Search

This review focuses on the usage of machine learning methods in sports. It closely follows the PRISMA framework for writing systematic reviews. We introduce the broader field of using sensor data for feedback in sport and cite similar reviews, that focus on other aspects of the field. With its focus on machine learning models that use signals from simple sensors, this review covers a very focused area that has not yet been covered by any other review. As described in problem definition, we use well-defined inclusion criteria, we have reviewed 72 papers. They present existing solutions, that use machine learning to extract useful information from data collected using various sensors in sports. To be included, papers had to use machine learning methods using data collected from sensors during sports, had to focus on sports-related applications and the result of machine learning had to be some information that can be used in real-time. We have found that the field is rapidly developing as 46 of the 72 included papers were from the last four years. Furthermore, we have found that the field is moving from using classical machine learning techniques to using deep learning. We analyze which data is used as input for machine learning, and we find that the most commonly used sensor is the accelerometer, closely followed by the gyroscope. The most common sensor platform is using a single wearable sensor, however, the studies that used deep learning, use multiple wearable sensors most often. Dataset sizes of sports papers are relatively small compared to other fields, but datasets are on average slightly larger in studies that use deep learning than in those that do not. We analyze the most common preprocessing methods and find that low-pass filtering and feature extraction are commonly used. We compare different machine learning models and the results of the studies that have tested multiple models on the same data, where we find that deep learning proved to be better than classical machine learning. Most studies show classification accuracy of over 90%, showing that machine learning is a useful tool for the researched problems. We end the review by researching how far the machine learning methods were implemented. Twenty of the included papers used their machine learning models in applications beyond a research paper and provided some sort of feedback back to athletes or coaches. After completing the review of the field, we propose a solution – a plan for future research. The proposed solution is to use a combination of best practices from the included paper and methods that we found are not yet implemented in the field of sports. We further elaborate, where we see the current state of the field. We conclude the article with short summary of the findings. [ABSTRACT FROM AUTHOR]

Deformable touch sensors with a high spatiotemporal resolution have recently attracted significant attention as a promising option for electronic skin and human‐machine interfaces. However, the conventional electronic matrix arrays require a large number of addressing lines and suffer from response time delay. In this study, a novel mechanically robust elastic electronic touch sensor is reported featuring only a limited number (2 or 4) of signal terminals. The sensor has a simple structure comprising an elastic spacer and two substrates with a conductive electrode of uniform resistance along the entire length of the electrode. By decoding the temporal resistance profiles from the touch sensor by using a simple simulator, the sensor can provide precise touch information such as position, instant moving speed and direction, and the trajectories of the movements. The touch actions are displayed in real‐time, regardless of whether the sensor is deformed or not. It is expected that this study will present a new approach to simplify the architecture of human‐machine interfaces. [ABSTRACT FROM AUTHOR]

Due to severe deformation, noise, and occlusion, the registration problem of non-rigid point sets in rolling formed metal workpieces poses challenges, and the demand for real-time data storage and registration during the rolling forming process makes this problem even more prominent. This paper proposes an enhanced nonrigid point set registration algorithm based on the Coherent Point Drift (CPD) framework, introducing novel methods to improve accuracy and efficiency. A refined local distance calculation method combining spatial distance has been proposed to improve matching accuracy. In contrast, an optimized shape context method introduces a new driving force criterion to expedite initial registration and reduce subsequent errors. Leveraging the Expectation-Maximization (EM) algorithm, the approach iteratively solves point correspondences, demonstrating robustness in handling complex scenarios like non-rigid deformation and noise. Experimental validation using real production datasets shows superior accuracy and efficiency over classical algorithms, showcasing a practical solution for non-rigid point set registration challenges in roll forming applications. [ABSTRACT FROM AUTHOR]

Abstract This review focuses on the usage of machine learning methods in sports. It closely follows the PRISMA framework for writing systematic reviews. We introduce the broader field of using sensor data for feedback in sport and cite similar reviews, that focus on other aspects of the field. With its focus on machine learning models that use signals from simple sensors, this review covers a very focused area that has not yet been covered by any other review. As described in problem definition, we use well-defined inclusion criteria, we have reviewed 72 papers. They present existing solutions, that use machine learning to extract useful information from data collected using various sensors in sports. To be included, papers had to use machine learning methods using data collected from sensors during sports, had to focus on sports-related applications and the result of machine learning had to be some information that can be used in real-time. We have found that the field is rapidly developing as 46 of the 72 included papers were from the last four years. Furthermore, we have found that the field is moving from using classical machine learning techniques to using deep learning. We analyze which data is used as input for machine learning, and we find that the most commonly used sensor is the accelerometer, closely followed by the gyroscope. The most common sensor platform is using a single wearable sensor, however, the studies that used deep learning, use multiple wearable sensors most often. Dataset sizes of sports papers are relatively small compared to other fields, but datasets are on average slightly larger in studies that use deep learning than in those that do not. We analyze the most common preprocessing methods and find that low-pass filtering and feature extraction are commonly used. We compare different machine learning models and the results of the studies that have tested multiple models on the same data, where we find that deep learning proved to be better than classical machine learning. Most studies show classification accuracy of over 90%, showing that machine learning is a useful tool for the researched problems. We end the review by researching how far the machine learning methods were implemented. Twenty of the included papers used their machine learning models in applications beyond a research paper and provided some sort of feedback back to athletes or coaches. After completing the review of the field, we propose a solution – a plan for future research. The proposed solution is to use a combination of best practices from the included paper and methods that we found are not yet implemented in the field of sports. We further elaborate, where we see the current state of the field. We conclude the article with short summary of the findings.

Copyright of Retos: Nuevas Perspectivas de Educación Física, Deporte y Recreación is the property of Federacion Espanola de Asociaciones de Docentes de Educacion Fisica and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Retos: Nuevas Perspectivas de Educación Física, Deporte y Recreación is the property of Federacion Espanola de Asociaciones de Docentes de Educacion Fisica and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The implementation of low-dimensional movement control by the central nervous system has been debated for decades. In this study, we investigated the dimensionality of the control signals received by spinal motor neurons when controlling either the ankle or knee joint torque. We first identified the low-dimensional latent factors underlying motor unit activity during torque-matched isometric contractions in male participants. Subsequently, we evaluated the extent to which motor units could be independently controlled. To this aim, we used an online control paradigm in which participants received the corresponding motor unit firing rates as visual feedback. We identified two main latent factors, regardless of the muscle group (vastus lateralis-medialis and gastrocnemius lateralis-medialis). The motor units of the gastrocnemius lateralis could be controlled largely independently from those of the gastrocnemius medialis during ankle plantarflexion. This dissociation of motor unit activity imposed similar behavior to the motor units that were not displayed in the feedback. Conversely, it was not possible to dissociate the activity of the motor units between the vastus lateralis and medialis muscles during the knee extension tasks. These results demonstrate that the number of latent factors estimated from linear dimensionality reduction algorithms does not necessarily reflect the dimensionality of volitional control of motor units. Overall, individual motor units were never controlled independently of all others but rather belonged to synergistic groups. Together, these findings provide evidence for a low-dimensional control of motor units constrained by common inputs, with notable differences between muscle groups. [ABSTRACT FROM AUTHOR]

Drawing inspiration from the intricate soft structures found in nature, soft actuators possess the ability to incrementally execute complex tasks and adapt to dynamic and interactive environments. In particular, the integration of sensor data feedback allows actuators to respond to environmental stimuli with heightened intelligence. However, conventional rigid sensors are constrained by their inherent lack of flexibility. The current manufacturing processes for flexible sensors are complex and fail to align with the inherent simplicity of soft actuators. In this study, to facilitate the straightforward and consistent sensing of soft pneumatic actuators, carbon–polydimethylsiloxane (CPDMS) materials were employed, utilizing 3D printing and laser-cutting techniques to fabricate a flexible sensor with ease. The preparation of standard tensile specimens verified that the sensor exhibits a fatigue life extending to several hundred cycles and determined its gauge factor to be −3.2. Experimental results indicate that the sensor is suitable for application in soft pneumatic actuators. Additionally, a printed circuit board (PCB) was fabricated and the piecewise constant curvature (PCC) kinematic method was utilized to enable real-time pose estimation of the soft pneumatic actuator. Compared with computer vision methods, the pose estimation error obtained by the sensing method is as low as 4.26%. This work demonstrates that this easily fabricated sensor can deliver real-time pose feedback for flexible pneumatic actuators, thereby expanding the potential application scenarios for soft pneumatic actuators (SPAs). [ABSTRACT FROM AUTHOR]

This study investigates the impact of real-time emotional feedback on the quality of teamwork conducted over videoconferencing. We developed a framework that provides real-time feedback through a virtual mirror based on facial and voice emotion recognition. In an experiment with 28 teams (84 participants), teams collaborated over Zoom (version 5.16.6) to set up a virtual Mars station using custom simulation software (Mars Star City, version 4.0). Participants were divided into 14 experimental teams, which were shown the virtual mirror, and 14 control teams without it. Team performance was measured by the improvement in the Mars simulation output quality. Our analysis using correlation, multi-level regression, and machine learning revealed that fewer interruptions but an increasing number over time correlated with higher performance. Higher vocal arousal and happiness also enhanced performance. We confirmed that female presence in teams boosts performance. SHAP values indicated that high variability in happiness, head movement, and positive facial valence—an "emotional rollercoaster"—positively predicted team performance. The experimental group outperformed the control group, suggesting that virtual mirroring improves virtual teamwork and that interrupting each other more while speaking less, leads to better results. [ABSTRACT FROM AUTHOR]

Control of multicomponent alloys during welding is challenging because it lacks a real‐time understanding of composition. The optical emissions of plasma formed during laser‐induced metal welding correlate with the composition of particles ejected from the melt pool. Plasma emissions observed in this study contain large iron, manganese, chrome, and copper signatures, which match the composition of emitted particles. Particles recovered closest to the melt pool exhibit a core–shell morphology that is composed of iron‐manganese‐chrome intermetallic cores within copper shells. Particles collected farther from the melt pool, do not share this core–shell morphology, though similar elemental compositions are observed. The correlation between plasma optical emissions and particle composition can be used to predict the composition of the melt pool, allowing for real‐time welding and sintering control. [ABSTRACT FROM AUTHOR]

Intraoperative monitoring of blood flow (BF) remains vital to guiding surgical decisions. Here, we report the use of SurgeON™ Blood Flow Monitor (BFM), a prototype system that attaches to surgical microscopes and implements laser speckle contrast imaging (LSCI) to noninvasively obtain and present vascular BF information in real-time within the microscope’s eyepiece.

Introduction: A self-paced (SP) heart rate (HR) control system proposed in a previous study was found to be feasible for healthy participants. The aims of this work were to investigate whether the SP HR control system is feasible to achieve accurate HR control in a participant with gait impairments, and to assess its interaction with an existing motor-driven body weight support (BWS) system. Methods: One participant with cerebral palsy was recruited in this case study. Three preliminary tests were completed to determine the appropriate mean value and amplitude of the target heart rate curve, and to identify a customised heart rate response model. Two series of formal self-paced heart rate control tests were then conducted to investigate the influence of different heart rate compensators and the presence of the BWS system. Results: The customised heart rate controller achieved improved accuracy in heart rate control and reduced oscillation in the treadmill target speed: the rootmean- square heart rate tracking error (RMSE) was 2.38 beats per minute (bpm) vs. 3.91 bpm (customised controller vs. nominal controller), and the average power of changes in the treadmill target speed was 0.4 X 10-4m²/s2 vs. 8.4 x 10-4m²/s². The BWS system resulted in improved HR tracking accuracy: RMSE on heart rate tracking was 3.02 bpm vs. 3.50 bpm (with BWS vs. without BWS). The BWS system had no influence on the automatic position control accuracy: RMSE on distance tracking was 0.0159m vs. 0.0164 m. Conclusion: After customising the heart rate compensator, the self-paced heart rate control system is feasible to achieve accurate heart rate control in an individual with gait impairments, and it can correctly interact with the BWS system. [ABSTRACT FROM AUTHOR]

Improvements in mental health through real-time feedback on emotions have consequences for productivity and employee wellness. However, we find few extant studies on how real-time feedback on emotions can influence subsequent behavior modification in the Japanese workplace. We conducted a randomized controlled trial (RCT) with 30 employees of an insurance company in Japan and observed their emotions for 10 working days using a wearable biometric device. We compared the emotions of employees who had access to real-time emotional states (treatment group) with those of employees who did not (control group). The results of the panel regression analysis showed that access to real-time emotions was negatively associated with happy emotions and positively associated with angry and sad emotions. The results indicated that even after having access to the objective statuses of emotions, participants were unable to continue with happy emotions and reverse angry and sad emotions to other comfortable emotions. Our findings imply that feedback on real-time emotional states should be associated with appropriate training and motivation to utilize feedback for behavioral modification. [ABSTRACT FROM AUTHOR]

This paper examines how older adults interact with fitness trackers and how that interaction influences their physical activity. We carried out qualitative interviews with 22 individuals between the ages of 55 and 72 who had used fitness trackers as part of a six-week field experiment investigating the effects of feedback from fitness trackers and the social influence of their spouses. From their comments, we derived an explorative process model explaining the mechanisms and the four stages of effects arising from personalised feedback, namely, cognitive, affective, conative, and intuitive. These effects were grouped into internal and external dimensions. Three types of goal-related decisions determined whether interviewees moved from the internal responses of cognition and emotion to the external response of behaviour change. The findings from this study elucidate how real-time personalised feedback can motivate physical activity among older adults and highlight the goal-related factors that influence this effect. [ABSTRACT FROM AUTHOR]

Mounting empirical support for early intensive behavioral intervention (EIBI) has increased demand for early intervention services for children diagnosed with autism spectrum disorder (ASD), which may include a variety of components such as discrete-trial instruction (DTI) or natural environment teaching (NET). Many caregivers are now learning EIBI techniques and becoming active agents in their child's ASD treatment. Behavioral skills training (BST) has been frequently used to teach individuals to correctly perform a variety of skills, including DTI (Lafasakis & Sturmey, Lafasakis and Sturmey, Journal of Applied Behavior Analysis 40:685–689, 2007). In this study, caregivers were trained to conduct a DTI procedure with a single-component BST method (i.e., real-time feedback). A concurrent, multiple baseline across caregivers design was used to evaluate the efficacy of real-time feedback on the caregivers' implementation of the DTI procedure with confederates. Results showed that real-time feedback yielded short caregiver training times and few sessions to meet the mastery criterion. In addition, caregivers expressed high satisfaction with the real-time feedback training method, and they were able to implement the procedures with their children with high integrity during treatment extension probes. [ABSTRACT FROM AUTHOR]

The buildings sector is a substantial contributor to total energy consumption and, according to current forecasts, will remain so in the near future. Technical energy efficiency innovations can reduce energy demand; however, if not accompanied appropriately by building occupants’ behaviour, discrepancies between planned and resulting energy consumption will persist, which is known as the building energy performance gap. To tackle this challenge, interventions such as feedback and social comparison are increasingly applied in combination with persuasive technologies. We report the results from a field experiment conducted in a Swiss energy-efficient district where two consecutive behavioural interventions involving persuasive technologies were tested: (1) real-time hot water consumption feedback while showering and (2) a weekly newsletter with social comparison feedback regarding overall hot water consumption, including hot water saving tips, in addition to real-time feedback. Based on the data from 33 households, we found that, compared with the baseline consumption, hot water consumption was 12.4% lower immediately after the real-time feedback intervention and 16.1% lower after the combined intervention. Hot water consumption increased again after the intervention phase, but it was still 9.7% lower than the baseline consumption 2 months after the combined intervention and 8.6% lower 4.5 months after the combined intervention. While the reductions after the real-time feedback and combined intervention were significant, the reductions 2 and 4.5 months after the combined intervention were not. [ABSTRACT FROM AUTHOR]

Motorcycle assistance systems have been an increasing focus of research in recent years to promote safer riding practices and mitigate motorcycle-related accidents. While there is substantial interest in evaluating the beneficial aspect of these systems in improving driving safety, it is equally essential to clarify their unintended adverse effects on riders' driving behaviors and the overall interaction between riders and such systems. In this study, we designed alert and continuous real-time feedback HMIs that convey information about lateral deviation from the lane center based on our previous research results. Experiments were then conducted on a riding simulator to investigate whether variations in information presentation could alter rider-system interaction and ultimately affect riding performance. Fifteen young motorcyclists (mean age = 22.1 ± 1.87 years) were exposed to dummy and risky scenarios at uncontrolled intersections while interacting with alerting or real-time feedback systems separately. A path model was constructed, and the impacts of HMIs on riders' reaction time, information observation time, weighted workload, and risk of collision were clarified. Cluster analysis was subsequently utilized to categorize participants into confident and methodical riders, predicated upon their riding styles. Independent t-tests revealed that, except for Obs-time, there were no significant differences between confident and methodical riders in RT and TTCmin when using an alert HMI. However, when real-time feedback was displayed, significant differences were found for TTCmin and Obs-time. In general, participants exhibited superior performance with the Alert HMI, characterized by a shorter RT (1 second), longer TTCmin (0.79 seconds), reduced information observation time (0.42 seconds), and lower perceived workload compared to when real-time feedback was used. The authors believe that this research will contribute to the development of more effective and rider-centric HMI designs.

Background: App-linked real-time feedback-devices for cardiopulmonary resuscitation (CPR) aim to improve laypersons’ resuscitation quality. Resuscitation guidelines recommend these technologies in training settings. This is the first study comparing resuscitation quality of all App-linked feedback-devices currently on market. Methods: A prospective randomised simulation study was performed. After standardised instructions, participants performed 2-minutes compression-only CPR on a manikin without feedback (baseline). Afterwards, participants performed 4 × 2 min CPR with four different feedback devices in randomised order (CorPatch® Trainer, CPRBAND AIO Training, SimCPR®ProTrainer, Relay Response™) (intervention). CPR metrics (chest compression depth (CD), chest compression rate (CR), percentage of correct CD/CR (%), correct hand position, correct chest recoil, and technical preparation-time) were assessed. Devices data were compared to the baseline group using Wilcoxon testing with IBM SPSS (primary outcome). Differences between devices were analysed with ANOVA testing (secondary outcome). Normally distributed data were described as mean ± standard deviation (SD) and non-normally distributed data as Median [Interquartile range (IQR). CPR self-confidence was measured by means of questionnaire before and after feedback devices’ use. Comparison was performed by students t-test. Results: Forty participants were involved. SimCPR®ProTrainer was the only device, which resulted in guideline-compliant chest compressions (Mean ± SD:5.37 ± 0.76) with improved chest compression depth (p

Aim: Current guidelines for cardiopulmonary resuscitation (CPR) recommend a one-size-fits-all approach in relation to the positioning of chest compressions. We recently developed RescueDoppler, a hands-free Doppler ultrasound device for continuous monitoring of carotid blood flow velocity during CPR. The aim of the present study is to investigate whether RescueDoppler via real-time hemodynamic feedback, could identify both optimal and suboptimal compression positions. Methods: In this model of animal cardiac arrest, we induced ventricular fibrillation in five domestic pigs. Manual chest compressions were performed for ten seconds at three different positions on the sternum in random order and repeated six times. We analysed Time Average Velocity (TAV) with chest compression position as a fixed effect and animal, position, and sequential time within animals as random effects. Furthermore, we compared TAV to invasive blood pressure from the contralateral carotid artery. Results: We were able to detect changes in TAV when altering positions. The positions with the highest (range 19 to 48 cm/s) and lowest (6–25 cm/s) TAV were identified in all animals, with corresponding peak pressure 50–81 mmHg, and 46–64 mmHg, respectively. Blood flow velocity was, on average, highest at the middle position (TAV 33 cm/s), but with significant variability between animals (SD 2.8) and positions within the same animal (SD 9.3). Conclusion: RescueDoppler detected TAV changes during CPR with alternating chest compression positions, identifying the position yielding maximal TAV. Future clinical studies should investigate if RescueDoppler can be used as a real-time hemodynamical feedback device to guide compression position.

Introduction: The level of BLS achievement at the end of basic education is not clear, so to develop a BLS training program using QCPR LearnerⓇ and to verify its effectiveness. Methods: A quantitative descriptive study design was used. The developed BLS program was implemented for 81 fourth-year students at the school of nursing. The program consisted of 2 minutes of training per student and real-time feedback by QCPR LearnerⓇ as well as feedback among students and from faculty members and was conducted twice for each student. Evaluation was conducted from three aspects: learner response and program evaluation both using questionnaires, learning achievement of QCPR score. Results: The mean values of learners' responses before and after the program were: attention, 4.32 before and 4.59 after; relevance, 4.48 before and 4.75 after; confidence, 2.32 before and 3.78 after; and satisfaction, 2.12 before and 3.41 after, which increased significantly after the program. The QCPR LearnerⓇ scores increased significantly from 74.08 for the first time to 86.76 for the second time. In the free response, some respondents stated that "visualisation of the procedure by the application improved my skills." Conclusion: The results of the evaluation from three aspects showed that this program was effective in improving students' motivation to learn and skills.

Serial crystallography (SX) is a cutting-edge technique in structural biology, involving the systematic collection of X-ray diffraction data from numerous randomly oriented microcrystals. To extract comprehensive three-dimensional information about the studied system, SX utilises thousands of measured diffraction patterns. As such, SX takes advantages of the properties of modern X-ray sources, including Free Electron Lasers (FELs) and third and fourth generation synchrotrons, as well as contemporary high-repetition-rate detectors. Efficient analysis of the extensive datasets generated during SX experiments demands fast and effective algorithms. The FDIP library offers meticulously optimised functions tailored for preprocessing data obtained in SX experiments. This encompasses tasks such as background subtraction, identification and masking of parasitic streaks, elimination of unwanted powder diffraction (e.g., from ice or salt crystals), and pinpointing useful Bragg peaks in each diffraction pattern. The library is equipped with a user-friendly graphical interface for facile parameter adjustment tailored to specific datasets. Compatible with popular SX processing software like OnDA, Cheetah, CrystFEL, and Merge3D, the FDIP library enhances the capabilities of these tools for streamlined and precise serial crystallography analyses. [ABSTRACT FROM AUTHOR]

In lower extremity amputee rehabilitation programs, difficult-to-master targeted activation of deep core muscles and pursed-lip breathing training are prescribed to treat poor movement quality and to improve recovery after amputation. Non-invasive wireless sensors and mixed reality (MR) technologies are proposed as a solution. The main aim was to validate a novel rehabilitation technology by exploring whether a combined verbal and visual mixed reality feedback (VF + MR) will initiate a greater change in muscle electrical activation magnitude compared to verbal feedback only (VF) during exercising. The second objective was to evaluate the effectiveness of specific exercise program targeted to engage specifically deep core muscles. Pre-post-test cross-over study involved electromyographic activity (EMG) analysis from Transversus Abdominis (TA) and Multifidus (MF) muscles and self-reported questionnaires to evaluate the efficiency of MR feedback. Anthropometric data, state of health, subjective low back pain (Oswestry Disability Index), and physical activity level (IPAQ) estimation were analysed. The data from 13 patients following unilateral transtibial and transfemoral amputation showed a significant EMG increase in (VF + MR) for Chair Lean (p = 0.03) and Bent Leg Raise (p = 0.0005) exercises for TA muscle. Even though there was no significant difference in Back Bridge and Side Plank exercises, 6 to 10 participants depending on the exercise, had an increase of EMG in the range of 50–400% for both – TA and MF muscles. The proposed solution has a high potential for increasing motivation, self-awareness, and muscle engagement during exercises, based on EMG and self-reported questionnaire data. [ABSTRACT FROM AUTHOR]

Drawing inspiration from the intricate soft structures found in nature, soft actuators possess the ability to incrementally execute complex tasks and adapt to dynamic and interactive environments. In particular, the integration of sensor data feedback allows actuators to respond to environmental stimuli with heightened intelligence. However, conventional rigid sensors are constrained by their inherent lack of flexibility. The current manufacturing processes for flexible sensors are complex and fail to align with the inherent simplicity of soft actuators. In this study, to facilitate the straightforward and consistent sensing of soft pneumatic actuators, carbon–polydimethylsiloxane (CPDMS) materials were employed, utilizing 3D printing and laser-cutting techniques to fabricate a flexible sensor with ease. The preparation of standard tensile specimens verified that the sensor exhibits a fatigue life extending to several hundred cycles and determined its gauge factor to be −3.2. Experimental results indicate that the sensor is suitable for application in soft pneumatic actuators. Additionally, a printed circuit board (PCB) was fabricated and the piecewise constant curvature (PCC) kinematic method was utilized to enable real-time pose estimation of the soft pneumatic actuator. Compared with computer vision methods, the pose estimation error obtained by the sensing method is as low as 4.26%. This work demonstrates that this easily fabricated sensor can deliver real-time pose feedback for flexible pneumatic actuators, thereby expanding the potential application scenarios for soft pneumatic actuators (SPAs).

This study investigates the impact of real-time emotional feedback on the quality of teamwork conducted over videoconferencing. We developed a framework that provides real-time feedback through a virtual mirror based on facial and voice emotion recognition. In an experiment with 28 teams (84 participants), teams collaborated over Zoom (version 5.16.6) to set up a virtual Mars station using custom simulation software (Mars Star City, version 4.0). Participants were divided into 14 experimental teams, which were shown the virtual mirror, and 14 control teams without it. Team performance was measured by the improvement in the Mars simulation output quality. Our analysis using correlation, multi-level regression, and machine learning revealed that fewer interruptions but an increasing number over time correlated with higher performance. Higher vocal arousal and happiness also enhanced performance. We confirmed that female presence in teams boosts performance. SHAP values indicated that high variability in happiness, head movement, and positive facial valence—an “emotional rollercoaster”—positively predicted team performance. The experimental group outperformed the control group, suggesting that virtual mirroring improves virtual teamwork and that interrupting each other more while speaking less, leads to better results.

Badminton is a very popular subject in Physical Education (PE). Many students enroll badminton courses in every semester which pose a tremendous teaching load to the instructors. The one-on-one guiding/feedback time provided by the instructor to each student is also greatly reduced. To overcome this challenge, some studies have tried to adopt pose recognition technique in teaching badminton. However, the lack of mobility and recognition accuracy problems hinder its applicability. To address this issue, a new pose recognition technique, OpenPose, was employed to develop a real-time pose recognition badminton teaching APP in this study. The APP was then installed on a mobile device to enhance badminton smash skill learning performance. The scores distribution of the experimental group shows majority of students achieved satisfactory performance, this implies the badminton teaching APP is helpful to all students no matter what their initial skill levels are. [ABSTRACT FROM AUTHOR]

This research introduces the self-explanation-based automated feedback (SEAF) system, aimed at alleviating the teaching burden through real-time, automated feedback while aligning with SDG 4's sustainability goals for quality education. The system specifically targets the enhancement of self-explanation, a proven but challenging cognitive strategy that bolsters both conceptual and procedural knowledge. Utilizing a triad of core feedback mechanisms—customized messages, quality assessments, and peer-generated exemplars—SEAF aims to fill the gap left by traditional and computer-aided self-explanation methods, which often require extensive preparation and may not provide effective scaffolding for all students. In a pilot study involving 50 junior high students, those with initially limited self-explanation skills showed significant improvement after using SEAF, achieving a moderate learning effect. A resounding 91.7% of participants acknowledged the system's positive impact on their learning. SEAF's automated capabilities serve dual purposes: they offer a more personalized and scalable approach to student learning while simultaneously reducing the educators' workload related to feedback provision. [ABSTRACT FROM AUTHOR]

Training devices to enhance golf swing technique are increasingly in demand. Golf swing biomechanics are typically assessed in a laboratory setting and not readily accessible. Inertial measurement units (IMUs) offer improved access as they are wearable, cost-effective, and user-friendly. This study investigates the accuracy of IMU-based golf swing kinematics of upper torso and pelvic rotation compared to lab-based 3D motion capture. Thirty-six male and female professional and amateur golfers participated in the study, nine in each sub-group. Golf swing rotational kinematics, including upper torso and pelvic rotation, pelvic rotational velocity, S-factor (shoulder obliquity), O-factor (pelvic obliquity), and X-factor were compared. Strong positive correlations between IMU and 3D motion capture were found for all parameters; Intraclass Correlations ranged from 0.91 (95% confidence interval [CI]: 0.89, 0.93) for O-factor to 1.00 (95% CI: 1.00, 1.00) for upper torso rotation; Pearson coefficients ranged from 0.92 (95% CI: 0.92, 0.93) for O-factor to 1.00 (95% CI: 1.00, 1.00) for upper torso rotation (p < 0.001 for all). Bland–Altman analysis demonstrated good agreement between the two methods; absolute mean differences ranged from 0.61 to 1.67 degrees. Results suggest that IMUs provide a practical and viable alternative for golf swing analysis, offering golfers accessible and wearable biomechanical feedback to enhance performance. Furthermore, integrating IMUs into golf coaching can advance swing analysis and personalized training protocols. In conclusion, IMUs show significant promise as cost-effective and practical devices for golf swing analysis, benefiting golfers across all skill levels and providing benchmarks for training. [ABSTRACT FROM AUTHOR]

Real-time assessment of the ergonomic risks to which workers are exposed at a workstation and the provision of real-time corrective feedback intervention to workers play an essential role in improving safety in the workplace through the reduction of long-term exposure of workers to the ergonomically hazardous postures associated with physical fatigue and work-related musculoskeletal disorders. This study proposes a framework, virtual reality–based real-time ergonomics training (VR-RET), that integrates virtual reality (VR) and an inertia motion capture system to rapidly assess postures, providing the following inputs in real time: (1) full-body postural ergonomic risk assessment that deploys existing rule-based methods such as rapid upper limb assessment (RULA) and rapid entire body assessment (REBA); (2) auditory feedback, triggered when the exposure to ergonomic risks is higher than a predefined threshold; and (3) visual feedback intervention to correct ergonomically hazardous postures through the provision of recommendations during training on industrialized construction tasks. The proposed framework is verified through a pretest/posttest procedure in conjunction with a randomized control group experiment involving 37 subjects. Based on the comparison of the pretest and posttest data, a reduction of 35% in the percentage of time spent being subjected to ergonomic risks in the high-risk range is observed when training is administered using VR-RET and RULA is deployed as the risk assessment method; in contrast, a significant reduction is not observed when rapid entire body assessment is used. This study's contributions are twofold: (1) a framework for providing ergonomic and operational training through VR simulation based on real-time acquisition and processing of body motion data (with the objective of mitigating worker behaviors that increase exposure to the ergonomically hazardous postures that can lead to a work-related musculoskeletal disorder); and (2) updated evaluation of the effectiveness of real-time RULA and REBA assessments integrated with real-time auditory and visual postural feedback intervention for ergonomic risk reduction. [ABSTRACT FROM AUTHOR]

Industry 4.0, initiated by Germany in 2013, focuses on digitization and process optimization in manufacturing. China's 'Made in China 2025' plan, aligned with Industry 4.0, was introduced in 2015. Motors are pivotal in industrial manufacturing, necessitating robust quality control. To enable real-time adjustments and enhance product quality, we propose an Online Quality Feedback (OQF) system using MySQL and big data. Implemented in H company's motor production line, this system gathers real-time data from sensor-equipped stations, processes it through MySQL and big data analysis, and presents outcomes on a web interface. This empowers process and equipment engineers with concise insights for effective decisionmaking, ultimately improving the manufacturing process. Results affirm the effectiveness of our method in enhancing production management. [ABSTRACT FROM AUTHOR]

• Home-based NIBS is a promising new treatment strategy for neuro-psychiatric pathologies ensuring frequent stimulation exposure. • There are currently no solutions to direct and monitor correct electrode placement for self-application. • We propose an easy-to-use, digital electrode placement tool that marks an important step to improve home-based set-ups. Home-based non-invasive brain stimulation (NIBS) has been suggested as an adjunct treatment strategy for neuro-psychiatric disorders. There are currently no available solutions to direct and monitor correct placement of the stimulation electrodes. To address this issue, we propose an easy-to-use digital tool to support patients for self-application. We recruited 36 healthy participants and compared their cap placement performance with the one of a NIBS-expert investigator. We tested participants' placement accuracy with instructions before (Pre) and after the investigator's placement (Post), as well as participants using the support tool (CURRENT). User experience (UX) and confidence were further evaluated. Permutation tests demonstrated a smaller deviation within the CURRENT compared with Pre cap placement (p = 0.02). Subjective evaluation of ease of use and usefulness of the tool were vastly positive (8.04 out of 10). CURRENT decreased the variability of performance, ensured placement within the suggested maximum of deviation (10 mm) and supported confidence of correct placement. This study supports the usability of this novel technology for correct electrode placement during self-application in home-based settings. CURRENT provides an exciting opportunity to promote home-based, self-applied NIBS as a safe, high-frequency treatment strategy that can be well integrated in patients' daily lives. [ABSTRACT FROM AUTHOR]

To better promote the role of traditional constructivist teaching models, this study investigates on the impact of information technology-enhanced constructivist teaching on engineering undergraduates learning and engagement. Firstly, the framework of constructivist teaching theory model based on data analysis is constructed, and the relationship among the constructivist teaching model, teaching activity data and flow experience is explicit. Secondly, a real-time teaching management assisted analysis software is developed by ourselves, which expands the mere management tool to an educational method and integrated application. Finally, a practical study is conducted, and the investigation results show that technology information-enhanced constructivist teaching can improve effectiveness by facilitating flow experiences. In addition, real-time feedback on teaching evaluation is positively correlated with the overall assessment of learning effectiveness. [ABSTRACT FROM AUTHOR]

Teaching is a complex activity that requires a combination of different knowledges, attitudes, skills and values. Teachers are continuously making decisions in the classroom to promote the teaching-learning process. This paper presents the development of a prototype that aims to facilitate teachers' decision making in the classroom in real time, considering variables related to the students, the teacher, and the environment or environmental factors in the classroom. We used the DBR (Design Based Research) methodology for this project. We reached the first iteration when the second version of the prototype was presented. An analysis of the literature was carried out as a starting point and to establish the foundations for the first version of the prototype. A later expert judgment allowed the prototype to evolve to the second version. This is the starting point for the technological development of the designed solution. This research is a first step towards using technology to improve teacher decision making in the classroom, and has great potential benefits for both the teacher, for improving their skills, and the student, so they can have a better and more customized learning experience. [ABSTRACT FROM AUTHOR]

Background High‐quality cardiopulmonary resuscitation (CPR) is associated with improved survival from out‐of‐hospital cardiac arrest and includes chest compression depth, chest compression rate, and chest compression fraction within international guideline recommendations. Previous studies have demonstrated divergent results of real‐time feedback on CPR performance and patient outcomes. This study investigated the association between emergency medical service CPR quality and real‐time CPR feedback for out‐of‐hospital cardiac arrest. Methods and Results This study collected out‐of‐hospital cardiac arrest data within the Capital Region of Denmark and compared CPR quality delivered by ambulance personnel. Data were collected in 2 consecutive phases from October 2018 to February 2020. Median chest compression depth was 6.0 cm (no feedback) and 5.9 cm (real‐time feedback) (P=0.852). Corresponding proportion of guideline‐compliant chest compressions for depth was 16.6% and 28.7%, respectively (P

Rehabilitation is essential for post-stroke body function recovery. Supported by the mirror neuron theory, motor imagery (MI) has been proposed as a potential stroke therapy capable of facilitating the rehabilitation. However, it is often quite difficult to estimate the degree of the participation of patients during traditional MI training as well as difficult to evaluate the efficacy of MI based rehabilitation methods. The goal of this paper is to develop a virtual reality (VR) based MI training system combining electromyography (EMG) based real-time feedback for poststroke rehabilitation, with the immersive scenario of the VR system providing a shooting basketball training for bilateral upper limbs. Through acquiring electroencephalography (EEG) signal, the brain activity in alpha and beta frequency bands was mapped and the correlation analysis could be achieved. Furthermore, EMG data of each patient was collected and calculated as threshold with root-mean-square algorithm for feedback of the performance score of the shooting basketball training in virtual environment. To investigate the feasibility of this newly-built rehabilitation training system, four experiments namely initial assessment experiment, motor imagery (MI), action observation (AO), and combined motor imagery and action observation (MI+AO) were carried out on stroke patients at different recovery stages. The result shows that MI+AO can generate more pronounced event-related desynchronization (ERD) in alpha band compared to other cases and induce relatively obvious ERD in beta band compared to AO, which demonstrates that VR-based observation has ability to facilitate MI training. Furthermore, it has been found that the muscle strength from MI+AO is the highest through the EMG analysis. This proves that the feedback of EMG can be used to quantify patient’s training engagement and promote MI training at a certain extent. Hence, by incorporating such an EMG feedback, a VR-based MI training system has the potential to achieve higher efficacy for post-stroke rehabilitation.

Prosthetic limb embodiment remains a significant challenge for many amputees due to traditional designs’ lack of sensory feedback. To address this challenge, the effectiveness of non-invasive neuromuscular electrical stimulation (NMES) controlled by a hybrid proportional-differential (PD)-Fuzzy logic system was evaluated for providing real-time proprioception and tactile feedback. The study used a human-in-the-closed-loop approach with ten participants: five upper limb amputees and five non-disabled individuals as the control group. An applied force, the joint angle of a prosthetic hand’s finger, and surface electromyography signals generated by the biceps muscle all regulate the intensity of sensory feedback. Additionally, the C6 and C7 myotomes were selected as elicitation sites. The average threshold for detecting action motion and force was around 21° and 1.524N, respectively. The participants successfully reproduced desired joint angles within the range of 0°-110° at five separate intervals. In the weight recognition experiment, the amputee participant’s minimum number of false predictions was four. The highest accuracy achieved was 80.66% in detecting object size and stiffness. Additionally, unpaired t-tests were performed for the means of the results of the experiments to determine statistically significant differences between groups. The results suggest that stimulation of myotomes by NMES is an effective non-invasive method for delivering rich multimodal sensation information to individuals with disabilities, including upper limb amputees, without needing visual or auditory cues. These findings contribute to the development of non-invasive sensory substitution in prostheses.

Abstract Background Cardiopulmonary resuscitation skill have a direct impact on its success rate. Choosing the right method to acquire this skill can lead to effective performance. This investigation was conducted to compare the effect of Real-time feedback and debriefing by video recording on basic life support skill in nursing students. Methods This quasi-experimental study was performed on 67 first year nursing students. First, a theoretical basic life support (BLS) training session was held for the all participants, at the end of session the pre-test was taken. Students were randomly assigned to two groups. A 4-hour practical BLS training session was conducted in the real - time feedback group as well as the debriefing by video recording group, and at the end of the training, a post-test was taken from each group. Each group received a post-test. Data were analyzed using SPSS 25 software. Results Results showed a significant difference between mean (SD) of debriefing by video recording group in pre-test and post-test (p