Is a Head-Worn Inertial Sensor a Valid Tool to Monitor Swimming?

Abstract

Purpose: This study aimed to independently validate a wearable inertial sensor designed to monitor training and performance metrics in swimmers. Methods: A total of 4 male (21 [4] y, 1 national and 3 international) and 6 female (22 [3] y, 1 national and 5 international) swimmers completed 15 training sessions in an outdoor 50-m pool. Swimmers were fitted with a wearable device (TritonWear, 9-axis inertial measurement unit with triaxial accelerometer, gyroscope, and magnetometer), placed under the swim cap on top of the occipital protuberance. Video footage was captured for each session to establish criterion values. Absolute error, standardized effect, and Pearson correlation coefficient were used to determine the validity of the wearable device against video footage for total swim distance, total stroke count, mean stroke count, and mean velocity. A Fisher exact test was used to analyze the accuracy of stroke-type identification. Results: Total swim distance was underestimated by the device relative to video analysis. Absolute error was consistently higher for total and mean stroke count, and mean velocity, relative to video analysis. Across all sessions, the device incorrectly detected total time spent in backstroke, breaststroke, butterfly, and freestyle by 51% (15%). The device did not detect time spent in drill. Intraclass correlation coefficient results demonstrated excellent intrarater reliability between repeated measures across all swimming metrics. Conclusions: The wearable device investigated in this study does not accurately measure distance, stroke count, and velocity swimming metrics or detect stroke type. Its use as a training monitoring tool in swimming is limited.

Wearables in Swimming for Real-Time Feedback: A Systematic Review

“…Table 2 summarizes the aims of the studies, the participants´ demographics, and the swim strokes. From the 18 articles included for qualitative synthesis, eight (44.4%) [ 21 , 23 , 24 , 25 , 30 , 31 , 34 , 38 ] assessed wearables exclusively in front crawl, six (33.3%) [ 26 , 27 , 29 , 32 , 33 , 35 ] assessed wearables exclusively in all four swim strokes, two assessed wearables for the tumble turn in front crawl (11.1%) [ 36 , 37 ], one just assessed wearables in breaststroke (5.5%) [ 22 ], and another one assessed wearables in butterfly stroke (5.5%) [ 28 ]. Overall, 177 swimmers were recruited in all studies (103 males, 62 females, and 12 that the authors failed to note the sex of the participants).…”

“…Overall, 177 swimmers were recruited in all studies (103 males, 62 females, and 12 that the authors failed to note the sex of the participants). Four articles recruited elite-level swimmers (22.2%) [ 29 , 32 , 34 , 37 ], two articles recruited international-level participants (11.1%) [ 33 , 35 ], four articles recruited national-level/semi-professional participants (22.2%) [ 22 , 28 , 35 , 38 ], one article recruited local-level participants (5.5%) [ 31 ], and three articles recruited local/non-expert swimmers (16.7%) [ 22 , 25 , 36 ]. Conversely, six articles (33.3%) [ 21 , 23 , 24 , 26 , 27 , 30 ] did not report the swimmers’ competitive level.…”

“…Table 3 consolidates the details on the assessed sensor, the anatomical landmark where it was placed, variables analyzed, and the main findings of the studies. Fourteen studied accelerometers (77.8%) [ 21 , 22 , 23 , 24 , 25 , 26 , 27 , 29 , 32 , 33 , 35 , 36 , 37 , 38 ], seven studied microcontroller units (MCUs) (38.9%) [ 22 , 25 , 26 , 27 , 28 , 29 , 37 ], six studied IMUs (33.3%) [ 21 , 22 , 23 , 24 , 28 , 31 ], three studied visual feedback (16.7%) [ 25 , 26 , 27 ], and just one studied a gyroscope (5.5%) [ 34 ].…”

“…Figure 1 depicts the PRISMA flow diagram for identifying, screening, and checking eligibility, which then helps to determine inclusion of the articles. A total of 18 articles [ 21 , 22 , 23 , 24 , 25 , 26 , 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 , 36 , 37 , 38 ] were included in the qualitative synthesis.…”

Integrated Timing of Stroking, Breathing, and Kicking in Front-Crawl Swimming: A Novel Stroke-by-Stroke Approach Using Wearable Inertial Sensors

“…The sensor location on the head had several advantages, as it did not affect drag, and measured overall body motion. For this reason, this location was used to estimate the stroke parameters or intracyclic velocity of the swimmer [29,30]. Nevertheless, Shell et al found the accuracy of stroke parameter estimation was not sufficient enough for the training monitoring tool [29].…”