CSL-SHARE: Sensor-based Human Activity Recordings
The CSL-SHARE data corpus contains 22 activities performed by 20 study participants. The participants wore a knee bandage equipped with sensors totaling 19-channels.
The paper publishing this data corpus describes the structure and the usage of the dataset in detail (see under).
The data can be downloaded here.
Privacy Preservation and Data Security:
The participant's consent form stipulates that the use of the data is limited to non-commercial research purposes, and the data users guarantee not to attempt to identify the participating persons. Furthermore, the data users guarantee to pass on the data (or data derived from it) only to third parties who are bound by the same rules of use (for non-commercial research purposes, no identification attempts, restricted disclosure). Data users who violate the usage regulation mentioned above will bear the legal consequences themselves, where the dataset publisher takes no responsibility.
This dataset is freely available for non-commercial academic research. We would appreciate referencing the below publications if you use this dataset or the implementation approaches related to it:
The CSL-SHARE dataset and the semi-automatic segmentation and annotation mechanism:
Statistical details and activity duration analysis of the CSL-SHARE dataset:
Human Activity Recognition Research on the CSL-SHARE dataset and other Datasets:
More detailed information about the devices, the sensors, the bandage, and the implemented software applied in the CSL-SHARE dataset acquisition:
Feature extraction examples from the CSL-SHARE dataset using the open-source Time Series Feature Extraction Library (TSFEL):
- TSFEL: Time Series Feature Extraction Library. (Marília Barandas, Duarte Folgado, Letícia Fernandes, Sara Santos, Mariana Abreu, Patrícia Bota, Hui Liu, Tanja Schultz, Hugo Gamboa), In SoftwareX, Elsevier, Volume 11, 2020.
Feature dimensionality study on CSL-SHARE and other datasets:
- Feature Space Reduction for Human Activity Recognition based on Multi-channel Biosignals. (Yale Hartmann, Hui Liu, Tanja Schultz), In Proceedings of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies - BIOSIGNALS, pages 215-222, 2021.
- Feature Space Reduction for Multimodal Human Activity Recognition. (Yale Hartmann, Hui Liu, Tanja Schultz), In Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies - BIOSIGNALS, pages 135-140, 2020.
Novel human activity modeling method of Motion Units on the CSL-SHARE dataset: