Toggle Main Menu Toggle Search

ePrints

Ensembles of deep LSTM Learners for Activity Recognition using Wearables

Lookup NU author(s): Dr Yu Guan, Dr Thomas Ploetz

Downloads


Licence

This is the authors' accepted manuscript of an article that has been published in its final definitive form by ACM, 2017.

For re-use rights please refer to the publisher's terms and conditions.


Abstract

Recently, deep learning (DL) methods have been introduced very successfully into human activity recognition (HAR) scenarios in ubiquitous and wearable computing. Especially the prospect of overcoming the need for manual feature design combined with superior classification capabilities render deep neural networks very attractive for real-life HAR applications. Even though DL-based approaches now outperform the state-of-the-art in a number of recognition tasks, still substantial challenges remain. Most prominently, issues with real-life datasets, typically including imbalanced datasets and problematic data quality, still limit the effectiveness of activity recognition using wearables. In this paper we tackle such challenges through Ensembles of deep Long Short Term Memory (LSTM) networks. LSTM networks currently represent the state-of-the-art with superior classification performance on relevant HAR benchmark datasets. We have developed modified training procedures for LSTM networks and combine sets of diverse LSTM learners into classifier collectives. We demonstrate that Ensembles of deep LSTM learners outperform individual LSTM networks and thus push the state-of-the-art in human activity recognition using wearables. Through an extensive experimental evaluation on three standard benchmarks (Opportunity, PAMAP2, Skoda) we demonstrate the excellent recognition capabilities of our approach and its potential for real-life applications of human activity recognition.


Publication metadata

Author(s): Guan Y, Ploetz T

Publication type: Article

Journal: Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies

Year: 2017

Volume: 1

Issue: 2

Online publication date: 30/06/2017

Acceptance date: 03/05/2017

ISSN (electronic): 2474-9567

Publisher: ACM

URL: https://doi.org/10.1145/30900761

DOI: 10.1145/30900761


Altmetrics

Altmetrics provided by Altmetric


Actions

    Link to this publication


Share