EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Human Activity Recognition Using Attention-Mechanism-Based Deep Learning Feature Combination

Morsheda Akter, Shafew Ansary, Md Al-Masrur Khan iD, Dongwan Kim

Sensors · 2023

DOI: 10.3390/s23125715 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Morsheda Akter und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronics Engineering, Dong-A University, Busan 49315, Republic of Korea. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 78-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Dong-A University research fund.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Human activity recognition (HAR) performs a vital function in various fields, including healthcare, rehabilitation, elder care, and monitoring. Researchers are using mobile sensor data (i.e., accelerometer, gyroscope) by adapting various machine learning (ML) or deep learning (DL) networks. The advent of DL has enabled automatic high-level feature extraction, which has been effectively leveraged to optimize the performance of HAR systems. In addition, the application of deep-learning techniques has demonstrated success in sensor-based HAR across diverse domains. In this study, a novel methodology for HAR was introduced, which utilizes convolutional neural networks (CNNs). The proposed approach combines features from multiple convolutional stages to generate a more comprehensive feature representation, and an attention mechanism was incorporated to extract more refined features, further enhancing the accuracy of the model. The novelty of this study lies in the integration of feature combinations from multiple stages as well as in proposing a generalized model structure with CBAM modules. This leads to a more informative and effective feature extraction technique by feeding the model with more information in every block operation. This research used spectrograms of the raw signals instead of extracting hand-crafted features through intricate signal processing techniques. The developed model has been assessed on three datasets, including KU-HAR, UCI-HAR, and WISDM datasets. The experimental findings showed that the classification accuracies of the suggested technique on the KU-HAR, UCI-HAR, and WISDM datasets were 96.86%, 93.48%, and 93.89%, respectively. The other evaluation criteria also demonstrate that the proposed methodology is comprehensive and competent compared to previous works.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningHumansAgedNeural Networks, ComputerHuman ActivitiesMachine LearningSignal Processing, Computer-Assisted

Stichwörter der Autor:innen

attention mechanismdeep learningfeature combinationhuman action recognition

Autor:innen und Institutionen

  • Department of Electronics Engineering, Dong-A University, Busan 49315, Republic of Korea.
  • Department of ICT Integrated Ocean Smart and Cities Engineering, Dong-A University, Busan 49315, Republic of Korea.

ORCID-Profile: Md Al-Masrur Khan

Förderung

  • Dong-A University research fund

Zitieren

APA

Akter, M., Ansary, S., Khan, M. A., & Kim, D. (2023). Human Activity Recognition Using Attention-Mechanism-Based Deep Learning Feature Combination. Sensors. https://doi.org/10.3390/s23125715

Vancouver

Akter M, Ansary S, Khan MA, Kim D. Human Activity Recognition Using Attention-Mechanism-Based Deep Learning Feature Combination. Sensors. 2023. doi:10.3390/s23125715

BibTeX
@article{Akter2023,
  author = {Akter, Morsheda and Ansary, Shafew and Khan, Md Al-Masrur and Kim, Dongwan},
  title = {Human Activity Recognition Using Attention-Mechanism-Based Deep Learning Feature Combination},
  journal = {Sensors},
  year = {2023},
  doi = {10.3390/s23125715}
}
Kostenlos starten →