Description:	Background: Soft strain sensors can be integrated into clothing in a very unobtrusive fashion and may be used for kinematics measurement of runners in the field. This study collected data to train and test a machine learning model that predicted running kinematics from wearable strain sensor measurements. Objective: Evaluate whether soft fibre strain sensors worn in a tight-fitting garment around unilateral lower limb joints could be used to reconstruct running kinematics. The resisitve strain sensor signals (after processing with a machine learning model) were compared to the gold-standard optical motion capture reference which was collected simultaneously. Research outcomes: These data were collected for the study in [1]. Data intepretations: This dataset may be useful for others comparing resistive strain sensors in running, as there exists few public datasets that include both strain sensors and gold-standard motion capture data. Methods: Data was collected as described in [1]. Twelve subjects ran on an instrumented treadmill at five speeds (8, 9, ..., 12 km/h) wearing tights that included nine piezoresistive strain sensors. An optical motion capture system recorded the "gold standard" joint angles. Shortcomings of the dataset include: - Strain sensors placed only on the left leg. - Only the left side ground reaction forces were measured. [1] Gholami, M.; Rezaei, A.; Cuthbert, T.J.; Napier, C.; Menon, C. Lower Body Kinematics Monitoring in Running Using Fabric-Based Wearable Sensors and Deep Convolutional Neural Networks. Sensors 2019, 19, 5325–5343, doi:10.3390/s19235325.
Authors:	Gholami, Mohsen; Simon Fraser University Menon, Carlo; Simon Fraser University
Keywords:	wearable sensors human motion tracking textile sensors
Field of Research:	Medical and biomedical engineering > Medical and biomedical engineering > Biomechanical engineering
Publication Date:	2024-01-25
Publisher:	Federated Research Data Repository / dépôt fédéré de données de recherche
Funder:	Canada Foundation for Innovation; Centre for Wearable Biomedical Technologies; Project Number 36347
URI:	https://doi.org/10.20383/103.0871
Related Identifiers:	This dataset is derived from https://doi.org/10.3390/s19235325
Appears in Collections:	SFU Research Data