Applying MLP-Mixer and gMLP to Human Activity Recognition
Sensors · 2025
DOI: 10.3390/s25020311 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Takeru Miyoshi und 2 weiteren Autor:innen. Beteiligte Einrichtung: Graduate School of National Science and Technology, Kanazawa University, Kanazawa 920-1192, Japan. Hauptthemen laut MEDLINE: Neural Networks, Computer, Human Activities, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The development of deep learning has led to the proposal of various models for human activity recognition (HAR). Convolutional neural networks (CNNs), initially proposed for computer vision tasks, are examples of models applied to sensor data. Recently, high-performing models based on Transformers and multi-layer perceptrons (MLPs) have also been proposed. When applying these methods to sensor data, we often initialize hyperparameters with values optimized for image processing tasks as a starting point. We suggest that comparable accuracy could be achieved with fewer parameters for sensor data, which typically have lower dimensionality than image data. Reducing the number of parameters would decrease memory requirements and computational complexity by reducing the model size. We evaluated the performance of two MLP-based models, MLP-Mixer and gMLP, by reducing the values of hyperparameters in their MLP layers from those proposed in the respective original papers. The results of this study suggest that the performance of MLP-based models is positively correlated with the number of parameters. Furthermore, these MLP-based models demonstrate improved computational efficiency for specific HAR tasks compared to representative CNNs.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Graduate School of National Science and Technology, Kanazawa University, Kanazawa 920-1192, Japan.
- National Institute of Technology, Ishikawa College, Tsubata 929-0392, Japan.
ORCID-Profile: Takeru Miyoshi, Makoto Koshino, Hidetaka Nambo
Zitieren
APA
Miyoshi, T., Koshino, M., & Nambo, H. (2025). Applying MLP-Mixer and gMLP to Human Activity Recognition. Sensors. https://doi.org/10.3390/s25020311
Vancouver
Miyoshi T, Koshino M, Nambo H. Applying MLP-Mixer and gMLP to Human Activity Recognition. Sensors. 2025. doi:10.3390/s25020311
BibTeX
@article{Miyoshi2025,
author = {Miyoshi, Takeru and Koshino, Makoto and Nambo, Hidetaka},
title = {Applying MLP-Mixer and gMLP to Human Activity Recognition},
journal = {Sensors},
year = {2025},
doi = {10.3390/s25020311}
}
EUVIMED