Wearable Sensors and Artificial Intelligence for Ergonomics

A special issue of Diagnostics (ISSN 2075-4418). This special issue belongs to the section "Point-of-Care Diagnostics and Devices".

Deadline for manuscript submissions: closed (28 February 2023) | Viewed by 17124

Special Issue Editors

Department of Advanced Medical and Surgical Sciences, University of Campania “Luigi Vanvitelli”, Piazza Luigi Miraglia, 2, 80138 Naples, Italy
Interests: biomedical engineering; biosignal and bioimage processing; ergonomics; rehabilitation engineering, gait analysis, wearable sensors; telemedicine; machine learning; biostatistics
Special Issues, Collections and Topics in MDPI journals
Department of Electrical Engineering and Information Technology, University of Naples Federico II, Via Claudio 21, 80125 Naples, Italy
Interests: machine learning; statistics; gait analysis; health technology assessment; lean six sigma; biomedical engineering
Special Issues, Collections and Topics in MDPI journals
Department of Chemical, Materials and Production Engineering, University of Naples Federico II, Piazzale Tecchio 80, 80125 Naples, Italy
Interests: biomedical engineering; bioengineering; biomedical data analysis; biomedical signal processing; drug delivery systems; biomaterials; polymer microparticles; lean six sigma in healthcare
Special Issues, Collections and Topics in MDPI journals
Institute for Biomedical and Neural Engineering, Reykjavík University, Reykjavík, Iceland
Interests: biomedical engineering; biomechanical engineering; bioengineering; clinical engineering; medical image processing; 3D modelling for surgical planning; neuroscience; tissue engineering
Special Issues, Collections and Topics in MDPI journals
Faculty of Health Promotion, Sport and Leisure Studies, University of Iceland, Stakkahlíð, 105 Reykjavík, Iceland
Interests: sports science; biomechanics; human movement; athletics
Scientific Clinical Institutes ICS Maugeri, 27100 Pavia, Italy
Interests: ergonomics; occupational ergonomics; rehabilitation; biomechanical exposure

Special Issue Information

Dear Colleagues,

Ergonomics can contribute to maximizing human well-being and efficiency of a working system that safeguards workers’ health. The development of wearable sensors capable of collecting a wide variety of relevant physiological and environmental parameters allows acquisition of signals related to the workers in a non-intrusive, automatic and continuous way. Data can be obtained through both custom-made devices (namely ad hoc ones developed by scientific researchers) and commercial wearable devices. The availability of instruments (such as wearable motion trackers, inertial measurement units, pressure sensors, eye and facial expression tracking devices, smart sensors for temperature, breathing, electrocardiography, electroencephalography, electromyography, electrodermal activity) offers a wide perspective for novel solutions in the ergonomic field.

The number of proposed techniques for data processing and analysis increases every day, and newer approaches using deep learning and classical machine learning techniques to assess the potential biomechanical risk to employees during work activities are gaining significant interest in the ergonomic field.

Consequently, this Special Issue (“Wearable sensors and machine learning for ergonomics”) aims to highlight several of the latest developments in the ergonomic/occupational medicine fields. It will help to delineate a novel emerging branch which considers wearable sensors a tool for biomechanical risk assessment and injury prevention—even through the help of the artificial intelligence—during work-, home-, sport- and leisure-related activities. We welcome submissions spanning topics across the design of novel sensors or commercial wearable technologies and the development of any novel methodology which aims to integrate quantitative physiological and environmental information— with and without the use of artificial intelligence—for those that are the main goals of the ergonomics. Both research papers and review articles will be considered.

Topics of interest include, but are not limited to, the following application fields for machine learning:

  • Ergonomics and occupational medicine.
  • Wearable sensors, motion sensors, force/pressure sensors and EMG sensors for ergonomics.
  • Sensors for well-being.
  • Smart clothes and e-textiles for ergonomic applications.
  • Activity monitoring devices and systems.
  • Machine Learning and deep learning for wearable data analysis.
  • Biomechanical risk assessment.
  • Health monitoring in working environment.
  • Work-related musculoskeletal disorders.
  • Novel design approaches for ergonomic assessment.
  • Mhealth and/or ehealth solutions for ergonomics.
  • Data processing applied to risk assessments.

Dr. Leandro Donisi
Dr. Carlo Ricciardi
Dr. Alfonso Maria Ponsiglione
Dr. Giuseppe Cesarelli
Prof. Dr. Paolo Gargiulo
Dr. Milos Petrovic
Dr. Edda Maria Capodaglio
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. Diagnostics 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

  • ergonomics
  • occupational medicine
  • biomedical signal processing
  • biomechanics
  • human activity recognition
  • inertial measurements units and sensors for IoT
  • feature extraction
  • lifting
  • machine learning
  • modeling and simulation
  • neural networks

Published Papers (8 papers)

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

Research

Jump to: Other

21 pages, 5244 KiB  
Article
On the Use of a Convolutional Block Attention Module in Deep Learning-Based Human Activity Recognition with Motion Sensors
by Sumeyye Agac and Ozlem Durmaz Incel
Diagnostics 2023, 13(11), 1861; https://doi.org/10.3390/diagnostics13111861 - 26 May 2023
Cited by 6 | Viewed by 1862
Abstract
Sensor-based human activity recognition with wearable devices has captured the attention of researchers in the last decade. The possibility of collecting large sets of data from various sensors in different body parts, automatic feature extraction, and aiming to recognize more complex activities have [...] Read more.
Sensor-based human activity recognition with wearable devices has captured the attention of researchers in the last decade. The possibility of collecting large sets of data from various sensors in different body parts, automatic feature extraction, and aiming to recognize more complex activities have led to a rapid increase in the use of deep learning models in the field. More recently, using attention-based models for dynamically fine-tuning the model features and, in turn, improving the model performance has been investigated. However, the impact of using channel, spatial, or combined attention methods of the convolutional block attention module (CBAM) on the high-performing DeepConvLSTM model, a hybrid model proposed for sensor-based human activity recognition, has yet to be studied. Additionally, since wearables have limited resources, analysing the parameter requirements of attention modules can serve as an indicator for optimizing resource consumption. In this study, we explored the performance of CBAM on the DeepConvLSTM architecture both in terms of recognition performance and the number of additional parameters required by attention modules. In this direction, the effect of channel and spatial attention, individually and in combination, were examined. To evaluate the model performance, the Pamap2 dataset containing 12 daily activities and the Opportunity dataset with its 18 micro activities were utilized. The results showed that the performance for Opportunity increased from 0.74 to 0.77 in the macro f1-score owing to spatial attention, while for Pamap2, the performance increased from 0.95 to 0.96 owing to the channel attention applied to DeepConvLSTM with a negligible number of additional parameters. Moreover, when the activity-based results were analysed, it was observed that the attention mechanism increased the performance of the activities with the worst performance in the baseline model without attention. We present a comparison with related studies that use the same datasets and show that we could achieve higher scores on both datasets by combining CBAM and DeepConvLSTM. Full article
(This article belongs to the Special Issue Wearable Sensors and Artificial Intelligence for Ergonomics)
Show Figures

Figure 1

17 pages, 7231 KiB  
Article
Study of Motion Sickness Model Based on fNIRS Multiband Features during Car Rides
by Bin Ren, Wanli Guan and Qinyu Zhou
Diagnostics 2023, 13(8), 1462; https://doi.org/10.3390/diagnostics13081462 - 18 Apr 2023
Viewed by 1052
Abstract
Motion sickness is a common physiological discomfort phenomenon during car rides. In this paper, the functional near-infrared spectroscopy (fNIRS) technique was used in real-world vehicle testing. The fNIRS technique was utilized to model the relationship between changes in blood oxygenation levels in the [...] Read more.
Motion sickness is a common physiological discomfort phenomenon during car rides. In this paper, the functional near-infrared spectroscopy (fNIRS) technique was used in real-world vehicle testing. The fNIRS technique was utilized to model the relationship between changes in blood oxygenation levels in the prefrontal cortex of passengers and motion sickness symptoms under different motion conditions. To enhance the accuracy of motion sickness classification, the study utilized principal component analysis (PCA) to extract the most significant features from the test data. Wavelet decomposition was used to extract the power spectrum entropy (PSE) features of five frequency bands highly related to motion sickness. The correlation between motion sickness and cerebral blood oxygen levels was modeled by a 6-point scale calibration for the subjective evaluation of the degree of passenger motion sickness. A support vector machine (SVM) was used to build a motion sickness classification model, achieving an accuracy of 87.3% with the 78 sets of data. However, individual analysis of the 13 subjects showed a varying range of accuracy from 50% to 100%, suggesting the presence of individual differences in the relationship between cerebral blood oxygen levels and motion sickness symptoms. Thus, the results demonstrated that the magnitude of motion sickness during the ride was closely related to the change in the PSE of the five frequency bands of cerebral prefrontal blood oxygen, but further studies are needed to investigate individual variability. Full article
(This article belongs to the Special Issue Wearable Sensors and Artificial Intelligence for Ergonomics)
Show Figures

Figure 1

17 pages, 3268 KiB  
Article
Assessing Passengers’ Motion Sickness Levels Based on Cerebral Blood Oxygen Signals and Simulation of Actual Ride Sensation
by Bin Ren and Qinyu Zhou
Diagnostics 2023, 13(8), 1403; https://doi.org/10.3390/diagnostics13081403 - 12 Apr 2023
Viewed by 1417
Abstract
(1) Background: After motion sickness occurs in the ride process, this can easily cause passengers to have a poor mental state, cold sweats, nausea, and even vomiting symptoms. This study proposes to establish an association model between motion sickness level (MSL) and cerebral [...] Read more.
(1) Background: After motion sickness occurs in the ride process, this can easily cause passengers to have a poor mental state, cold sweats, nausea, and even vomiting symptoms. This study proposes to establish an association model between motion sickness level (MSL) and cerebral blood oxygen signals during a ride. (2) Methods: A riding simulation platform and the functional near-infrared spectroscopy (fNIRS) technology are utilized to monitor the cerebral blood oxygen signals of subjects in a riding simulation experiment. The subjects’ scores on the Fast Motion sickness Scale (FMS) are determined every minute during the experiment as the dependent variable to manifest the change in MSL. The Bayesian ridge regression (BRR) algorithm is applied to construct an assessment model of MSL during riding. The score of the Graybiel scale is adopted to preliminarily verify the effectiveness of the MSL evaluation model. Finally, a real vehicle test is developed, and two driving modes are selected in random road conditions to carry out a control test. (3) Results: The predicted MSL in the comfortable mode is significantly less than the MSL value in the normal mode, which is in line with expectations. (4) Conclusions: Changes in cerebral blood oxygen signals have a huge correlation with MSL. The MSL evaluation model proposed in this study has a guiding significance for the early warning and prevention of motion sickness. Full article
(This article belongs to the Special Issue Wearable Sensors and Artificial Intelligence for Ergonomics)
Show Figures

Figure 1

12 pages, 2135 KiB  
Article
Wearable Health Technology for Preoperative Risk Assessment in Elderly Patients: The WELCOME Study
by Massimiliano Greco, Alessandra Angelucci, Gaia Avidano, Giovanni Marelli, Stefano Canali, Romina Aceto, Marta Lubian, Paolo Oliva, Federico Piccioni, Andrea Aliverti and Maurizio Cecconi
Diagnostics 2023, 13(4), 630; https://doi.org/10.3390/diagnostics13040630 - 08 Feb 2023
Cited by 6 | Viewed by 1728
Abstract
Preoperative identification of high-risk groups has been extensively studied to improve patients’ outcomes. Wearable devices, which can track heart rate and physical activity data, are starting to be evaluated for patients’ management. We hypothesized that commercial wearable devices (WD) may provide data associated [...] Read more.
Preoperative identification of high-risk groups has been extensively studied to improve patients’ outcomes. Wearable devices, which can track heart rate and physical activity data, are starting to be evaluated for patients’ management. We hypothesized that commercial wearable devices (WD) may provide data associated with preoperative evaluation scales and tests, to identify patients with poor functional capacity at increased risk for complications. We conducted a prospective observational study including seventy-year-old patients undergoing two-hour surgeries under general anesthesia. Patients were asked to wear a WD for 7 days before surgery. WD data were compared to preoperatory clinical evaluation scales and with a 6-min walking test (6MWT). We enrolled 31 patients, with a mean age of 76.1 (SD ± 4.9) years. There were 11 (35%) ASA 3–4 patients. 6MWT results averaged 328.9 (SD ± 99.5) m. Daily steps and 𝑉𝑂2𝑚𝑎𝑥 as recorded using WD and were associated with 6MWT performance (R = 0.56, p = 0.001 and r = 0.58, p = 0.006, respectively) and clinical evaluation scales. This is the first study to evaluate WD as preoperative evaluation tools; we found a strong association between 6MWT, preoperative scales, and WD data. Low-cost wearable devices are a promising tool for the evaluation of cardiopulmonary fitness. Further research is needed to validate WD in this setting. Full article
(This article belongs to the Special Issue Wearable Sensors and Artificial Intelligence for Ergonomics)
Show Figures

Figure 1

17 pages, 2740 KiB  
Article
Mathematical Framework for Wearable Devices in the Internet of Things Using Deep Learning
by Olfat M. Mirza, Hana Mujlid, Hariprasath Manoharan, Shitharth Selvarajan, Gautam Srivastava and Muhammad Attique Khan
Diagnostics 2022, 12(11), 2750; https://doi.org/10.3390/diagnostics12112750 - 10 Nov 2022
Cited by 7 | Viewed by 1557
Abstract
To avoid dire situations, the medical sector must develop various methods for quickly and accurately identifying infections in remote regions. The primary goal of the proposed work is to create a wearable device that uses the Internet of Things (IoT) to carry out [...] Read more.
To avoid dire situations, the medical sector must develop various methods for quickly and accurately identifying infections in remote regions. The primary goal of the proposed work is to create a wearable device that uses the Internet of Things (IoT) to carry out several monitoring tasks. To decrease the amount of communication loss as well as the amount of time required to wait before detection and improve detection quality, the designed wearable device is also operated with a multi-objective framework. Additionally, a design method for wearable IoT devices is established, utilizing distinct mathematical approaches to solve these objectives. As a result, the monitored parametric values are saved in a different IoT application platform. Since the proposed study focuses on a multi-objective framework, state design and deep learning (DL) optimization techniques are combined, reducing the complexity of detection in wearable technology. Wearable devices with IoT processes have even been included in current methods. However, a solution cannot be duplicated using mathematical approaches and optimization strategies. Therefore, developed wearable gadgets can be applied to real-time medical applications for fast remote monitoring of an individual. Additionally, the proposed technique is tested in real-time, and an IoT simulation tool is utilized to track the compared experimental results under five different situations. In all of the case studies that were examined, the planned method performs better than the current state-of-the-art methods. Full article
(This article belongs to the Special Issue Wearable Sensors and Artificial Intelligence for Ergonomics)
Show Figures

Figure 1

15 pages, 1598 KiB  
Article
A Logistic Regression Model for Biomechanical Risk Classification in Lifting Tasks
by Leandro Donisi, Giuseppe Cesarelli, Edda Capodaglio, Monica Panigazzi, Giovanni D’Addio, Mario Cesarelli and Francesco Amato
Diagnostics 2022, 12(11), 2624; https://doi.org/10.3390/diagnostics12112624 - 29 Oct 2022
Cited by 6 | Viewed by 1343
Abstract
Lifting is one of the most potentially harmful activities for work-related musculoskeletal disorders (WMSDs), due to exposure to biomechanical risk. Risk assessment for work activities that involve lifting loads can be performed through the NIOSH (National Institute of Occupational Safety and Health) method, [...] Read more.
Lifting is one of the most potentially harmful activities for work-related musculoskeletal disorders (WMSDs), due to exposure to biomechanical risk. Risk assessment for work activities that involve lifting loads can be performed through the NIOSH (National Institute of Occupational Safety and Health) method, and specifically the Revised NIOSH Lifting Equation (RNLE). Aim of this work is to explore the feasibility of a logistic regression model fed with time and frequency domains features extracted from signals acquired through one inertial measurement unit (IMU) to classify risk classes associated with lifting activities according to the RNLE. Furthermore, an attempt was made to evaluate which are the most discriminating features relating to the risk classes, and to understand which inertial signals and which axis were the most representative. In a simplified scenario, where only two RNLE variables were altered during lifting tasks performed by 14 healthy adults, inertial signals (linear acceleration and angular velocity) acquired using one IMU placed on the subject’s sternum during repeated rhythmic lifting tasks were automatically segmented to extract several features in the time and frequency domains. The logistic regression model fed with significant features showed good results to discriminate “risk” and “no risk” NIOSH classes with an accuracy, sensitivity and specificity equal to 82.8%, 84.8% and 80.9%, respectively. This preliminary work indicated that a logistic regression model—fed with specific inertial features extracted by signals acquired using a single IMU sensor placed on the sternum—is able to discriminate risk classes according to the RNLE in a simplified context, and therefore could be a valid tool to assess the biomechanical risk in an automatic way also in more complex conditions (e.g., real working scenarios). Full article
(This article belongs to the Special Issue Wearable Sensors and Artificial Intelligence for Ergonomics)
Show Figures

Figure 1

12 pages, 1895 KiB  
Article
The Effect of Fatigue on Lower Limb Joint Stiffness at Different Walking Speeds
by Enze Shao, Zhenghui Lu, Xuanzhen Cen, Zhiyi Zheng, Dong Sun and Yaodong Gu
Diagnostics 2022, 12(6), 1470; https://doi.org/10.3390/diagnostics12061470 - 15 Jun 2022
Cited by 6 | Viewed by 2107
Abstract
The aim of this study was to assess the stiffness of each lower limb joint in healthy persons walking at varying speeds when fatigued. The study included 24 subjects (all male; age: 28.16 ± 7.10 years; height: 1.75 ± 0.04 m; weight: 70.62 [...] Read more.
The aim of this study was to assess the stiffness of each lower limb joint in healthy persons walking at varying speeds when fatigued. The study included 24 subjects (all male; age: 28.16 ± 7.10 years; height: 1.75 ± 0.04 m; weight: 70.62 ± 4.70 kg). A Vicon three-dimensional analysis system and a force plate were used to collect lower extremity kinematic and kinetic data from the participants before and after walking training under various walking situations. Least-squares linear regression equations were utilized to evaluate joint stiffness during single-leg support. Three velocities significantly affected the stiffness of the knee and hip joint (p < 0.001), with a positive correlation. However, ankle joint stiffness was significantly lower only at maximum speed (p < 0.001). Hip stiffness was significantly higher after walking training than that before training (p < 0.001). In contrast, knee stiffness after training was significantly lower than pre-training stiffness in the same walking condition (p < 0.001). Ankle stiffness differed only at maximum speed, and it was significantly higher than pre-training stiffness (p < 0.001). Walking fatigue appeared to change the mechanical properties of the joint. Remarkably, at the maximum walking velocity in exhaustion, when the load on the hip joint was significantly increased, the knee joint’s stiffness decreased, possibly leading to joint instability that results in exercise injury. Full article
(This article belongs to the Special Issue Wearable Sensors and Artificial Intelligence for Ergonomics)
Show Figures

Figure 1

Other

Jump to: Research

21 pages, 2388 KiB  
Systematic Review
Wearable Sensors and Artificial Intelligence for Physical Ergonomics: A Systematic Review of Literature
by Leandro Donisi, Giuseppe Cesarelli, Noemi Pisani, Alfonso Maria Ponsiglione, Carlo Ricciardi and Edda Capodaglio
Diagnostics 2022, 12(12), 3048; https://doi.org/10.3390/diagnostics12123048 - 05 Dec 2022
Cited by 12 | Viewed by 4293
Abstract
Physical ergonomics has established itself as a valid strategy for monitoring potential disorders related, for example, to working activities. Recently, in the field of physical ergonomics, several studies have also shown potential for improvement in experimental methods of ergonomic analysis, through the combined [...] Read more.
Physical ergonomics has established itself as a valid strategy for monitoring potential disorders related, for example, to working activities. Recently, in the field of physical ergonomics, several studies have also shown potential for improvement in experimental methods of ergonomic analysis, through the combined use of artificial intelligence, and wearable sensors. In this regard, this review intends to provide a first account of the investigations carried out using these combined methods, considering the period up to 2021. The method that combines the information obtained on the worker through physical sensors (IMU, accelerometer, gyroscope, etc.) or biopotential sensors (EMG, EEG, EKG/ECG), with the analysis through artificial intelligence systems (machine learning or deep learning), offers interesting perspectives from both diagnostic, prognostic, and preventive points of view. In particular, the signals, obtained from wearable sensors for the recognition and categorization of the postural and biomechanical load of the worker, can be processed to formulate interesting algorithms for applications in the preventive field (especially with respect to musculoskeletal disorders), and with high statistical power. For Ergonomics, but also for Occupational Medicine, these applications improve the knowledge of the limits of the human organism, helping in the definition of sustainability thresholds, and in the ergonomic design of environments, tools, and work organization. The growth prospects for this research area are the refinement of the procedures for the detection and processing of signals; the expansion of the study to assisted working methods (assistive robots, exoskeletons), and to categories of workers suffering from pathologies or disabilities; as well as the development of risk assessment systems that exceed those currently used in ergonomics in precision and agility. Full article
(This article belongs to the Special Issue Wearable Sensors and Artificial Intelligence for Ergonomics)
Show Figures

Figure 1

Back to TopTop