EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Achieving More with Less: A Lightweight Deep Learning Solution for Advanced Human Activity Recognition (HAR)

Sarab AlMuhaideb iD, Lama AlAbdulkarim, Deemah Mohammed AlShahrani, Hessah AlDhubaib, Dalal Emad AlSadoun

Sensors · 22.08.2024 · 24 (16) · 5436

DOI: 10.3390/s24165436 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 22.08.2024. Verfasst von Sarab AlMuhaideb und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, College of Computer and Information Sciences, King Saud University, P.O. Box 266, Riyadh 11362, Saudi Arabia. Hauptthemen laut MEDLINE: Deep Learning, Human Activities. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Human activity recognition (HAR) is a crucial task in various applications, including healthcare, fitness, and the military. Deep learning models have revolutionized HAR, however, their computational complexity, particularly those involving BiLSTMs, poses significant challenges for deployment on resource-constrained devices like smartphones. While BiLSTMs effectively capture long-term dependencies by processing inputs bidirectionally, their high parameter count and computational demands hinder practical applications in real-time HAR. This study investigates the approximation of the computationally intensive BiLSTM component in a HAR model by using a combination of alternative model components and data flipping augmentation. The proposed modifications to an existing hybrid model architecture replace the BiLSTM with standard and residual LSTM, along with convolutional networks, supplemented by data flipping augmentation to replicate the context awareness typically provided by BiLSTM networks. The results demonstrate that the residual LSTM (ResLSTM) model achieves superior performance while maintaining a lower computational complexity compared to the traditional BiLSTM model. Specifically, on the UCI-HAR dataset, the ResLSTM model attains an accuracy of 96.34% with 576,702 parameters, outperforming the BiLSTM model’s accuracy of 95.22% with 849,534 parameters. On the WISDM dataset, the ResLSTM achieves an accuracy of 97.20% with 192,238 parameters, compared to the BiLSTM’s 97.23% accuracy with 283,182 parameters, demonstrating a more efficient architecture with minimal performance trade-off. For the KU-HAR dataset, the ResLSTM model achieves an accuracy of 97.05% with 386,038 parameters, showing comparable performance to the BiLSTM model’s 98.63% accuracy with 569,462 parameters, but with significantly fewer parameters.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningHuman ActivitiesHumansNeural Networks, ComputerAlgorithmsSmartphone

Stichwörter der Autor:innen

Inertial measurement unitconvolutional neural networks (CNNs)data augmentationdeep learninghuman activity recognition (HAR)lightweight modelslong short-term memory (LSTM)sensor data

Autor:innen und Institutionen

  • Department of Computer Science, College of Computer and Information Sciences, King Saud University, P.O. Box 266, Riyadh 11362, Saudi Arabia.

ORCID-Profile: Sarab AlMuhaideb

Zitieren

APA

AlMuhaideb, S., AlAbdulkarim, L., AlShahrani, D. M., AlDhubaib, H., & AlSadoun, D. E. (2024). Achieving More with Less: A Lightweight Deep Learning Solution for Advanced Human Activity Recognition (HAR). Sensors, 24(16), 5436. https://doi.org/10.3390/s24165436

Vancouver

AlMuhaideb S, AlAbdulkarim L, AlShahrani DM, AlDhubaib H, AlSadoun DE. Achieving More with Less: A Lightweight Deep Learning Solution for Advanced Human Activity Recognition (HAR). Sensors. 2024;24(16):5436. doi:10.3390/s24165436

BibTeX
@article{AlMuhaideb2024,
  author = {AlMuhaideb, Sarab and AlAbdulkarim, Lama and AlShahrani, Deemah Mohammed and AlDhubaib, Hessah and AlSadoun, Dalal Emad},
  title = {Achieving More with Less: A Lightweight Deep Learning Solution for Advanced Human Activity Recognition (HAR)},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {16},
  pages = {5436},
  doi = {10.3390/s24165436}
}
Kostenlos starten →