Browse by author
Lookup NU author(s): Nils Hammerla,
Dr Thomas Ploetz
This is the authors' accepted manuscript of a conference proceedings (inc. abstract) that has been published in its final definitive form by AAAI Press / International Joint Conferences on Artificial Intelligence, 2016.
For re-use rights please refer to the publisher's terms and conditions.
Human activity recognition (HAR) in ubiquitous computing is beginning to adopt deep learning to substitute for well-established analysis techniques that rely on hand-crafted feature extraction and classification methods. However, from these isolated applications of custom deep architectures it is difficult to gain an overview of their suitability for problems ranging from the recognition of manipulative gestures to the segmentation and identification of physical activities like running or ascending stairs. In this paper we rigorously explore deep, convolutional, and recurrent approaches across three representative datasets that contain movement data captured with wearable sensors. We describe how to train recurrent approaches in this setting, introduce a novel regularisation approach, and illustrate how they outperform the state-of-the-art on a large benchmark dataset. We investigate the suitability of each model for HAR, across thousands of recognition experiments with randomly sampled model configurations, explore the impact of hyper parameters using the fANOVA framework, and provide guidelines for the practitioner who wants to apply deep learning in their problem setting.
Author(s): Hammerla N, Halloran S, Ploetz T
Editor(s): Subbarao Kambhampati
Publication type: Conference Proceedings (inc. Abstract)
Publication status: Published
Conference Name: Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence
Year of Conference: 2016
Online publication date: 15/07/2016
Acceptance date: 05/04/2016
Date deposited: 04/05/2016
Publisher: AAAI Press / International Joint Conferences on Artificial Intelligence
Notes: arxiv version here: http://arxiv.org/abs/1604.08880
Library holdings: Search Newcastle University Library for this item