Explaining machine learning models for age classification in human gait analysis
- Publication type:
- Journal article
- Metadata:
-
- Author's licence
- InCopyright
- Autoren
- Djordje Slijepcevic
- Fabian Horst
- Marvin Simak
- Sebastian Lapuschkin
- Anna-Maria Raberger
- Wojciech Samek
- Christian Breiteneder
- Wolfgang I Schöllhorn
- Matthias Zeppelzauer
- Brian Horsak
- Hosting institution
- Universitätsbibliothek Mainz
- Resource version
- Published version
- DOI
- 10.1016/j.gaitpost.2022.07.153
- File(s) embargoed
- false
- Open access
- true
- ISSN
- 0966-6362
- Ausgabe der Veröffentlichung
- Supplement 1
- Zeitschrift
- Gait & posture
- Sprache
- eng
- Open access status
- Open Access
- Paginierung
- 252 - 253
- Herausgeber
- Elsevier
- Zugang
- Deleted
- Titel
- Explaining machine learning models for age classification in human gait analysis
- Ausgabe der Zeitschrift
- 97
Files
explaining_machine_learning_m-20230628092404808.pdf
Data source: OPENSCIENCE.UB
- Other metadata sources:
-
- Abstract
- Machine learning (ML) models have proven effective in classifying gait analysis data, e.g., binary classification of young vs. older adults. ML models, however, lack in providing human understandable explanations for their predictions. This "black-box" behavior impedes the understanding of which input features the model predictions are based on. We investigated an Explainable Artificial Intelligence method, i.e., Layer-wise Relevance Propagation (LRP), for gait analysis data. The research question was: Which input features are used by ML models to classify age-related differences in walking patterns? We utilized a subset of the AIST Gait Database 2019 containing five bilateral ground reaction force (GRF) recordings per person during barefoot walking of healthy participants. Each input signal was min-max normalized before concatenation and fed into a Convolutional Neural Network (CNN). Participants were divided into three age groups: young (20-39 years), middle-aged (40-64 years), and older (65-79 years) adults. The classification accuracy and relevance scores (derived using LRP) were averaged over a stratified ten-fold cross-validation. The mean classification accuracy of 60.1% was clearly higher than the zero-rule baseline of 37.3%. The confusion matrix shows that the CNN distinguished younger and older adults well, but had difficulty modeling the middle-aged adults.
- Autoren
- Djordje Slijepcevic
- Fabian Horst
- Marvin Simak
- Sebastian Lapuschkin
- Anna-Maria Raberger
- Wojciech Samek
- Christian Breiteneder
- Wolfgang I Schöllhorn
- Matthias Zeppelzauer
- Brian Horsak
- Autoren-URL
- http://arxiv.org/abs/2211.17016v1
- Zeitschrift
- Gait & Posture 97 (Supplement 1) (2022) 252-253
- Schlüsselwörter
- cs.LG
- cs.LG
- Notes
- 3 pages, 1 figure
- Datum der Veröffentlichung
- 2022
- Herausgeber URL
- http://dx.doi.org/10.1016/j.gaitpost.2022.07.153
- Datum der Datenerfassung
- 2022
- Datum, an dem der Datensatz öffentlich gemacht wurde
- 2022
- Titel
- Explaining machine learning models for age classification in human gait analysis
Files
2211.17016v1.pdf
Data source: arXiv
- Autoren
- Djordje Slijepcevic
- Fabian Horst
- Marvin Simak
- Sebastian Lapuschkin
- Anna-Maria Raberger
- Wojciech Samek
- Christian Breiteneder
- Wolfgang I Schöllhorn
- Matthias Zeppelzauer
- Brian Horsak
- DOI
- 10.1016/j.gaitpost.2022.07.153
- ISSN
- 0966-6362
- Ausgabe der Veröffentlichung
- Supplement 1
- Zeitschrift
- Gait & posture
- Sprache
- eng
- Open access status
- Open Access
- Paginierung
- 252 - 253
- Datum der Veröffentlichung
- 2022
- Herausgeber
- Elsevier
- Datum der Datenerfassung
- 2023
- Titel
- Explaining machine learning models for age classification in human gait analysis
- Ausgabe der Zeitschrift
- 97
Data source: Manual
- Beziehungen:
- Property of