Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.3
3.7
Journals
Bioengineering
Special Issues
Intelligent Systems for Human Action Recognition
share announcement

Intelligent Systems for Human Action Recognition

A special issue of Bioengineering (ISSN 2306-5354). This special issue belongs to the section "Biosignal Processing".

Deadline for manuscript submissions: closed (31 December 2025) | Viewed by 8171

Special Issue Editors

Dr. Mondher Bouazizi

E-Mail Website
Guest Editor
Faculty of Science and Technology, Keio University, Yokohama, Japan
Interests: information technology; computer science; data mining; image processing; deep learning; healthcare; action recognition
Special Issues, Collections and Topics in MDPI journals
Dr. Yue Yin

E-Mail Website
Guest Editor
Faculty of Science and Technology, Keio University, Yokohama, Japan
Interests: information technology; computer science; semantic communications; wireless caching networks
Prof. Dr. Tomoaki Ohtsuki

E-Mail Website
Guest Editor
Department of Information and Computer Science, Keio University, Yokohama 223-8522, Japan
Interests: artificial intelligence; wireless communications; biomedical engineering; data science
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Human action recognition (HAR) has become an essential area of research with significant implications for various fields, including surveillance, healthcare, sports analytics, and human–computer interaction. This Special Issue aims to collate the latest research and developments in HAR systems, highlighting innovative methodologies, applications, and interdisciplinary approaches.

The objective of this Special Issue is to provide a comprehensive platform for researchers, practitioners, and industry professionals to present their latest findings, share insights, and discuss the future directions of intelligent systems in the field of human action recognition. This Special Issue will cover theoretical contributions, practical implementations, and case studies, fostering a deeper understanding and advancing the state of the art in HAR.

We invite submissions focused on a wide range of topics related to intelligent systems for human action recognition, including, but not limited to, the following:

  • Sensor-Based HAR: Utilization of wearable sensors, IoT devices, and multimodal sensor fusion for accurate action recognition.
  • Computer Vision-Based HAR: Techniques for action recognition using video analysis, image processing, and pattern recognition.
  • Real-Time HAR Systems: Development and optimization of real-time HAR systems for various applications.
  • Human–Robot Interaction: HAR systems enabling intuitive and effective interactions between humans and robots.
  • Activity and Gesture Recognition: Techniques for recognizing specific activities and gestures in various contexts.
  • Sports and Performance Analysis: HAR for sports training, performance enhancement, and injury prevention.
  • Security and Surveillance: Implementation of HAR in public safety, anomaly detection, and security systems.
  • Multimodal HAR: Combining visual, audio, and other sensory inputs for enhanced action recognition accuracy.
  • Transfer Learning and Domain Adaptation: Applying HAR models across different domains and environments.
  • Sensor Technology for HAR: Advances in sensor technologies and their applications in HAR.
  • Healthcare Applications: HAR in monitoring and assisting elderly care, rehabilitation, and physical therapy.
  • Rehabilitation and Monitoring Applications: HAR systems for rehabilitation, patient monitoring, and healthcare assistance.
  • Behavior Analysis: Analyzing human behavior patterns for applications in psychology, social sciences, and public health.

Researchers and practitioners are invited to submit their original research articles, review papers, and case studies. All submissions will undergo a rigorous peer review process to ensure that the papers are of a high quality and relevant to the content.

Dr. Mondher Bouazizi
Dr. Yue Yin
Prof. Dr. Tomoaki Ohtsuki
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 250 words) can be sent to the Editorial Office for assessment.

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. Bioengineering is an international peer-reviewed open access monthly 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 2700 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

  • wearable sensors
  • IoT devices
  • action recognition
  • computer vision
  • video analysis
  • image processing
  • pattern recognition
  • human–robot interaction
  • healthcare
  • biomedical sensing
  • biosignal processing
  • signal processing
  • activity detection
  • deep learning
  • AI

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (5 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

Jump to: Review

14 pages, 788 KB  
Article
Trunk Kinematics in Writhing and Fidgety Movements: A Pilot Study on Early Postural Control in Infants Using Computer Vision
by Lucía Fernanda Flores-Santy, Karina Elizabeth Flores Santy and Juan Pablo Hervás-Pérez
Bioengineering 2026, 13(1), 91; https://doi.org/10.3390/bioengineering13010091 - 13 Jan 2026
Viewed by 473
Abstract
Background: General Movement Assessment is a strong early predictor of adverse neurodevelopmental outcomes but remains qualitative and examiner-dependent. Quantitative, video-based kinematic analysis may complement General Movement Assessment by providing objective, scalable metrics. Methods: In this pilot study, a computer–vision-based pipeline was [...] Read more.
Background: General Movement Assessment is a strong early predictor of adverse neurodevelopmental outcomes but remains qualitative and examiner-dependent. Quantitative, video-based kinematic analysis may complement General Movement Assessment by providing objective, scalable metrics. Methods: In this pilot study, a computer–vision-based pipeline was used to extract trunk center-of-mass kinematics from video recordings of spontaneous General Movements in infants under three months corrected age during the Writhing and Fidgety stage. Two measures were derived: trunk quantity of motion and movement duration. Group differences were examined using t-tests and effect sizes, and associations with corrected age and sex were explored with correlation analyses. Results: Writhing Movements were substantially longer than Fidgety Movements, with a large effect size, whereas trunk quantity of motion did not differ meaningfully between movement types. Correlations between corrected age and both the quantity of motion and duration were small and imprecise. Sex did not moderate duration changes, but trunk motion showed a significant age–sex interaction effect. Conclusions: Video-based extraction of trunk kinematics is feasible in early infancy and reveals robust differences in GMs type duration between Writhing and Fidgety Movements. Larger longitudinal studies are needed to clarify the value of these measures as early quantitative markers of postural control and neuromotor development. Full article
(This article belongs to the Special Issue Intelligent Systems for Human Action Recognition)
►▼ Show Figures

Graphical abstract

16 pages, 1500 KB  
Article
Fallville: A Perspective on an Interactive Pedagogical Tool to Enhance Understanding and Implementation of Fall-Compliant Flooring
by Shashank Ghai and Ishan Ghai
Bioengineering 2026, 13(1), 80; https://doi.org/10.3390/bioengineering13010080 - 12 Jan 2026
Viewed by 327
Abstract
Fall-compliant flooring represents a passive fall preventative approach that has emerged as an effective intervention for reducing fall-related injuries, yet its adoption remains limited due to insufficient understanding among end-users and key stakeholders. To address this knowledge gap, this perspective article provides a [...] Read more.
Fall-compliant flooring represents a passive fall preventative approach that has emerged as an effective intervention for reducing fall-related injuries, yet its adoption remains limited due to insufficient understanding among end-users and key stakeholders. To address this knowledge gap, this perspective article provides a proof-of-concept for an interactive pedagogical tool designed to use gamification principles to improve understanding of the mechanical behavior of fall-compliant flooring. This two-part perspective article first establishes the scientific foundation through controlled ball drop experiments comparing energy dissipation between fall-compliant and standard flooring. Through video-based tracking analysis, the experiments quantified kinetic energy and force dissipation across spatial and temporal dimensions. Results revealed that fall-compliant flooring exhibits significantly superior spatiotemporal energy dissipation capabilities compared to standard flooring across both force and kinetic energy metrics. Building on these findings, the second part proposes a conceptual framework for a pedagogical tool that translates these experimental insights into an interactive learning experience that could, in future implementations, allow users to conduct hands-on ball drop activities supported by real-time scientific explanations. This approach transforms complex biomechanical concepts into accessible, engaging learning experiences. By combining experiential learning with gamified elements, this tool, termed “Fallville”, has the potential to increase fall-injury prevention awareness, deepen understanding of fall-compliant flooring mechanisms, and ultimately accelerate adoption of this proven safety intervention in healthcare and residential settings. Full article
(This article belongs to the Special Issue Intelligent Systems for Human Action Recognition)
►▼ Show Figures

Figure 1

10 pages, 477 KB  
Article
Evaluation of the Validity and Reliability of NeuroSkin’s Wearable Sensor Gait Analysis Device in Healthy Individuals
by Maël Descollonges, Baptiste Moreau, Nicolas Feppon, Oussama Abdoun, Perrine Séguin, Lana Popovic-Maneski, Julie Di Marco and Amine Metani
Bioengineering 2025, 12(9), 960; https://doi.org/10.3390/bioengineering12090960 - 6 Sep 2025
Viewed by 1706
Abstract
Gait analysis plays a crucial role in assessing and monitoring the progress of individuals undergoing rehabilitation. This preliminary validation study aims to compare the performance of a new wearable system, NeuroSkin®, equipped with embedded sensors (inertial measurement unit and pressure sensors), [...] Read more.
Gait analysis plays a crucial role in assessing and monitoring the progress of individuals undergoing rehabilitation. This preliminary validation study aims to compare the performance of a new wearable system, NeuroSkin®, equipped with embedded sensors (inertial measurement unit and pressure sensors), with the non-wearable gold standard, GAITRite®, in assessing spatio-temporal parameters during gait. Data was collected from nine healthy participants wearing the NeuroSkin while walking on the GAITRite walkway. Temporal parameters were calculated using the pressure sensors of the NeuroSkin® to detect heel strike (HS) and toe off (TO) on both sides. Distances were calculated using vertical hip acceleration with an inverted pendulum method. We found that the level of agreement between NeuroSkin® and GAITRite® measures was excellent for speed, cadence, as well as length and duration of stride and step (lower bound of intraclass correlation coefficients (ICCs) > 0.95), and moderate to excellent for stance and swing durations (ICC > 0.5). These levels of agreement are comparable to the known test–retest reliability of GAITRite® measures. These results demonstrate the potential of NeuroSkin® as an embedded gait assessment system for healthy subjects. As this study was conducted exclusively in healthy adults, the results are not directly generalizable to clinical populations. Thus, future studies are needed to investigate its use in patients. Full article
(This article belongs to the Special Issue Intelligent Systems for Human Action Recognition)
►▼ Show Figures

Figure 1

22 pages, 3735 KB  
Article
Non-Contact Cross-Person Activity Recognition by Deep Metric Ensemble Learning
by Chen Ye, Siyuan Xu, Zhengran He, Yue Yin, Tomoaki Ohtsuki and Guan Gui
Bioengineering 2024, 11(11), 1124; https://doi.org/10.3390/bioengineering11111124 - 7 Nov 2024
Cited by 2 | Viewed by 1641
Abstract
In elderly monitoring or indoor intrusion detection, the recognition of human activity is a key task. Owing to several strengths of Wi-Fi-based devices, including their non-contact and privacy protection, these devices have been widely applied in the area of smart homes. By the [...] Read more.
In elderly monitoring or indoor intrusion detection, the recognition of human activity is a key task. Owing to several strengths of Wi-Fi-based devices, including their non-contact and privacy protection, these devices have been widely applied in the area of smart homes. By the deep learning technique, numerous Wi-Fi-based activity recognition methods can realize satisfied recognitions, however, these methods may fail to recognize the activities of an unknown person without the learning process. In this study, using channel state information (CSI) data, a novel cross-person activity recognition (CPAR) method is proposed by a deep learning approach with generalization capability. Combining one of the state-of-the-art deep neural networks (DNNs) used in activity recognition, i.e., attention-based bi-directional long short-term memory (ABLSTM), the snapshot ensemble is the first to be adopted to train several base-classifiers for enhancing the generalization and practicability of recognition. Second, to discriminate the extracted features, metric learning is further introduced by using the center loss, obtaining snapshot ensemble-used ABLSTM with center loss (SE-ABLSTM-C). In the experiments of CPAR, the proposed SE-ABLSTM-C method markedly improved the recognition accuracies to an application level, for seven categories of activities. Full article
(This article belongs to the Special Issue Intelligent Systems for Human Action Recognition)
►▼ Show Figures

Graphical abstract

Review

Jump to: Research

15 pages, 551 KB  
Review
Virtual and Augmented Reality for Chronic Musculoskeletal Rehabilitation: A Systematic Review and Exploratory Meta-Analysis
by Theodora Plavoukou, Pantelis Staktopoulos, Georgios Papagiannis, Dimitrios Stasinopoulos and George Georgoudis
Bioengineering 2025, 12(7), 745; https://doi.org/10.3390/bioengineering12070745 - 8 Jul 2025
Cited by 2 | Viewed by 2890
Abstract
Background: Chronic musculoskeletal disorders (CMDs) represent a leading cause of global disability and diminished quality of life, and they are often resistant to conventional physiotherapy. Emerging technologies such as virtual reality (VR), augmented reality (AR), and exergaming are increasingly used to enhance rehabilitation [...] Read more.
Background: Chronic musculoskeletal disorders (CMDs) represent a leading cause of global disability and diminished quality of life, and they are often resistant to conventional physiotherapy. Emerging technologies such as virtual reality (VR), augmented reality (AR), and exergaming are increasingly used to enhance rehabilitation outcomes, yet their comparative effectiveness remains unclear. Objective: To systematically evaluate the effectiveness of VR, AR, and exergaming interventions in improving pain, function, balance, and psychological outcomes among adults with CMDs. Methods: This systematic review and exploratory meta-analysis followed PRISMA 2020 guidelines and was prospectively registered (PROSPERO: CRD42024589007). A structured search was conducted in PubMed, Cochrane CENTRAL, Scopus, and PEDro (up to 1 May 2025). Eligible studies were randomized controlled trials (RCTs) involving adults (≥18 years) with CMDs receiving VR, AR, or exergaming-based rehabilitation. Risk of bias was assessed using the PEDro scale and the Downs and Black checklist. Where feasible, standardized mean differences (SMDs) for pain outcomes were pooled using a random-effects model. Results: Thirteen RCTs (n = 881 participants) met the inclusion criteria. Interventions spanned immersive VR, AR overlays, exergaming platforms (e.g., Kinect, Wii), and motion-tracking systems. Pain, function, and quality of life improved in most studies. An exploratory meta-analysis of eight RCTs (n = 610) yielded a significant pooled effect favoring VR/AR interventions for pain reduction (SMD = −1.14; 95% CI: −1.63 to −0.75; I2 = 0%). Exergaming showed consistent improvements in physical performance, while immersive VR was more effective for kinesiophobia and psychological outcomes. AR was underrepresented, with only one study. Risk of bias was generally low; however, publication bias could not be excluded due to limited funnel plot power (n < 10). Conclusions: VR, AR, and exergaming are effective adjuncts to conventional rehabilitation for CMDs, improving pain and function with high patient adherence. Nevertheless, gaps in long-term data, economic evaluation, and modality comparison persist. Future RCTs should address these limitations through standardized, inclusive, and longitudinal design. Full article
(This article belongs to the Special Issue Intelligent Systems for Human Action Recognition)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-5
Back to TopTop