BioMAT (Biomechanics Multiactivity Transformer)

This dataset is derived from a publicly available dataset generated by Camargo et al. The dataset aimed to convert the exciting dataset to a format which is used for training and evaluation of machine learning models, specifically transformer-based model, proposed by the Sharifi et al study.

Dataset Use Case

This dataset has been used in training and evaluation of multiple deep neural networks architecture such as BioMAT, BiLSTM, and CNNLSTM. The source code related the usage of this dataset is availabe here: https://github.com/MohsenSharifi1991/BioMAT

Data Availability

The dataset is available for public use and can be accessed through the provided link https://digitalcommons.du.edu/biomat/ . Researchers, data analysts, and machine learning practitioners can utilize this dataset for academic, research, or commercial purposes, under the terms of the Creative Commons Attribution 4.0 International License.

Citations

If you use this dataset in your research or publications, we kindly request that you cite it using the following references:

Sharifi-Renani, M.; Mahoor, M.H.; Clary, C.W. BioMAT: An Open-Source Biomechanics Multi-Activity Transformer for Joint Kinematic Predictions Using Wearable Sensors. Sensors 2023, 23, x.

Camargo, Jonathan, et al. "A comprehensive, open-source dataset of lower limb biomechanics in multiple conditions of stairs, ramps, and level-ground ambulation and transitions." Journal of Biomechanics 119 (2021): 110320. https://doi.org/10.1016/j.jbiomech.2021.110320