A Lightweight Deep Human Activity Recognition Algorithm Using Multiknowledge Distillation

Human activity recognition (HAR) is crucial in fields such as human-computer interaction, motion estimation, and intelligent transportation. Yet, attaining high accuracy in HAR, especially in scenarios limited by computing resources, poses a considerable challenge. This article presents Stage-Memory...

Full description

Saved in:
Bibliographic Details
Published in:IEEE sensors journal 2024-10, Vol.24 (19), p.31495-31511
Main Authors: Chen, Runze, Luo, Haiyong, Zhao, Fang, Meng, Xuechun, Xie, Zhiqing, Zhu, Yida
Format: Article
Language:English
Subjects:
Algorithms
Artificial neural network
Computational modeling
Computing costs
Deep learning
Economic models
Energy consumption
Energy costs
Feature extraction
Human activity recognition
human activity recognition (HAR)
Human motion
Motion simulation
multiknowledge distillation
Performance degradation
Performance evaluation
Sensor arrays
Sensors
Task analysis
Training
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Human activity recognition (HAR) is crucial in fields such as human-computer interaction, motion estimation, and intelligent transportation. Yet, attaining high accuracy in HAR, especially in scenarios limited by computing resources, poses a considerable challenge. This article presents Stage-Memory-Logits Distillation (SMLDist), a framework designed to build highly customizable HAR models that achieve optimal performance under various resource constraints. SMLDist prioritizes frequency-related features in its distillation process to bolster HAR classification robustness. We also introduce an auto-search mechanism within heterogeneous classifiers to boost the performance further. Our evaluation addresses the challenges of generalizing across users, sensor placements, and recognizing a wide array of activity modes. Models crafted with SMLDist, leveraging a teacher-based approach that achieves a 40%-50% reduction in operational expenditure, surpass the performance of existing state-of-the-art architectures. When assessing computational costs and energy consumption on the Jetson Xavier AGX platform, SMLDist-based models show strong economic and environmental sustainability advantages. Our results indicate that SMLDist effectively alleviates the performance degradation typically associated with limited computational resources, underscoring its significant theoretical and practical contributions to the field of HAR.
ISSN:1530-437X
1558-1748
DOI:10.1109/JSEN.2024.3443308