Deep CNN-GRU based human activity recognition with automatic feature extraction using smartphone and wearable sensors

Mst Alema Khatun, Mohammad Abu Yousuf, Mohammad Ali Moni

Research output: Book chapter/Published conference paperConference paperpeer-review

7 Citations (Scopus)

Abstract

This article describes a method to Human Activity Recognition (HAR) challenges based on data from wearable and smartphone sensors. We introduced a deep learning model and recognition system that is a combination of CNN (Convolutional Neural Network) and GRU (Gated Recurrent Unit) to improve results. Preferably, the data have been collected from several wearables as the participants go about their everyday activities. The convolutional neural network (CNN) deployed to improve the extraction of features at various scales. The derived attributes are then inserted into the gated recurrent unit (GRU), which labels features and enhances feature representation by understanding temporal connections. The CNN-GRU model uses a fully inte-grated (FC) layer, which is employed to hook up the feature maps with the classification standard. Three publicly accessible datasets, UCIHAR, OPPORTUNITY, and MHEALTH, were used to test the model's performance, with accuracy rates of 98.74%, 99.05%, and 99.53%, respectively. The outcomes show that the proposed model transcends some of the notified results in terms of activity detection.

Original languageEnglish
Title of host publication3rd International Conference on Electrical, Computer and Communication Engineering, ECCE 2023
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages6
ISBN (Electronic)9798350345360
ISBN (Print)9798350345377 (Print on demand)
DOIs
Publication statusPublished - 2023
Event3rd International Conference on Electrical, Computer and Communication Engineering 2023: ECCE 2023 - Chittagong University of Engineering & Technology, Chittagong, Bangladesh
Duration: 23 Feb 202325 Feb 2023
https://www.aconf.org/conf_186189.html (Conference website)
https://ieeexplore-ieee-org.ezproxy.csu.edu.au/xpl/conhome/10101485/proceeding (Conference proceedings)
https://ieeexplore-ieee-org.ezproxy.csu.edu.au/stamp/stamp.jsp?tp=&arnumber=10101509 (Organising chair message)

Publication series

NameInternational Conference on Electrical, Computer and Communication Engineering, ECCE 2023
PublisherIEEE
Volume3

Conference

Conference3rd International Conference on Electrical, Computer and Communication Engineering 2023
Country/TerritoryBangladesh
CityChittagong
Period23/02/2325/02/23
OtherChittagong University of Engineering & Technology (CUET) is one of the leading public universities of Bangladesh- situated in the countryside- 25 km away from the heart of the port city Chittagong. This university is playing a pioneering role in higher education, research and development in the field of engineering and applied sciences. The faculty of Electrical and Computer Engineering (ECE), CUET is going to organize the 3rd International Conference on Electrical, Computer and Communication Engineering (ECCE) on February 2023 in CUET, Bangladesh. The goal of this conference is to bring together the leading academic scientists, researchers and scholars in various fields of Electrical, Computer and Communication Engineering around the world to exchange new ideas, share knowledge and explore recent developments in contemporary technologies. Authors are welcome to submit their original research contributions addressing the conference theme.
Internet address

Fingerprint

Dive into the research topics of 'Deep CNN-GRU based human activity recognition with automatic feature extraction using smartphone and wearable sensors'. Together they form a unique fingerprint.

Cite this