Table of Contents Author Guidelines Submit a Manuscript
Journal of Sensors
Volume 2018, Article ID 8580959, 10 pages
https://doi.org/10.1155/2018/8580959
Research Article

Sequential Human Activity Recognition Based on Deep Convolutional Network and Extreme Learning Machine Using Wearable Sensors

1School of Mechanical Engineering & Automation, Beihang University, Beijing 100191, China
2The F.R.I. of Ministry of Public Security, Beijing 100048, China
3School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, China

Correspondence should be addressed to Shengguang Li; moc.361@nusjihs

Received 1 January 2018; Revised 29 July 2018; Accepted 6 August 2018; Published 27 September 2018

Academic Editor: Jaime Lloret

Copyright © 2018 Jian Sun et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

Human activity recognition (HAR) problems have traditionally been solved by using engineered features obtained by heuristic methods. These methods ignore the time information of the streaming sensor data and cannot achieve sequential human activity recognition. With the use of traditional statistical learning methods, results could easily plunge into the local minimum other than the global optimal and also face the problem of low efficiency. Therefore, we propose a hybrid deep framework based on convolution operations, LSTM recurrent units, and ELM classifier; the advantages are as follows: (1) does not require expert knowledge in extracting features; (2) models temporal dynamics of features; and (3) is more suitable to classify the extracted features and shortens the runtime. All of these unique advantages make it superior to other HAR algorithms. We evaluate our framework on OPPORTUNITY dataset which has been used in OPPORTUNITY challenge. Results show that our proposed method outperforms deep nonrecurrent networks by 6%, outperforming the previous reported best result by 8%. When compared with neural network using BP algorithm, testing time reduced by 38%.