/deep-learning-for-time-series-data

The examples showcase two ways of using deep learning for classifying time-series data, i.e. ECG data. The first way is using continuous wavelet transform and transfer learning, whereas the second way is using Wavelet Scattering and LSTMs. The explanations of the code are in Chinese. The used data set can be download on：https://github.com/mathworks/physionet_ECG_data/

OtherNOASSERTION

deep-learning-for-time-series-data

The examples showcase two ways of using deep learning for classifying time-series data, i.e. ECG data. The first way is using continuous wavelet transform and transfer learning, whereas the second way is using Wavelet Scattering and LSTMs. The explanations of the code are in Chinese. The used data set can be download on：https://github.com/mathworks/physionet_ECG_data/

Folder structure:

ECGDeepLearningWithCWT_cn.mlx: ECG Classification with Continuous Wavelet Transform;

ECGWaveletScatteringWithLSTMs_cn.mlx: ECG Classification using Wavelet Scattering and LSTMs;

PrepareSignalData_cn.mlx: Prepare Signal Data for ECG Classification with Continuous Wavelet Transform;

training.mp4: the video shows the training process of ECG Classification with Continuous Wavelet Transform.

The video series (in Chinese) on this topic can be found as follows:

https://www.mathworks.com/videos/series/deep-learning-for-time-series-data.html