Cargando…
SemNet: Learning semantic attributes for human activity recognition with deep belief networks
Human Activity Recognition (HAR) is a prominent application in mobile computing and Internet of Things (IoT) that aims to detect human activities based on multimodal sensor signals generated as a result of diverse body movements. Human physical activities are typically composed of simple actions (su...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9469877/ https://www.ncbi.nlm.nih.gov/pubmed/36111178 http://dx.doi.org/10.3389/fdata.2022.879389 |
_version_ | 1784788730847952896 |
---|---|
author | Venkatachalam, Shanmuga Nair, Harideep Zeng, Ming Tan, Cathy Shunwen Mengshoel, Ole J. Shen, John Paul |
author_facet | Venkatachalam, Shanmuga Nair, Harideep Zeng, Ming Tan, Cathy Shunwen Mengshoel, Ole J. Shen, John Paul |
author_sort | Venkatachalam, Shanmuga |
collection | PubMed |
description | Human Activity Recognition (HAR) is a prominent application in mobile computing and Internet of Things (IoT) that aims to detect human activities based on multimodal sensor signals generated as a result of diverse body movements. Human physical activities are typically composed of simple actions (such as “arm up”, “arm down”, “arm curl”, etc.), referred to as semantic features. Such abstract semantic features, in contrast to high-level activities (“walking”, “sitting”, etc.) and low-level signals (raw sensor readings), can be developed manually to assist activity recognition. Although effective, this manual approach relies heavily on human domain expertise and is not scalable. In this paper, we address this limitation by proposing a machine learning method, SemNet, based on deep belief networks. SemNet automatically constructs semantic features representative of the axial bodily movements. Experimental results show that SemNet outperforms baseline approaches and is capable of learning features that highly correlate with manually defined semantic attributes. Furthermore, our experiments using a different model, namely deep convolutional LSTM, on household activities illustrate the broader applicability of semantic attribute interpretation to diverse deep neural network approaches. These empirical results not only demonstrate that such a deep learning technique is semantically meaningful and superior to its handcrafted counterpart, but also provides a better understanding of the deep learning methods that are used for Human Activity Recognition. |
format | Online Article Text |
id | pubmed-9469877 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-94698772022-09-14 SemNet: Learning semantic attributes for human activity recognition with deep belief networks Venkatachalam, Shanmuga Nair, Harideep Zeng, Ming Tan, Cathy Shunwen Mengshoel, Ole J. Shen, John Paul Front Big Data Big Data Human Activity Recognition (HAR) is a prominent application in mobile computing and Internet of Things (IoT) that aims to detect human activities based on multimodal sensor signals generated as a result of diverse body movements. Human physical activities are typically composed of simple actions (such as “arm up”, “arm down”, “arm curl”, etc.), referred to as semantic features. Such abstract semantic features, in contrast to high-level activities (“walking”, “sitting”, etc.) and low-level signals (raw sensor readings), can be developed manually to assist activity recognition. Although effective, this manual approach relies heavily on human domain expertise and is not scalable. In this paper, we address this limitation by proposing a machine learning method, SemNet, based on deep belief networks. SemNet automatically constructs semantic features representative of the axial bodily movements. Experimental results show that SemNet outperforms baseline approaches and is capable of learning features that highly correlate with manually defined semantic attributes. Furthermore, our experiments using a different model, namely deep convolutional LSTM, on household activities illustrate the broader applicability of semantic attribute interpretation to diverse deep neural network approaches. These empirical results not only demonstrate that such a deep learning technique is semantically meaningful and superior to its handcrafted counterpart, but also provides a better understanding of the deep learning methods that are used for Human Activity Recognition. Frontiers Media S.A. 2022-08-30 /pmc/articles/PMC9469877/ /pubmed/36111178 http://dx.doi.org/10.3389/fdata.2022.879389 Text en Copyright © 2022 Venkatachalam, Nair, Zeng, Tan, Mengshoel and Shen. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Big Data Venkatachalam, Shanmuga Nair, Harideep Zeng, Ming Tan, Cathy Shunwen Mengshoel, Ole J. Shen, John Paul SemNet: Learning semantic attributes for human activity recognition with deep belief networks |
title | SemNet: Learning semantic attributes for human activity recognition with deep belief networks |
title_full | SemNet: Learning semantic attributes for human activity recognition with deep belief networks |
title_fullStr | SemNet: Learning semantic attributes for human activity recognition with deep belief networks |
title_full_unstemmed | SemNet: Learning semantic attributes for human activity recognition with deep belief networks |
title_short | SemNet: Learning semantic attributes for human activity recognition with deep belief networks |
title_sort | semnet: learning semantic attributes for human activity recognition with deep belief networks |
topic | Big Data |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9469877/ https://www.ncbi.nlm.nih.gov/pubmed/36111178 http://dx.doi.org/10.3389/fdata.2022.879389 |
work_keys_str_mv | AT venkatachalamshanmuga semnetlearningsemanticattributesforhumanactivityrecognitionwithdeepbeliefnetworks AT nairharideep semnetlearningsemanticattributesforhumanactivityrecognitionwithdeepbeliefnetworks AT zengming semnetlearningsemanticattributesforhumanactivityrecognitionwithdeepbeliefnetworks AT tancathyshunwen semnetlearningsemanticattributesforhumanactivityrecognitionwithdeepbeliefnetworks AT mengshoelolej semnetlearningsemanticattributesforhumanactivityrecognitionwithdeepbeliefnetworks AT shenjohnpaul semnetlearningsemanticattributesforhumanactivityrecognitionwithdeepbeliefnetworks |