41	@article{mousavi2018inter,	39	@article{mousavi2018inter,
42	title={Inter-and intra-patient ECG heartbeat classification for arrhythmia detection: a sequence to sequence deep learning approach},	40	title={Inter-and intra-patient ECG heartbeat classification for arrhythmia detection: a sequence to sequence deep learning approach},
43	author={Mousavi, Sajad and Afghah, Fatemeh},	41	author={Mousavi, Sajad and Afghah, Fatemeh},
44	journal={arXiv preprint arXiv:1812.07421},	42	journal={arXiv preprint arXiv:1812.07421},
45	year={2018}	43	year={2018}
46	}	44	}
47	```	45	```
48		46
49	## References	47	## References
50	[deepschool.io](https://github.com/sachinruk/deepschool.io/blob/master/DL-Keras_Tensorflow)	48	[deepschool.io](https://github.com/sachinruk/deepschool.io/blob/master/DL-Keras_Tensorflow)
51		49
52	## Licence	50	## Licence
53	For academtic and non-commercial usage	51	For academtic and non-commercial usage
54		52