EUVIMEDEUVIMED entdecken
Crossref

Deep Ensemble Learning for Human Activity Recognition Using Wearable Sensors via Filter Activation

Wenbo Huang, Lei Zhang, Shuoyuan Wang, Hao Wu, Aiguo Song

ACM Transactions on Embedded Computing Systems · 31.01.2023 · 22 (1) · 1-23

DOI: 10.1145/3551486 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Embedded Computing Systems, online erschienen am 29.10.2022. Verfasst von Wenbo Huang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 42-mal zitiert (Crossref) und nennt 57 Literaturangaben. Gefördert von: Natural Science Foundation of Jiangsu Province, National Nature Science Foundation of China, Industry Academia Cooperation Innovation Fund Projection of Jiangsu Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

During the past decade, human activity recognition ( HAR ) using wearable sensors has become a new research hot spot due to its extensive use in various application domains such as healthcare, fitness, smart homes, and eldercare. Deep neural networks, especially convolutional neural networks ( CNNs ), have gained a lot of attention in HAR scenario. Despite exceptional performance, CNNs with heavy overhead is not the best option for HAR task due to the limitation of computing resource on embedded devices. As far as we know, there are many invalid filters in CNN that contribute very little to output. Simply pruning these invalid filters could effectively accelerate CNNs , but it inevitably hurts performance. In this article, we first propose a novel CNN for HAR that uses filter activation. In comparison with filter pruning that is motivated for efficient consideration, filter activation aims to activate these invalid filters from an accuracy boosting perspective. We perform extensive experiments on several public HAR datasets, namely, UCI-HAR ( UCI ), OPPORTUNITY ( OPPO ), UniMiB-SHAR ( Uni ), PAMAP2 ( PAM2 ), WISDM ( WIS ), and USC-HAD ( USC ), which show the superiority of the proposed method against existing state-of-the-art ( SOTA ) approaches. Ablation studies are conducted to analyze its internal mechanism. Finally, the inference speed and power consumption are evaluated on an embedded Raspberry Pi Model 3 B plus platform.

Förderung

  • Natural Science Foundation of Jiangsu Province
  • National Nature Science Foundation of China
  • Industry Academia Cooperation Innovation Fund Projection of Jiangsu Province

Zitieren

APA

Huang, W., Zhang, L., Wang, S., Wu, H., & Song, A. (2023). Deep Ensemble Learning for Human Activity Recognition Using Wearable Sensors via Filter Activation. ACM Transactions on Embedded Computing Systems, 22(1), 1-23. https://doi.org/10.1145/3551486

Vancouver

Huang W, Zhang L, Wang S, Wu H, Song A. Deep Ensemble Learning for Human Activity Recognition Using Wearable Sensors via Filter Activation. ACM Transactions on Embedded Computing Systems. 2023;22(1):1-23. doi:10.1145/3551486

BibTeX
@article{Huang2023,
  author = {Huang, Wenbo and Zhang, Lei and Wang, Shuoyuan and Wu, Hao and Song, Aiguo},
  title = {Deep Ensemble Learning for Human Activity Recognition Using Wearable Sensors via Filter Activation},
  journal = {ACM Transactions on Embedded Computing Systems},
  year = {2023},
  volume = {22},
  number = {1},
  pages = {1--23},
  doi = {10.1145/3551486}
}
Kostenlos starten →