Movement Representation Learning for Pain Level Classification DOI
Temitayo Olugbade, Amanda C de C Williams, Nicolas Gold

et al.

IEEE Transactions on Affective Computing, Journal Year: 2023, Volume and Issue: 15(3), P. 1303 - 1314

Published: Nov. 20, 2023

Self-supervised learning has shown value for uncovering informative movement features human activity recognition. However, there been minimal exploration of this approach affect recognition where availability large labelled datasets is particularly limited. In paper, we propose a P-STEMR (Parallel Space-Time Encoding Movement Representation) architecture with the aim addressing gap and specifically leveraging higher pain-level classification. We evaluated analyzed using three different across four sets experiments. found statistically significant increase in average F1 score to 0.84 pain level classification two classes based on compared use hand-crafted features. This suggests that it capable representations transferring these from data captured lab settings levels messier real-world data. further efficacy transfer between can be undermined by dissimilarities population groups due impairments behaviour motion primitives (e.g. rotation versus flexion). Future work should investigate how effect differences could minimized so healthy people more valuable learning.

Language: Английский

Sensing behavior change in chronic pain: a scoping review of sensor technology for use in daily life DOI Creative Commons
Diego Vitali, Temitayo Olugbade, Christopher Eccleston

et al.

Pain, Journal Year: 2024, Volume and Issue: 165(6), P. 1348 - 1360

Published: Jan. 23, 2024

Technology offers possibilities for quantification of behaviors and physiological changes relevance to chronic pain, using wearable sensors devices suitable data collection in daily life contexts. We conducted a scoping review passive sensor technologies that sample psychological interest including social situations. Sixty articles met our criteria from the 2783 citations retrieved searching. Three-quarters recruited people were with mostly musculoskeletal, remainder acute or episodic pain; those pain had mean age 43 (few studies sampled adolescents children) 60% women. Thirty-seven performed laboratory clinical settings settings. Most used only 1 type technology, 76 types overall. The commonest was accelerometry (mainly contexts), followed by motion capture settings), smaller number collecting autonomic activity, vocal signals, brain activity. Subjective self-report provided "ground truth" mood, other variables, but often at different timescale automatically collected data, many reported weak relationships between technological relevant constructs, instance, fear movement muscle There relatively little discussion practical issues: frequency sampling, missing human reasons, users' experience, particularly when users did not receive any form. conclude some suggestions content process future this field.

Language: Английский

Citations

9
Touch Technology in Affective Human–, Robot–, and Virtual–Human Interactions: A Survey DOI
Temitayo Olugbade, Liang He, Perla Maiolino

et al.

Proceedings of the IEEE, Journal Year: 2023, Volume and Issue: 111(10), P. 1333 - 1354

Published: May 22, 2023

Given the importance of affective touch in human interactions, technology designers are increasingly attempting to bring this modality core interactive technology. Advances haptics and touch-sensing have been critical fostering interest area. In survey, we review how is investigated enhance support experience with or through We explore question across three different research areas highlight their epistemology, main findings, challenges that persist. First, human–computer interaction literature understand it has applied mediation human–human its roles other interactions particularly oneself, augmented objects/media, affect-aware devices. further datasets methods for automatic detection interpretation addition, discuss modalities expressions both humans these interactions. Second, separately explored human–robot real-human–virtual-human where technical encountered types aimed at different. conclude a discussion gaps emerge from steer directions advancing recognition systems. our discussion, also raise ethical issues should be considered responsible innovation growing

Language: Английский

Citations

18
Deep learning for computer vision based activity recognition and fall detection of the elderly: a systematic review DOI Creative Commons
F. Xavier Gaya-Morey, Cristina Manresa-Yee, José María Buades Rubio

et al.

Applied Intelligence, Journal Year: 2024, Volume and Issue: 54(19), P. 8982 - 9007

Published: July 8, 2024

Abstract As the proportion of elderly individuals in developed countries continues to rise globally, addressing their healthcare needs, particularly preserving autonomy, is paramount concern. A growing body research focuses on Ambient Assisted Living (AAL) systems, aimed at alleviating concerns related independent living elderly. This systematic review examines literature pertaining fall detection and Human Activity Recognition (HAR) for elderly, two critical tasks ensuring safety when alone. Specifically, this emphasizes utilization Deep Learning (DL) approaches computer vision data, reflecting current trends field. comprehensive search yielded 2,616 works from five distinct sources, spanning years 2019 2023 (inclusive). From pool, 151 relevant were selected detailed analysis. The scrutinizes employed DL models, datasets, hardware configurations, with particular emphasis aspects such as privacy preservation real-world deployment. main contribution study lies synthesis recent advancements DL-based HAR providing insights into state-of-the-art techniques identifying areas further improvement. Given increasing importance AAL systems enhancing quality life serves a valuable resource researchers, practitioners, policymakers involved developing implementing technologies. Graphical abstract

Language: Английский

Citations

7
Electronic skin based on natural biodegradable polymers for human motion monitoring DOI

Ruiqin Yao,

Xun Liu, Honghao Yu

et al.

International Journal of Biological Macromolecules, Journal Year: 2024, Volume and Issue: 278, P. 134694 - 134694

Published: Aug. 13, 2024

Language: Английский

Citations

6
Exploring raw data transformations on inertial sensor data to model user expertise when learning psychomotor skills DOI Creative Commons
Miguel Portaz, Alberto Corbí, Alberto Casas-Ortiz

et al.

User Modeling and User-Adapted Interaction, Journal Year: 2024, Volume and Issue: 34(4), P. 1283 - 1325

Published: April 17, 2024

Abstract This paper introduces a novel approach for leveraging inertial data to discern expertise levels in motor skill execution, specifically distinguishing between experts and beginners. By implementing transformation fusion techniques, we conduct comprehensive analysis of behaviour. Our goes beyond conventional assessments, providing nuanced insights into the underlying patterns movement. Additionally, explore potential utilising this data-driven methodology aid novice practitioners enhancing their performance. The findings showcase efficacy accurately identifying proficiency lay groundwork personalised interventions support refinement mastery. research contributes field assessment intervention strategies, with broad implications sports training, physical rehabilitation, performance optimisation across various domains.

Language: Английский

Citations

5
A Full-Body IMU-Based Motion Dataset of Daily Tasks by Older and Younger Adults DOI Creative Commons
Loreen Pogrzeba, Evelyn Muschter, Simon Hanisch

et al.

Scientific Data, Journal Year: 2025, Volume and Issue: 12(1)

Published: March 29, 2025

Abstract This dataset (named CeTI-Age-Kinematics ) fills the gap in existing motion capture (MoCap) data by recording kinematics of full-body movements during daily tasks an age-comparative sample with 32 participants two groups: older adults (66–75 years) and younger (19–28 years). The were recorded using sensor suits gloves inertial measurement units (IMUs). features 30 common elemental that are grouped into nine categories, including simulated interactions imaginary objects. Kinematic under well-controlled conditions, repetitions well-documented task procedures variations. It also entails anthropometric body measurements spatial experimental setups to enhance interpretation IMU MoCap relation characteristics situational surroundings. can contribute advancing machine learning, virtual reality, medical applications enabling detailed analyses modeling naturalistic motions their variability across a wide age range. Such technologies essential for developing adaptive systems tele-diagnostics, rehabilitation, robotic planning aim serve broad populations.

Language: Английский

Citations

0
Towards Personalized Physiotherapy through Interactive Machine Learning: A Conceptual Infrastructure Design for In-Clinic and Out-of-Clinic Support DOI
Laia Turmo Vidal, Annika Wærn, Rosa Cabanas‐Valdés

et al.

Published: April 24, 2025

Language: Английский

Citations

0
Intelligent Video Analytics for Human Action Recognition: The State of Knowledge DOI Creative Commons
Marek Kulbacki, Jakub Segen, Zenon Chaczko

et al.

Sensors, Journal Year: 2023, Volume and Issue: 23(9), P. 4258 - 4258

Published: April 25, 2023

The paper presents a comprehensive overview of intelligent video analytics and human action recognition methods. article provides an the current state knowledge in field activity recognition, including various techniques such as pose-based, tracking-based, spatio-temporal, deep learning-based approaches, visual transformers. We also discuss challenges limitations these potential modern edge AI architectures to enable real-time resource-constrained environments.

Language: Английский

Citations

9
Neural network-based Bluetooth synchronization of multiple wearable devices DOI Creative Commons
Karthikeyan Kalyanasundaram Balasubramanian,

Andrea Merello,

Giorgio Zini

et al.

Nature Communications, Journal Year: 2023, Volume and Issue: 14(1)

Published: July 25, 2023

Abstract Bluetooth-enabled wearables can be linked to form synchronized networks provide insightful and representative data that is exceptionally beneficial in healthcare applications. However, synchronization affected by inevitable variations the component’s performance from their ideal behavior. Here, we report an application-level solution embeds a Neural network analyze overcome these variations. The neural examines timing at each wearable node, recognizes time shifts, fine-tunes virtual clock make them operate unison thus achieve synchronization. We demonstrate integration of multiple Kinematics Detectors motion capture high frequency (200 Hz) could used for performing spatial temporal interpolation movement assessments. technique presented this work general independent physical layer used, it potentially applied any wireless communication protocol.

Language: Английский

Citations

7
Triaxial Force Plate With Prism Imaging and Sampling Moiré Method DOI

Ohga Nomura,

Hidetoshi Takahashi

IEEE Sensors Journal, Journal Year: 2024, Volume and Issue: 24(7), P. 9671 - 9678

Published: Feb. 27, 2024

Many studies have been conducted on the locomotion of terrestrial animals to evaluate ground reaction forces (GRFs) using a force plate. Conventional plates typically utilize strain gauges, but there are challenges in developing small plates. While with noncontact type sensors developed, these not suitable for multiaxial measurement. On other hand, sampling moiré (SM) method has garnered attention as high-resolution in-plane measurement technique. This study proposes plate capable triaxial single camera SM method. The proposed comprises plate, spring structure, 2-D grating, prism, and camera. Three directional displacements measured from images that two inclined grating (GIs) before after displacement by In this study, we designed fabricated $25\times25$ mm element resonant frequency approximately 100 Hz. independently enabled three-axis measurements, each axial resolution < 1 mN, positional error vertical remaining within ±3%. Therefore, sensor can be utilized evaluating GRFs animals.

Language: Английский

Citations

2