TY - GEN
T1 - A hybrid hierarchical model for accessing physical activity recognition towards free-living environments
AU - Qi, Jun
AU - Liang, Hai Ning
AU - Chen, Jianjun
AU - Peng, Xiyang
AU - Newcombe, Lee
AU - Yang, Po
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/12
Y1 - 2020/12
N2 - Driven by the new revolution in healthcare, the importance of understanding Physical Activity (PA) in the uncertain, dynamic, free-living environments has been drawing growing attention. However, there is a lack of holistic investigation on how to improve the accuracy of PA recognition in free-living environments using cost-effective wearable devices with feasible algorithms. In this paper, we design a two-layer hybrid hierarchical model for accessing and evaluating cost-effective wearable intelligence approaches for PA recognition in free-living environments. The hypothesis of this model first suggests utilising less-attached on-body consumable wearables like belt and wristband devices, and then building up a PA dataset collected in free-living environments like an elderly home, hospital, office and gym. The model is then defined with components of lightGBM (LGB) and Artificial Neural Networks (ANN) for coarse and fine-grained classification, parameters of achieving high recognition rate including time window sizes, features and activation functions. The experimental results indicate that our model has superior ability over other state-of-the-art algorithms in classifying three typical types of PA (dynamic, sedentary, and transitional) with an average accuracy up to 84%. Specifically, our model performs good results of PA recognition with the ageing populations including 5 Mild Cognitive Impairment (MCI) and 17 Parkinson's disease (PD) patients.
AB - Driven by the new revolution in healthcare, the importance of understanding Physical Activity (PA) in the uncertain, dynamic, free-living environments has been drawing growing attention. However, there is a lack of holistic investigation on how to improve the accuracy of PA recognition in free-living environments using cost-effective wearable devices with feasible algorithms. In this paper, we design a two-layer hybrid hierarchical model for accessing and evaluating cost-effective wearable intelligence approaches for PA recognition in free-living environments. The hypothesis of this model first suggests utilising less-attached on-body consumable wearables like belt and wristband devices, and then building up a PA dataset collected in free-living environments like an elderly home, hospital, office and gym. The model is then defined with components of lightGBM (LGB) and Artificial Neural Networks (ANN) for coarse and fine-grained classification, parameters of achieving high recognition rate including time window sizes, features and activation functions. The experimental results indicate that our model has superior ability over other state-of-the-art algorithms in classifying three typical types of PA (dynamic, sedentary, and transitional) with an average accuracy up to 84%. Specifically, our model performs good results of PA recognition with the ageing populations including 5 Mild Cognitive Impairment (MCI) and 17 Parkinson's disease (PD) patients.
KW - Artificial neural networks
KW - Healthcare
KW - Physical activity recognition
KW - Wearable device
UR - http://www.scopus.com/inward/record.url?scp=85108030143&partnerID=8YFLogxK
U2 - 10.1109/ISPA-BDCloud-SocialCom-SustainCom51426.2020.00199
DO - 10.1109/ISPA-BDCloud-SocialCom-SustainCom51426.2020.00199
M3 - Conference Proceeding
AN - SCOPUS:85108030143
T3 - Proceedings - 2020 IEEE International Symposium on Parallel and Distributed Processing with Applications, 2020 IEEE International Conference on Big Data and Cloud Computing, 2020 IEEE International Symposium on Social Computing and Networking and 2020 IEEE International Conference on Sustainable Computing and Communications, ISPA-BDCloud-SocialCom-SustainCom 2020
SP - 1342
EP - 1347
BT - Proceedings - 2020 IEEE International Symposium on Parallel and Distributed Processing with Applications, 2020 IEEE International Conference on Big Data and Cloud Computing, 2020 IEEE International Symposium on Social Computing and Networking and 2020 IEEE International Conference on Sustainable Computing and Communications, ISPA-BDCloud-SocialCom-SustainCom 2020
A2 - Hu, Jia
A2 - Min, Geyong
A2 - Georgalas, Nektarios
A2 - Zhao, Zhiwei
A2 - Hao, Fei
A2 - Miao, Wang
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 18th IEEE International Symposium on Parallel and Distributed Processing with Applications, 10th IEEE International Conference on Big Data and Cloud Computing, 13th IEEE International Symposium on Social Computing and Networking and 10th IEEE International Conference on Sustainable Computing and Communications, ISPA-BDCloud-SocialCom-SustainCom 2020
Y2 - 17 December 2020 through 19 December 2020
ER -