gabrock94 / pysiology

A Python package for physyological's signals processing

PySiology

Introduction

PySiology is a Python package used to analyze Physiological signals. With pysiology you can easily analyze:

• Electromyographic signals
• Electrocardiographic signals
• Electrodermal activity signals

Installation

PySiology can be installed using pip:

pip install pysiology

or downloading / cloning the repository and, from the root folder of the project, running:

python setup.py install

Updating the package

To update the package via pip, you can use:

pip install --user --upgrade pysiology

Documentation

You can check the full documentation here: https://pysiology.rtfd.io

WARNING

Sample data are not downloaded when using Pip. Please download the samples manually from the repository (https://github.com/Gabrock94/Pysiology/tree/master/share/data) and load them using

import pickle

with open("path/to/sample/data.pkl",'rb') as f:
          data = pickle.load(f)

Example

import matplotlib.pyplot as plt #used for visualization purposes in this tutorial.

import pysiology
print(pysiology.__version__)


ECG = pysiology.sampledata.loadsampleECG() #load the sample ECG Signal
EMG = pysiology.sampledata.loadsampleEMG() #load the sample EMG Signal
GSR = pysiology.sampledata.loadsampleEDA() #load the sample GSR Signal

sr = 1000 #samplerate in Hz

#We can define the event in the way we prefer. 
#In this example I will use a 2 x nEvent matrix, containing the name of the event and the onset time.
events = [["A",10],
          ["B",20]]
eventLenght = 8 #lenght in seconds we want to use to compute feature estimation
results = {} #we will store the results in a dict for simplicity.
for event in events:
    startSample = sr * event[1] #samplerate of the signal multiplied by the onset of the event in s
    endSample = startSample + (sr * eventLenght) #Final sample to use for estimation
    results[event[0]] = {} #initialize the results
    results[event[0]]["ECG"] = pysiology.electrocardiography.analyzeECG(ECG[startSample:endSample],sr) #analyze the ECG signal
    results[event[0]]["EMG"] = pysiology.electromyography.analyzeEMG(EMG[startSample:endSample],sr) #analyze the EMG signal
    results[event[0]]["GSR"] = pysiology.electrodermalactivity.analyzeGSR(GSR[startSample:endSample],sr) #analyze the GSR signal

Cite

If you use PySiology, please cite:

Gabrieli G., Azhari A., Esposito G. (2020) PySiology: A Python Package for Physiological Feature Extraction. In: Esposito A., Faundez-Zanuy M., Morabito F., Pasero E. (eds) Neural Approaches to Dynamics of Signal Exchanges. Smart Innovation, Systems and Technologies, vol 151. Springer, Singapore

Requirements

• Numpy
• Scipy
• Peakutils
• Matplotlib

Contacts

Feel free to contact me for questions, suggestions or to give me advice as well at: [email protected]

Scientific Publications that used pysiology

• Jain, A., & Kumar, R. (2024, May). Machine Learning based Anxiety Detection using Physiological Signals and Context Features. In 2024 2nd International Conference on Advancement in Computation & Computer Technologies (InCACCT) (pp. 116-121). IEEE.
• Krivich, E., Mottus, M., & Bauters, M. (2023). Comparing Psychophysiological Responses to Vicarious Pain Experience Elicited by Videos Featuring either Humans or Avatars. In Proceedings of the 26th International Academic Mindtrek Conference.
• Wiercinski, T., & Zawadzka, T. (2023). Short Paper: Late Fusion Approach for Multimodal Emotion Recognition Based on Convolutional and Graph Neural Networks.
• Gabrieli, G., Bornstein, M. H., Setoh, P., & Esposito, G. (2023). Machine learning estimation of users’ implicit and explicit aesthetic judgments of web-pages. Behaviour & Information Technology, 42(4), 392-402.- Hsu, S. M., Chen, S. H., &
• Momota, M. M. R., Morshed, B. I., Ferdous, T., & Fujiwara, T. (2023). Fabrication and Characterization of Inkjet Printed Flexible Dry ECG Electrodes. IEEE Sensors Journal, 23(7), 7917-7928.
• Warner, J., Gault, R., & McAllister, J. (2022, July). Optimised EMG pipeline for gesture classification. In 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) (pp. 3628-3631). IEEE.
• Momota, M. M. R., & Morshed, B. I. (2022). ML algorithms to estimate data reliability metric of ECG from inter-patient data for trustable AI-based cardiac monitors. Smart Health, 26, 100350.
• Chan, S. H. M., Qiu, L., Esposito, G., Mai, K. P., Tam, K. P., & Cui, J. (2021). Nature in virtual reality improves mood and reduces stress: evidence from young adults and senior citizens. Virtual reality, 1-16.
• Chan, S. H. M., Qiu, L., Esposito, G., & Mai, K. P. (2021). Vertical greenery buffers against stress: Evidence from psychophysiological responses in virtual reality. Landscape and Urban Planning, 213, 104127.
• Huang, T. R. (2021). Personal Resilience Can Be Well Estimated from Heart Rate Variability and Paralinguistic Features during Human–Robot Conversations. Sensors, 21(17), 5844.
• Aqajari, S. A. H., Naeini, E. K., Mehrabadi, M. A., Labbaf, S., Rahmani, A. M., & Dutt, N. (2020). Gsr analysis for stress: Development and validation of an open source tool for noisy naturalistic gsr data. arXiv preprint arXiv:2005.01834.
• Bizzego, A., Azhari, A., Campostrini, N., Truzzi, A., Ng, L. Y., Gabrieli, G., ... & Esposito, G. (2019). Strangers, friends, and lovers show different physiological synchrony in different emotional states. Behavioral Sciences, 10(1), 11.

Coffee?

pysiology's Issues

EMG Analysis - Future

Add testunits

Sample data not installed via Pip

Installing the package using pip does not install the sample data.
Add a function to download the data, if missing.

Add frequency Analysis for ECG

Sample signals not loaded if installed using pip

Sample signals are not packed inside the pip version of the library.
Create a function to download them later, in order not to increase the size of the package installation.

GSR Analysis

• Noise Filtering
• Signal Decomposition --> Phasic Phase Extraction
• Features Extraction

Print citation info on package import

On import, the package should print the citation information, as in Pyphysio: https://github.com/MPBA/pyphysio

Add sample data for Debug and Learning

• ECG sample Data
• GSR sample Data
• EMG sample Data
• ECG Tutorial
• GSR Tutorial
• EMG Tutorial

Add Pysiology to open-neuroscience.com

Hello!

We are reaching out because we would love to have your project listed on Open Neuroscience, and also share information about this project:

Open Neuroscience is a community run project, where we are curating and highlighting open source projects related to neurosciences!

Briefly, we have a website where short descritptions about projects are listed, with links to the projects themselves, their authors, together with images and other links.

Once a new entry is made, we make a quick check for spam, and publish it.

Once published, we make people aware of the new entry by Twitter and a Facebook group.

To add information about their project, developers only need to fill out this form

In the form, people can add subfields and tags to their entries, so that projects are filterable and searchable on the website!

The reason why we have the form system is that it makes it open for everyone to contribute to the website and allows developers themselves to describe their projects!

Also, there are so many amazing projects coming out in Neurosciences that it would be impossible for us to keep track and log them all!

Please get in touch if you have any questions or would like to collaborate!

Documentation

Documentation should cover

• Usage of different functions
• Tutorial with sample data loading and processing
• Literature used

Future Functions

Generic:

• Automatic detection of bad signal

EDA/GSR:

• Add function for separating phasic and tonic component (and keep both)

EMG

• V V-order
  "An optimal value for v has been reported to be 2, which leads to the definition of RMS feature."
  Phinyomark, A., Phukpattaranont, P., & Limsakul, C. (2012). Feature reduction and selection for EMG signal classification. Expert Systems with Applications, 39(8), 7420-7431.
• MHWk Multiple hamming windows
• MTVk Multiple Trapezoidal Windows
• Auto Regressive Coefficient
• Cepstral Coefficient

Add peak detection parameters to the analyzeSignal functions

As suggested,
add the peak detection parameters to the different dummy analyzeSignal entrypoint functions.

EMG Analysis

Phinyomark, A., Phukpattaranont, P., & Limsakul, C. (2012). Feature reduction and selection for EMG signal classification. Expert Systems with Applications, 39(8), 7420-7431.

Pre Processing

• Highpass Filter
• LowPass Filter

Time Domain Features

• IEMG Integrated EMG
• MAV Mean absolute value
• MAV1 Modified Mean Absolute Value 1
• MAV2 Modified Mean Absolute Value 2
• SSI Simple Square Integral
• VAR Variance of EMG
• TM3 Absolute of the 3rd Temporal Moment
• TM4 Absolute of the 4rd Temporal Moment
• TM5 Absolute of the 5rd Temporal Moment
• RMS Root Mean Square
• LOG Log Detector
• WL Waveform Lenght
• AAC Average Amplitude Change
• DASDV Difference absolute standard deviation value
• AFB Amplitude at First Burst
• ZC Zero Crosstime
• MYOP Myopulse Percentage Rate
• WAMP Wilson Amplitude
• SSC Slope Sign Change
• MAVSLPk Mean absolute value slope
• Histogram of EMG

Frequency Domain Features

• MNF Mean Frequency
• MDF Median Frequency
• PKF Peak frequency
• MNP Mean Power
• TTP Total Power
• SM1 1st Spectral Moment
• SM2 2nd Spectral Moment
• SM3 3rd Spectral Moment
• FR Frequency Ratio
• PSR Power Spectrum Ratio
• VCF Variance of Central Frequency

Problem with function [def getPSD(rawEMGSignal, samplerate):]

The window type in the scipy library does not have hanning and needs to be changed to hann.
Otherwise, an error will be reported. The following are the corrected results.

Validation

• Check some example data with other packages / software.

Problem with time generations in __utilis__ ccleandri()

Mismatch between len of times and average/median.

Add Link to paper in readme and docs

Add link to the springer's paper in the readme and docs files.