physiossl 0.0.1a2

PhysioSSL: A Python Toolbox for Physiological Time-series Representation Learning

PhysioSSL: A Python Toolbox for Physiological Time-series Representation Learning

Introduction

Installation

Install from PyPi:

pip install physiossl

or install via the GitHub link:

pip install git+https://github.com/larryshaw0079/PhysioSSL

Getting Started

Implemented Algorithms

Algo	Title	Year	Ref
TCL			[1]
RP			[2]
TS			[2]
CPC
Moco
SimCLR
DPC
DPCM
TripletLoss
DCC
TNC
TSTCC
CoSleep		2021

Supported Datasets

Sleep Stage Classification

Emotion Recognition

Human Activity Recognition

Citing

@misc{qfxiao2021physiossl,
  author =       {Qinfeng Xiao},
  title =        {PhysioSSL: A Python Toolbox for Physiological Time-series Representation Learning},
  howpublished = {\url{https://github.com/larryshaw0079/PhysioSSL}},
  year =         {2021}
}

Reference

[1] Hyvarinen, Aapo and Morioka, Hiroshi,. (2016). Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICA. Advances in Neural Information Processing Systems.

[2] Banville, H., Chehab, O., Hyvarinen, A., Engemann, D., & Gramfort, A. (2020). Uncovering the structure of clinical EEG signals with self-supervised learning. Journal of neural engineering, 10.1088/1741-2552/abca18. Advance online publication. https://doi.org/10.1088/1741-2552/abca18