sensors-logo

Journal Browser

Journal Browser

Machine Learning in Human Activity Recognition

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Intelligent Sensors".

Deadline for manuscript submissions: closed (1 January 2023) | Viewed by 4669

Special Issue Editors

College of Computing, Georgia Institute of Technology, North Ave NW, Atlanta, GA 30332, USA
Interests: human activity recognition; computational behavior analysis; health informatics; machine learning; representation learning
School of Computing, Newcastle University, Newcastle upon Tyne NE1 7RU, UK
Interests: human activity recognition; computational behavior analysis; health informatics; machine learning
Sensor Technology Research Centre, University of Sussex, Sussex House, Brighton BN1 9RH, UK
Interests: human activity recognition; wearable computing; sensing; machine learning
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Human Activity Recognition (HAR) using pervasive and body-worn sensors has become a major research field with numerous practical applications. At the heart of most HAR systems lies the automated analysis of sensor readings, for which machine learning techniques are typically applied. With the explosion of research in the core machine learning area, numerous methods have been developed that are also of value for the HAR community. However, HAR comes with its own challenges for machine learning methods, such as challenging data quality, including sensor noise, faulty sensor readings, or ambiguities; often only very small datasets come with ground truth annotation; computational challenges for performing activity recognition in real time and on severely resource constrained devices; open ended activity recognition; and continuous adaptation of recognition systems, to name but a few. This Special Issue aims to provide an overview of the state-of-the-art and latest developments in the field of machine learning for human activity recognition. 

Prof. Dr. Thomas Ploetz
Dr. Yu Guan
Prof. Dr. Daniel Roggen
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Machine learning
  • Pervasive and ubiquitous computing
  • Wearable computing
  • Human computer interaction
  • Time series analysis
  • Unsupervised learning
  • Deep learning
  • Model adaptation
  • Novel application
  • Recognition paradigms

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

26 pages, 2717 KiB  
Article
Complex Deep Neural Networks from Large Scale Virtual IMU Data for Effective Human Activity Recognition Using Wearables
by Hyeokhyen Kwon, Gregory D. Abowd and Thomas Plötz
Sensors 2021, 21(24), 8337; https://doi.org/10.3390/s21248337 - 13 Dec 2021
Cited by 12 | Viewed by 3566
Abstract
Supervised training of human activity recognition (HAR) systems based on body-worn inertial measurement units (IMUs) is often constrained by the typically rather small amounts of labeled sample data. Systems like IMUTube have been introduced that employ cross-modality transfer approaches to convert videos of [...] Read more.
Supervised training of human activity recognition (HAR) systems based on body-worn inertial measurement units (IMUs) is often constrained by the typically rather small amounts of labeled sample data. Systems like IMUTube have been introduced that employ cross-modality transfer approaches to convert videos of activities of interest into virtual IMU data. We demonstrate for the first time how such large-scale virtual IMU datasets can be used to train HAR systems that are substantially more complex than the state-of-the-art. Complexity is thereby represented by the number of model parameters that can be trained robustly. Our models contain components that are dedicated to capture the essentials of IMU data as they are of relevance for activity recognition, which increased the number of trainable parameters by a factor of 1100 compared to state-of-the-art model architectures. We evaluate the new model architecture on the challenging task of analyzing free-weight gym exercises, specifically on classifying 13 dumbbell execises. We have collected around 41 h of virtual IMU data using IMUTube from exercise videos available from YouTube. The proposed model is trained with the large amount of virtual IMU data and calibrated with a mere 36 min of real IMU data. The trained model was evaluated on a real IMU dataset and we demonstrate the substantial performance improvements of 20% absolute F1 score compared to the state-of-the-art convolutional models in HAR. Full article
(This article belongs to the Special Issue Machine Learning in Human Activity Recognition)
Show Figures

Figure 1

Back to TopTop