ConvAE-LSTM: Convolutional Autoencoder Long Short-Term Memory Network for Smartphone-Based Human Activity Recognition

Thakur, Dipanwita, Biswas, Suparna, Ho, Edmond and Chattopadhyay, Samiran (2022) ConvAE-LSTM: Convolutional Autoencoder Long Short-Term Memory Network for Smartphone-Based Human Activity Recognition. IEEE Access, 10. pp. 4137-4159. ISSN 2169-3536

[img]
Preview
Text
AAM.pdf - Accepted Version
Available under License Creative Commons Attribution 4.0.

Download (1MB) | Preview
[img]
Preview
Text
ConvAE-LSTM_Convolutional_Autoencoder_Long_Short-Term_Memory_Network_for_Smartphone-Based_Human_Activity_Recognition.pdf - Published Version
Available under License Creative Commons Attribution 4.0.

Download (2MB) | Preview
Official URL: https://doi.org/10.1109/ACCESS.2022.3140373

Abstract

The self-regulated recognition of human activities from time-series smartphone sensor data is a growing research area in smart and intelligent health care. Deep learning (DL) approaches have exhibited improvements over traditional machine learning (ML) models in various domains, including human activity recognition (HAR). Several issues are involved with traditional ML approaches; these include handcrafted feature extraction, which is a tedious and complex task involving expert domain knowledge, and the use of a separate dimensionality reduction module to overcome overfitting problems and hence provide model generalization. In this article, we propose a DL-based approach for activity recognition with smartphone sensor data, i.e., accelerometer and gyroscope data. Convolutional neural networks (CNNs), autoencoders (AEs), and long short-term memory (LSTM) possess complementary modeling capabilities, as CNNs are good at automatic feature extraction, AEs are used for dimensionality reduction and LSTMs are adept at temporal modeling. In this study, we take advantage of the complementarity of CNNs, AEs, and LSTMs by combining them into a unified architecture. We explore the proposed architecture, namely, “ConvAE-LSTM”, on four different standard public datasets (WISDM, UCI, PAMAP2, and OPPORTUNITY). The experimental results indicate that our novel approach is practical and provides relative smartphone-based HAR solution performance improvements in terms of computational time, accuracy, F1-score, precision, and recall over existing state-of-the-art methods.

Item Type: Article
Additional Information: Funding information: 10.13039/501100000288-Royal Society International Exchanges Grant (Grant Number: IES/R1 191147)
Uncontrolled Keywords: Deep Learning, Human activity recognition, Smartphone Sensors, Autoencoder
Subjects: G400 Computer Science
G900 Others in Mathematical and Computing Sciences
Department: Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User: Rachel Branson
Date Deposited: 07 Jan 2022 10:11
Last Modified: 18 Jan 2022 14:15
URI: http://nrl.northumbria.ac.uk/id/eprint/48094

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics