AutoGCN-Toward Generic Human Activity Recognition With Neural Architecture Search

This paper introduces AutoGCN, a generic Neural Architecture Search (NAS) algorithm for Human Activity Recognition (HAR) using Graph Convolution Networks (GCNs). HAR has enjoyed increased attention due to advances in deep learning, increased data availability, and enhanced computational capabilities...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access Vol. 12; pp. 39505 - 39516
Main Authors: Tempel, Felix, Ihlen, Espen Alexander F., Strumke, Inga
Format: Journal Article
Language:English
Published: Piscataway IEEE 2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Algorithms
Architecture
AutoML
Buildings
Computer architecture
Convolutional neural networks
Datasets
graph convolution networks
Human activity recognition
Machine learning
Neural architecture search
Neural networks
Search process
Task analysis
ISSN:2169-3536, 2169-3536
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper introduces AutoGCN, a generic Neural Architecture Search (NAS) algorithm for Human Activity Recognition (HAR) using Graph Convolution Networks (GCNs). HAR has enjoyed increased attention due to advances in deep learning, increased data availability, and enhanced computational capabilities. Concurrently, GCNs have shown promising abilities in modeling relationships between body key points in a skeletal graph. Typically, domain experts develop dataset-specific GCN-based methods, which limits their applicability beyond the specific context. AutoGCN seeks to address this limitation by simultaneously searching for the ideal hyperparameters and architecture combination within a versatile search space using a reinforcement controller while balancing optimal exploration and exploitation behavior with a knowledge reservoir during the search process. We conduct extensive experiments on two large datasets focused on skeleton-based action recognition to assess the proposed algorithm's performance. Our experimental results demonstrate the effectiveness of AutoGCN in constructing optimal GCN architectures for HAR, outperforming conventional NAS and GCN methods, as well as random search. These findings highlight the significance of a diverse search space and an expressive input representation to achieve good model performance and generalizability.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2024.3377103