An investigation of transfer learning for deep architectures in group activity recognition

DSpace Repository

An investigation of transfer learning for deep architectures in group activity recognition

Details

Files for download

Find Full text There are no files associated with this item..

Overview of item record
Publication Paper in proceeding
Title An investigation of transfer learning for deep architectures in group activity recognition
Author Casserfelt, Karl ; Mihailescu, Radu-Casian
Research Centre Internet of Things and People Research Centre (IOTAP)
Date 2019
English abstract
Pervasive technologies permeating our immediate surroundings provide a wide variety of means for sensing and actuating in our environment, having a great potential to impact the way we live, but also how we work. In this paper, we address the problem of activity recognition in office environments, as a means for inferring contextual information in order to automatically and proactively assists people in their daily activities. To this end we employ state-of-the-art image processing techniques and evaluate their capabilities in a real-world setup. Traditional machine learning is characterized by instances where both the training and test data share the same distribution. When this is not the case, the performance of the learned model is deteriorated. However, often times, the data is expensive or difficult to collect and label. It is therefore important to develop techniques that are able to make the best possible use of existing data sets from related domains, relative to the target domain. To this end, we further investigate in this work transfer learning techniques in deep learning architectures for the task of activity recognition in office settings. We provide herein a solution model that attains a 94% accuracy under the right conditions.
Conference
IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) (11-15 March 2019 : Kyoto, Japan)
DOI https://doi.org/10.1109/PERCOMW.2019.8730589 (link to publisher's fulltext.)
Publisher IEEE
Host/Issue 2019 IEEE International Conference On Pervasive Computing and Communications Workshops (Percom Workshops);
Series/Issue Proceedings of the ... IEEE International Conference on Pervasive Computing and Communications
ISSN 2474-2503
ISBN 978-1-5386-9151-9
Language eng (iso)
Subject Computer Science
Machine learning
Activity recognition
Technology
Research Subject Categories::TECHNOLOGY
Handle http://hdl.handle.net/2043/30635 Permalink to this page
Link to publication in DiVA Find this research publication in DiVA.
Facebook

This item appears in the following Collection(s)

Details

Search


Browse

My Account

Statistics