Introduction: Recent advances in sensor technology demonstrate the potential to enhance training regimes with sensor-based augmented visual feedback training systems for complex movement tasks in sports. Sensorimotor learning requires feedback that guides the learning process towards an optimal solution for the task to be learned, while considering relevant aspects of the individual control system—a process that can be summarized as learning or improving coordination. Sensorimotor learning can be fostered significantly by coaches or therapists providing additional external feedback, which can be incorporated very effectively into the sensorimotor learning process when chosen carefully and administered well. Sensor technology can complement existing measures and therefore improve the feedback provided by the coach or therapist. Ultimately, this sensor technology constitutes a means for autonomous training by giving augmented feedback based on physiological, kinetic, or kinematic data, both in real-time and after training. This requires that the key aspects of feedback administration that prevent excessive guidance can also be successfully automated and incorporated into such electronic devices.Methods: After setting the stage from a computational perspective on motor control and learning, we provided a scoping review of the findings on sensor-based augmented visual feedback in complex sensorimotor tasks occurring in sports-related settings. To increase homogeneity and comparability of the results, we excluded studies focusing on modalities other than visual feedback and employed strict inclusion criteria regarding movement task complexity and health status of participants.Results: We reviewed 26 studies that investigated visual feedback in training regimes involving healthy adults aged 18-65. We extracted relevant data regarding the chosen feedback and intervention designs, measured outcomes, and summarized recommendations from the literature.Discussion: Based on these findings and the theoretical background on motor learning, we compiled a set of considerations and recommendations for the development and evaluation of future sensor-based augmented feedback systems in the interim. However, high heterogeneity and high risk of bias prevent a meaningful statistical synthesis for an evidence-based feedback design guidance. Stronger study design and reporting guidelines are necessary for future research in the context of complex skill acquisition.

Background: Digital sensing devices have become an increasingly important component of modern biomedical research, as they help provide objective insights into individuals’ everyday behavior in terms of changes in motor and nonmotor symptoms. However, there are significant barriers to the adoption of sensor-enhanced biomedical solutions in terms of both technical expertise and associated costs. The currently available solutions neither allow easy integration of custom sensing devices nor offer a practicable methodology in cases of limited resources. This has become particularly relevant, given the need for real-time sensor data that could help lower health care costs by reducing the frequency of clinical assessments performed by specialists and improve access to health assessments (eg, for people living in remote areas or older adults living at home). Objective: The objective of this paper is to detail the end-to-end development of a novel sensor recording software system that supports the integration of heterogeneous sensor technologies, runs as an on-demand service on consumer-grade hardware to build sensor systems, and can be easily used to reliably record longitudinal sensor measurements in research settings. Methods: The proposed software system is based on a server-client architecture, consisting of multiple self-contained microservices that communicated with each other (eg, the web server transfers data to a database instance) and were implemented as Docker containers. The design of the software is based on state-of-the-art open-source technologies (eg, Node.js or MongoDB), which fulfill nonfunctional requirements and reduce associated costs. A series of programs to facilitate the use of the software were documented. To demonstrate performance, the software was tested in 3 studies (2 gait studies and 1 behavioral study assessing activities of daily living) that ran between 2 and 225 days, with a total of 114 participants. We used descriptive statistics to evaluate longitudinal measurements for reliability, error rates, throughput rates, latency, and usability (with the System Usability Scale [SUS] and the Post-Study System Usability Questionnaire [PSSUQ]). Results: Three qualitative features (event annotation program, sample delay analysis program, and monitoring dashboard) were elaborated and realized as integrated programs. Our quantitative findings demonstrate that the system operates reliably on consumer-grade hardware, even across multiple months (>420 days), providing high throughput (2000 requests per second) with a low latency and error rate (<0.002%). In addition, the results of the usability tests indicate that the system is effective, efficient, and satisfactory to use (mean usability ratings for the SUS and PSSUQ were 89.5 and 1.62, respectively). Conclusions: Overall, this sensor recording software could be leveraged to test sensor devices, as well as to develop and validate algorithms that are able to extract digital measures (eg, gait parameters or actigraphy). The proposed software could help significantly reduce barriers related to sensor-enhanced biomedical research and allow researchers to focus on the research questions at hand rather than on developing recording technologies.

Sensorimotor training on an unstable base of support is considered to lead to improvements in balance and coordination tasks. Here, we intend to lay the groundwork for generating cost-effective real-time kinematic feedback for coordination training on devices with an unstable base of support, such as Sensopros or slacklines, by establishing a model for estimating relevant tape kinematic data from angle measurements alone. To assess the accuracy of the model in a real-world setting, we record a convenience sample of three people performing ten exercises on the Sensopro Luna and compare the model predictions to motion capture data of the tape. The measured accuracy is reported for each target measure separately, namely the roll angle and $XYZ$-position of the tape segment directly below the foot. After the initial assessment of the model in its general form, we also propose how to adjust the model parameters based on preliminary measurements to adapt it to a specific setting and further improve its accuracy. The results show that the proposed method is viable for recording tape kinematic data in real-world settings, and may therefore serve as a performance indicator directly or form the basis for estimating posture and other measures related to human motor control in a more intricate training feedback system.

BACKGROUND Digital sensing devices have become an increasingly important component of modern biomedical research, as they help provide objective insights into individuals’ everyday behavior in terms of changes in motor and nonmotor symptoms. However, there are significant barriers to the adoption of sensor-enhanced biomedical solutions in terms of both technical expertise and associated costs. The currently available solutions neither allow easy integration of custom sensing devices nor offer a practicable methodology in cases of limited resources. This has become particularly relevant, given the need for real-time sensor data that could help lower health care costs by reducing the frequency of clinical assessments performed by specialists and improve access to health assessments (eg, for people living in remote areas or older adults living at home). OBJECTIVE The objective of this paper is to detail the end-to-end development of a novel sensor recording software system that supports the integration of heterogeneous sensor technologies, runs as an on-demand service on consumer-grade hardware to build sensor systems, and can be easily used to reliably record longitudinal sensor measurements in research settings. METHODS The proposed software system is based on a server-client architecture, consisting of multiple self-contained microservices that communicated with each other (eg, the web server transfers data to a database instance) and were implemented as Docker containers. The design of the software is based on state-of-the-art open-source technologies (eg, Node.js or MongoDB), which fulfill nonfunctional requirements and reduce associated costs. A series of programs to facilitate the use of the software were documented. To demonstrate performance, the software was tested in 3 studies (2 gait studies and 1 behavioral study assessing activities of daily living) that ran between 2 and 225 days, with a total of 114 participants. We used descriptive statistics to evaluate longitudinal measurements for reliability, error rates, throughput rates, latency, and usability (with the System Usability Scale [SUS] and the Post-Study System Usability Questionnaire [PSSUQ]). RESULTS Three qualitative features (event annotation program, sample delay analysis program, and monitoring dashboard) were elaborated and realized as integrated programs. Our quantitative findings demonstrate that the system operates reliably on consumer-grade hardware, even across multiple months (>420 days), providing high throughput (2000 requests per second) with a low latency and error rate (<0.002%). In addition, the results of the usability tests indicate that the system is effective, efficient, and satisfactory to use (mean usability ratings for the SUS and PSSUQ were 89.5 and 1.62, respectively). CONCLUSIONS Overall, this sensor recording software could be leveraged to test sensor devices, as well as to develop and validate algorithms that are able to extract digital measures (eg, gait parameters or actigraphy). The proposed software could help significantly reduce barriers related to sensor-enhanced biomedical research and allow researchers to focus on the research questions at hand rather than on developing recording technologies. CLINICALTRIAL

Monitoring center-of-mass is crucial for assessing postural control, but field measurements are often impractical or cost-prohibitive. This study investigates the feasibility of predicting center-of-mass kinematics from the motion of an unstable base—the Sensopro Luna—using deep learning, eliminating the need for wearable sensors. We conducted a cross-sectional study in which 64 participants were recorded performing three coordination exercises (Single-Leg Stance, Stepping, and Waves). Marker-based motion capture and auxiliary inertial sensors were used to record reference and tape kinematics. The model inputs consisted of IMU- and motion-capture-derived tape segment orientations, IMU accelerations and angular velocities, and algorithmic estimates of the lowest tape positions. Nine axis-specific exercise models were developed using a hybrid Encoder–LSTM–Decoder architecture and compared against linear regression baselines. Our results indicate that the deep learning models successfully predicted horizontal center-of-mass displacements (DNN Mean Absolute Errors of 16.1–23.7 mm for X-axis and 4.4–31.3 mm for Y-axis) and exhibited descriptively lower errors than linear models in mean absolute error and signal morphology. However, vertical predictions were less reliable, likely due to the physical constraints inherent to the kinematics of the unstable base. Error analysis revealed that prediction accuracy was highest within common postural ranges, but decreased for extreme displacements. These findings provide a proof-of-concept for wearable-free postural monitoring, particularly for movement along the mediolateral and sagittal axes. Such a system could facilitate automated, cost-effective postural feedback and performance tracking in rehabilitation and fitness environments, supporting autonomous coordination training without the practical constraints of traditional measurement systems.