sensors-logo

Journal Browser

Journal Browser

Special Issue "Activity Recognition Using Constrained IoT Devices"

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

Deadline for manuscript submissions: closed (15 July 2021).

Special Issue Editors

Dr. Ian Cleland
E-Mail Website
Guest Editor
School of Computing, Ulster University
Interests: wearable computing; activity recognition; digital health; unobtrusive sensing
Prof. Dr. Oresti Banos
E-Mail Website
Guest Editor
Research Centre for Information and Communications Technology, University of Granada (UGR), 18071 Granada, Spain
Interests: wearable, ubiquitous, and mobile computing; artificial intelligence; data mining; digital health
Special Issues and Collections in MDPI journals

Special Issue Information

Dear Colleagues,

Understanding human behavior in an automatic and non-intrusive manner constitutes an important and emerging area of research within pervasive systems. With the rapid development of the Internet of Things (IoT), combined with advances in machine/deep learning, technology-based solutions to automatically detect and model human behaviors are becoming possible. This technology can support services such as activity recognition, fall detection, behavior modelling and risk determination. Recently, there has been a move toward edge computing as a way to reduce communication latency and network communication whilst preserving privacy. Various solutions have been developed to support modelling of human behavior. In particular, deep learning algorithms have shown high performance for applications such as human activity recognition. These algorithms, however, typically require large amounts of computation for training and inference, making them unsuitable for deployment on resource-constrained edge devices. Devices in a resource-constrained environment become even more challenging when they are battery-powered, such as is the case with wearable applications, making them computationally intensive and power demanding.

This Special Issue seeks to bring together innovative research solutions in the area of behavioral modeling specifically for constrained devices. Authors are invited to submit original articles across the full development stack (hardware, system, software and applications), including architectures, techniques, tools and approaches on the device modelling of human behaviors. This may include, but is not limited to, new and novel sensing modalities (audio, vision, environment, health), strategies for data collection, annotation and labelling, personalization, sensor fusion, computational constraints reduction, extreme energy efficiency, model optimization, and federated learning, as well as examining the performance of these solutions in real-world settings with diverse populations.

Dr. Ian Cleland
Prof. Dr. Oresti Banos
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 papers will be 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 2200 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

  • behavior modelling
  • unobtrusive sensing
  • activity recognition
  • constrained devices
  • resource constrained environments
  • privacy by design
  • edge computing
  • deep learning
  • transfer learning
  • TinyML
  • ethical issues
  • context awareness
  • wearable computing
  • pervasive computing

Published Papers (2 papers)

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

Research

Article
Classification of Tennis Shots with a Neural Network Approach
Sensors 2021, 21(17), 5703; https://doi.org/10.3390/s21175703 - 24 Aug 2021
Viewed by 395
Abstract
Data analysis plays an increasingly valuable role in sports. The better the data that is analysed, the more concise training methods that can be chosen. Several solutions already exist for this purpose in the tennis industry; however, none of them combine data generation [...] Read more.
Data analysis plays an increasingly valuable role in sports. The better the data that is analysed, the more concise training methods that can be chosen. Several solutions already exist for this purpose in the tennis industry; however, none of them combine data generation with a wristband and classification with a deep convolutional neural network (CNN). In this article, we demonstrate the development of a reliable shot detection trigger and a deep neural network that classifies tennis shots into three and five shot types. We generate a dataset for the training of neural networks with the help of a sensor wristband, which recorded 11 signals, including an inertial measurement unit (IMU). The final dataset included 5682 labelled shots of 16 players of age 13–70 years, predominantly at an amateur level. Two state-of-the-art architectures for time series classification (TSC) are compared, namely a fully convolutional network (FCN) and a residual network (ResNet). Recent advances in the field of machine learning, like the Mish activation function and the Ranger optimizer, are utilized. Training with the rather inhomogeneous dataset led to an F1 score of 96% in classification of the main shots and 94% for the expansion. Consequently, the study yielded a solid base for more complex tennis analysis tools, such as the indication of success rates per shot type. Full article
(This article belongs to the Special Issue Activity Recognition Using Constrained IoT Devices)
Show Figures

Figure 1

Article
On-Device Deep Personalization for Robust Activity Data Collection
Sensors 2021, 21(1), 41; https://doi.org/10.3390/s21010041 - 23 Dec 2020
Viewed by 870
Abstract
One of the biggest challenges of activity data collection is the need to rely on users and keep them engaged to continually provide labels. Recent breakthroughs in mobile platforms have proven effective in bringing deep neural networks powered intelligence into mobile devices. This [...] Read more.
One of the biggest challenges of activity data collection is the need to rely on users and keep them engaged to continually provide labels. Recent breakthroughs in mobile platforms have proven effective in bringing deep neural networks powered intelligence into mobile devices. This study proposes a novel on-device personalization for data labeling for an activity recognition system using mobile sensing. The key idea behind this system is that estimated activities personalized for a specific individual user can be used as feedback to motivate user contribution and improve data labeling quality. First, we exploited fine-tuning using a Deep Recurrent Neural Network to address the lack of sufficient training data and minimize the need for training deep learning on mobile devices from scratch. Second, we utilized a model pruning technique to reduce the computation cost of on-device personalization without affecting the accuracy. Finally, we built a robust activity data labeling system by integrating the two techniques outlined above, allowing the mobile application to create a personalized experience for the user. To demonstrate the proposed model’s capability and feasibility, we developed and deployed the proposed system to realistic settings. For our experimental setup, we gathered more than 16,800 activity windows from 12 activity classes using smartphone sensors. We empirically evaluated the proposed quality by comparing it with a baseline using machine learning. Our results indicate that the proposed system effectively improved activity accuracy recognition for individual users and reduced cost and latency for inference for mobile devices. Based on our findings, we highlight critical and promising future research directions regarding the design of efficient activity data collection with on-device personalization. Full article
(This article belongs to the Special Issue Activity Recognition Using Constrained IoT Devices)
Show Figures

Figure 1

Back to TopTop