Tifex-Py: Time-Series Feature Extraction for Python in a Human Activity Recognition Scenario

Human Activity Recognition (HAR) is a valuable tool for healthcare and rehabilitation, enabling applications like remote patient monitoring and rehabilitation progress assessment. This paper introduces TIFEX-Py, a comprehensive Python toolbox designed for time series feature extraction in HAR. TIFEX...

Full description

Saved in:
Bibliographic Details
Published inIEEE International Conference on Rehabilitation Robotics Vol. 2025; pp. 1332 - 1339
Main Authors Ejtehadi, Mehdi, Graham, Gloria Edumaba, Ringstrom, Cailin, Du, Elisa, Riener, Robert, Paez-Granados, Diego
Format Conference Proceeding Journal Article
LanguageEnglish
Published United States IEEE 01.05.2025
Subjects
Accuracy
Algorithms
Benchmark testing
Classification
Feature extraction
Human Activities - classification
Human activity recognition
Humans
Machine Learning
Measurement
Medical services
Pipelines
Programming Languages
Python
Software
Time Series
Time series analysis
Time-frequency analysis
Wearable sensors
Online AccessGet full text

Cover

More Information
Summary:Human Activity Recognition (HAR) is a valuable tool for healthcare and rehabilitation, enabling applications like remote patient monitoring and rehabilitation progress assessment. This paper introduces TIFEX-Py, a comprehensive Python toolbox designed for time series feature extraction in HAR. TIFEX-Py offers a rich set of 195 feature extraction methods across statistical, amplitude, spectral, and time-frequency domains. To evaluate its effectiveness, TIFEX-Py was applied to 11 publicly available HAR datasets: DSADS, HHAR, MHEALTH, MotionSense, PAMAP2, REALDISP, RealWorld, UniMiBSHAR, USC-HAD, WARD, and WISDM. Machine learning pipelines utilizing TIFEX-Py features, evaluated under both random and subject-stratified cross-validation settings, consistently achieved performance that is competitive with or superior to state-of-theart (SOTA) benchmark performances available for the datasets. In 11 out of 11 random split cross-validation scenarios, our pipeline surpassed or matched SOTA performance. For stratified by subject cross-validation, this was the case for more than half of the datasets. These results highlight the power of TIFEX-Py's feature space in representing time series data. TIFEX-Py is opensource and publicly available for researchers in rehabilitation and movement analysis fields.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1945-7901
1945-7901
DOI:10.1109/ICORR66766.2025.11062978