Running patterns for male and female competitive and recreational runners based on accelerometer data

Abstract

The purpose of this study was to classify runners in sex-specific groups as either competitive or recreational based on center of mass (CoM) accelerations. Forty-one runners participated in the study (25 male and 16 female), and were labeled as competitive or recreational based on age, sex, and race performance. Three-dimensional acceleration data were collected during a 5-minute treadmill run, and 24 features were extracted. Support vector machine classification models were used to examine the utility of the features in discriminating between competitive and recreational runners within each sex-specific subgroup. Competitive and recreational runners could be classified with 82.63 % and 80.4 % in the male and female models, respectively. Dominant features in both models were related to regularity and variability, with competitive runners exhibiting more consistent running gait patterns, but the specific features were slightly different in each sex-specific model. Therefore, it is important to separate runners into sex-specific competitive and recreational subgroups for future running biomechanical studies. In conclusion, we have demonstrated the ability to analyze running biomechanics in competitive and recreational runners using only CoM acceleration patterns. A runner, clinician, or coach may use this information to monitor how running patterns change as a result of training.

New Considerations for Collecting Biomechanical Data Using Wearable Sensors: The Effect of Different Running Environments

“…Despite the use of 10fold cross-validation of the training dataset to attempt to improve generalizability of classification, the model slightly overfit to the training dataset as there was lower classification accuracy for the independent testing dataset compared to the 10-fold crossvalidation of the training dataset. Regarding real-world usability, previous studies that have classified IMU-generated running and walking patterns have consistently reported classification accuracy greater than 80% (Kobsar et al, 2014(Kobsar et al, , 2015Phinyomark et al, 2014;Ahamed et al, 2018Ahamed et al, , 2019Benson et al, 2018b;Clermont et al, 2018). Thus, the reported 93.17% accuracy for the training dataset and 83.81% accuracy for the independent testing dataset in the current study suggests that this classification mechanism has practical use.…”

“…Inertial measurement units (IMUs) are portable devices that can be used to quantify running biomechanical patterns in a runner's natural environment (Norris et al, 2014;Reenalda et al, 2016), yet, these investigations are still rare (Benson et al, 2018a). Running biomechanical analysis using IMUs is commonly conducted by recording 3D center of mass accelerations and extracting features related to the magnitude, consistency and variability of the signal (Henriksen et al, 2004;Moe-Nilssen and Helbostad, 2004;Kobsar et al, 2014;Benson et al, 2018b;Clermont et al, 2018). There remains an absence of an association between joint-level mechanics commonly investigated using laboratory-based motion capture systems and features generated from center of mass accelerations.…”

The kinematics of cyclic human movement

“…The latter authors state that competitive runners show a greater consistency of their subject-specific movement pattern compared to their recreational opponents, whose gait characteristics become significantly atypical halfway through the race. Further Clermont et al [29] have demonstrated with their approach the ability to differentiate sex-and training level-specific subgroups based on acceleration data. An athlete with a extensive running experience combined with an increased mileage performs necessarily a higher number of strides leading to a more implanted and efficient movement pattern [30].…”

Tibial Acceleration-Based Prediction of Maximal Vertical Loading Rate During Overground Running: A Machine Learning Approach

“…Holzreiter and Köhle (1993) introduced the use of neural networks to assess gait patterns in locomotion biomechanics. Recently more advanced machine learning techniques have been used to detect pathologic gait-patterns (Williams et al, 2015;Zeng et al, 2016), fatigue (Janssen et al, 2011;Op De Beéck et al, 2018) as well as classifying gender, performance-level (Clermont et al, 2018) and age-related running patterns (Fukuchi et al, 2011).…”