TF-C Pretrain HAR
Lists
Only you see this
Abstract
- Paper: Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency - Paper link: - Github repo: https://github.com/mims-harvard/TFC-pretraining - Project website: <br> <strong>HAR</strong> contains recordings of 30 health volunteers performing six daily activities such as walking, walking upstaris, walking downstairs, sitting, standing, and laying. The prediction labels are the six activities. The wearable sensors on a smartphone measure triaxial linear acceleration and triaxial angular velocity at 50 Hz. After preprocessing and isolating out gravitational acceleration from body acceleration, there are nine channels in total. To line up the semantic domain with the channels in the dataset use during fine-tuning <strong>Gesture</strong> we only use the three channels of body linear accelerations. <br> <br>
BibTeX
@inproceedings{zhang2022tf,
author = {Xiang Zhang and Ziyuan Zhao and Theodoros Tsiligkaridis and Marinka Žitnik},
title = {{TF-C Pretrain HAR}},
booktitle = {Figshare},
year = {2022},
doi = {10.6084/m9.figshare.19930244},
}Loading related content...