raphaelvallat/yasa

YASA (Yet Another Spindle Algorithm): a Python package to analyze polysomnographic sleep recordings.

What it solves

YASA provides a comprehensive set of tools for analyzing sleep data, specifically polysomnography (PSG) and EEG recordings. It automates the tedious process of sleep staging and detects specific brain wave patterns associated with sleep, reducing the manual effort required for sleep research and clinical analysis.

How it works

The toolbox operates on EEG data to perform several key tasks:

  • Automatic Sleep Staging: It uses algorithms to categorize sleep stages automatically from PSG data.
  • Event Detection: It identifies specific neurological events such as sleep spindles, slow-waves, and rapid eye movements.
  • Signal Processing: It includes tools for artefact rejection and spectral analyses, such as bandpower and phase-amplitude coupling.
  • Data Analysis: It processes hypnograms to calculate sleep statistics and stage transitions.

Who it’s for

It is designed for researchers and clinicians who work with polysomnography and EEG data to study sleep patterns and brain activity.

Highlights

  • Automatic sleep staging of polysomnography data.
  • Detection of sleep spindles, slow-waves, and rapid eye movements.
  • Artefact rejection for single or multi-channel EEG data.
  • Advanced spectral analyses including 1/f slope and phase-amplitude coupling.
  • Hypnogram analysis for sleep statistics and visualization.

Related

  • Project
    YuChuang1205/PAL

    A progressive active learning framework for infrared small target detection that enables models to achieve high performance using only single-point supervision instead of full masks.

  • Project
    l3p-cv/lost

    A flexible, web-based framework for collaborative image annotation that supports semi-automatic pipelines to speed up the labeling of machine learning datasets.

  • Project
    pySTEPS/pysteps

    A Python library for probabilistic precipitation nowcasting that uses optical flow and stochastic generators to create short-term ensemble prediction systems.

  • Project
    mudler/locate-anything.cpp

    A C++/ggml inference port of NVIDIA's LocateAnything-3B that enables fast, open-vocabulary object detection on CPU and GPU without a Python runtime.