PreprintArticleVersion 2Preserved in Portico This version is not peer-reviewed
Study on Temperature (τ) Variation for SimCLR based Activity Recognition
Pranjal Kumar
*
Version 1
: Received: 6 July 2021 / Approved: 6 July 2021 / Online: 6 July 2021 (11:38:18 CEST)
Version 2
: Received: 9 July 2021 / Approved: 9 July 2021 / Online: 9 July 2021 (15:46:05 CEST)
How to cite:
Kumar, P. Study on Temperature (τ) Variation for SimCLR based Activity Recognition. Preprints2021, 2021070138. https://doi.org/10.20944/preprints202107.0138.v2
Kumar, P. Study on Temperature (τ) Variation for SimCLR based Activity Recognition. Preprints 2021, 2021070138. https://doi.org/10.20944/preprints202107.0138.v2
Kumar, P. Study on Temperature (τ) Variation for SimCLR based Activity Recognition. Preprints2021, 2021070138. https://doi.org/10.20944/preprints202107.0138.v2
APA Style
Kumar, P. (2021). Study on Temperature (τ) Variation for SimCLR based Activity Recognition. Preprints. https://doi.org/10.20944/preprints202107.0138.v2
Chicago/Turabian Style
Kumar, P. 2021 "Study on Temperature (τ) Variation for SimCLR based Activity Recognition" Preprints. https://doi.org/10.20944/preprints202107.0138.v2
Abstract
Human Activity Recognition (HAR) is a process to automatically detect human activities based on stream data generated from various sensors, including inertial sensors, physiological sensors, location sensors, cameras, time, and many others. Unsupervised contrastive learning has been excellent, while the contrastive loss mechanism is less studied. In this paper, we provide a temperature (τ) variance study affecting the loss of SimCLR model and ultimately full HAR evaluation results. We focus on understanding the implications of unsupervised contrastive loss in context of HAR data. In this work, also regulation of the temperature(τ) coefficient is incorporated for improving the HAR feature qualities and overall performance for downstream tasks in healthcare setting. Performance boost of 1.3% is observed in experimentation.
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Commenter: Pranjal Kumar
Commenter's Conflict of Interests: Author