PresentationPDF Available

PySiology: A python package for physiological feature extraction

Authors:

Abstract and Figures

Introduction to Pysiology and advanced example (estimating images' valence from viewers physiological measurements)
No caption available
… 
No caption available
… 
No caption available
… 
No caption available
… 
No caption available
… 
Content may be subject to copyright.
PySiology
A python package for
physiological feature
extraction
Gabrieli G., Azhari A., Esposito G.
WIRN 2018
2
Feature estimation
Classification
Raw signal
GUI
Feature estimation is
done using a GUI. Easier
for non-experts.
Low customizability
Hidden parameters

CL / Scripting
Feature estimation is
done by (hard)-coding
your own set of functions
and classes.
(ex: MNE-python)
Errors
Time-consuming
3
Suitable for novice and expert users
Low learning curve
Highly customizable
Up-to-date with latest techniques

4
PySiology
Features estimation from ECG, EMG
and EDA raw signals
pysiology.rtfd.io
git.io/vh0PB
5
Python
Division by signals and not by stage of analysis
Scripting vs OOP
Clear documentation
Tutorials and sample data
Dummy pipelines for preprocessing and analysis
Open source package

6

7
Features in v. 0.0.9
ECG IBI, BPM,SDNN, SDSD, RMSSD, PNN50, PNN20, PNN50 / PNN20,
frequency analysis (high, low, very low)
EDA Rise time, latency, amplitude, half amplitude, EDA at apex, decay
time, SCR width
EMG
IEMG, MAV, SSI, VAR, TM, LOG, RMS, WL, AAC, DASDV, AFB, MYOP,
WAMP, SSC, MAVSLPk, HIST, MNF, MDF, peak frequency, MNP, TTP, SM,
FR, PSR, VCF
pysiology.signals.getFeatureNames(signal,
p1=stdalue1, …, pN=stdvalueN)
pysiology.signals.analyzeSignal(signal, sr)
8
import pysiology
ECG = pysiology.sampledata.loadsampleECG() #load the sample ECG Signal
sr = 1000 #samplerate in hZ
events = [["A",10], ["B",20]] #we can define the events the way we prefer
eventLenght = 8 #in seconds
for event in events:
startS, endS = [sr * event[1],startSample + (sr * eventLenght)
results = pysiology.electrocardiography.analyzeECG(ECG[startS:endS],sr)
9
Advanced
Example
Estimating images’ valence
through physiological
measurements

58 university students (age = 21.5+2,3)
50 IAPS images (25 low val., 25 high val.)
Images were presented for 8s (6s interval)
Physiological measurements:
ECG
EDA
EMG (Corrugator supercilii)
11

12
 !
13
"#
Preprocessing (using PySiology, standard parameters)
Feature estimation (using PySiology, standard
parameters)
Principal component analysis (using Scikit-learn, 6
components)
Classification using MLPNN (using Scikit-learn,
standard parameters)
Classification using Decision Tree (using Scikit-learn,
standard parameters)
Bootstrapping:
test = 100 repetition
train = 45 images (10% of the dataset)
14
$
 %
&'' 65%
$( 66%
15
Conclusions
PySiology is an open source python package for
physiological features estimation.
Suitable for novice users
Highly customizable
Tutorials and documentation
Reliable method for physiological features estimation
16
Thanks!
Any questions?
You can find me at:
giulio.gabrieli@studenti.unitn.it
17
$%)
 %
&'' 97%
18
N = 1361 epochs, bootstrapping with 100 repetition, 90% Train
Reference vs estimated valence
Reference valence
Estimated valence
... ECG, EDA, and EMG (corrugator supercilii) signals were collected on a Bitalino Revolution BT board, a low-cost device designed for physiological data collection (sampling rate: 1000 Hz, Wireless Biosignals S.A.) [15], at a resolution of 1279 × 800. Data used in this manuscript are available online [16]. ...
Chapter
Physiological signals have been widely used to measure continuous data from the autonomic nervous system in the fields of computer science, psychology, and human–computer interaction. Signal processing and feature estimation of physiological measurements can be performed with several commercial tools. Unfortunately, those tools possess a steep learning curve and do not usually allow for complete customization of estimation parameters. For these reasons, we designed PySiology, an open-source package for the estimation of features from physiological signals, suitable for both novice and expert users. This package provides clear documentation of utilized methodology, guided functionalities for semi-automatic feature estimation, and options for extensive customization. In this article, a brief introduction to the features of the package, and to its design workflow, are presented. To demonstrate the usage of the package in a real-world context, an advanced example of image valence estimation from physiological measurements (ECG, EMG, and EDA) is described. Preliminary tests have shown high reliability of feature estimated using PySiology.
Chapter
Physiological signals have been widely used to measure continuous data from the autonomic nervous system in the fields of computer science, psychology, and human–computer interaction. Signal processing and feature estimation of physiological measurements can be performed with several commercial tools. Unfortunately, those tools possess a steep learning curve and do not usually allow for complete customization of estimation parameters. For these reasons, we designed PySiology, an open-source package for the estimation of features from physiological signals, suitable for both novice and expert users. This package provides clear documentation of utilized methodology, guided functionalities for semi-automatic feature estimation, and options for extensive customization. In this article, a brief introduction to the features of the package, and to its design workflow, are presented. To demonstrate the usage of the package in a real-world context, an advanced example of image valence estimation from physiological measurements (ECG, EMG, and EDA) is described. Preliminary tests have shown high reliability of feature estimated using PySiology.
ResearchGate has not been able to resolve any references for this publication.