A wearable biofeedback control system based body area network for freestyle swimming

Abstract

Wearable posture measurement units are capable of enabling real-time performance evaluation and providing feedback to end users. This paper presents a wearable feedback prototype designed for freestyle swimming with focus on trunk rotation measurement. The system consists of a nine-degree-of-freedom inertial sensor, which is built in a central data collection and processing unit, and two vibration motors for delivering real-time feedback. Theses devices form a fundamental body area network (BAN). In the experiment setup, four recreational swimmers were asked to do two sets of 4 x 25m freestyle swimming without and with feedback provided respectively. Results showed that real-time biofeedback mechanism improves swimmers kinematic performance by an average of 4.5% reduction in session time. Swimmers can gradually adapt to feedback signals, and the biofeedback control system can be employed in swimmers daily training for fitness maintenance.

Frogman Self-Navigation Method Based on Virtual Transponder Array and Dead Reckoning

“…The scheme of semi-physical simulation experiment is composed of three parts: a) simulation of frogman's motion state; b) acquisition of frogman's movement parameters; c) processing of experimental data. a) Simulation of frogman's motion state It can be seen from [31] and [32] that the movement parameters of pedestrian's feet and frogman's body both show regular changes when walking and swimming respectively, and the similarity between these two motion models is high. Therefore, we can use different foot movements of lifting and landing the foot, changing the heading direction of the toes, changing the inclination angle between the foot and the ground, etc., to simulate various possible motion states of the frogman during underwater swimming, such as the heaving and dipping of the body, the change of frogman's swimming direction and the swing from side to side, which is as the circumstance shown in Fig.…”

Body sensor networks for monitoring performances in sports: A brief overview and some new thoughts

“…In Ref., [17] wearable sensors attached to swimmer's back (Horizontally) are used to design a biofeedback control system for freestyle swimming based on trunk rotation measurement. Four recreational swimmers have swum 200 m with and without feedback.…”

“…Table 3. Types of classifiers used as well as the classification results/performance of the sensor in performance monitoring for various sports and the corresponding references [13] Stroke type, Lap time, Lap count, Moving Average filtering of acceleration and stroke frequency and Distance per stroke gyroscope data to find breathing pattern [17] Lap time, Rotation status, Stroke rate Raw acceleration data [21] Stroke counts for front-crawl, Raw acceleration data; Calculate Pearson's correlation coefficient breaststroke, backstroke (correlation between 0.98 and 1) [22] Lap time, Velocity, Stroke count Calculate Kolmogorov-Smirnov test, t-Test, Pearson's correlation coefficient, Stroke duration, Stroke rate, Stroke phases Different types of errors [23] Breast stroke velocity Bayesian algorithm, estimate velocity model parameters iteratively using maximum posteriori (MAP) criterion and calculate cycle mean velocity (CMV) [24] Front crawl velocity Gaussian process (GP) regression framework or parameter learning to calculate cycle mean velocity (CMV) [25] Stroke rate Maximums algorithm to calculate stroke rate and the time difference between strokes [26] Stroke rate Lowpass filtering of raw acceleration data to find highpass data; Total acceleration Mean velocity data by summing the data in x, y, z axes; Velocity profile by integrating total acceleration data (using trapezoidal rule) over time [27] Lap count, Stroke count, Lap time, Iterative algorithms in an ample-by-sample basis, Speed per lap, Total swam distance, Total swimming time, Swimming efficiency State-machine and spectral analysis, Decision graph of depth two [28] Stroke phases Temporal phase detection algorithm based on slope tracker by Kalman filtering, adaptive…”

“…Bluetooth (BT) can be used for wireless data transmission due to its pervasiveness and low-power consumption in real-time wearable system. [17] Not sufficient accuracy for feedback Needs more participants, more accurate information to the swimmers. time keeping as well as more appropriate swimming techniques for real-time feedback.…”

A Survey on Biofeedback and Actuation in Wireless Body Area Networks (WBANs)

“…Trade-offs in selection and WBAN performance in regard of each selection criterion are summarised in Table II. • Integrated mode fuses sensors, actuators and a control hub in a single node. A typical example application can be found in [34] where an inertial sensor and a microprocessor are jointly placed in a single node and used to collect data of swimmer's body rotation. In some special environment, swimming, for instance, wireless date transmission is limited so integrated WBAN mode is a convenient solution.…”