Subject-specific and group-based running pattern classification using a single wearable sensor

• Published in: Journal of biomechanics Vol. 84; pp. 227 - 233
• Main Authors: Ahamed, Nizam Uddin, Kobsar, Dylan, Benson, Lauren C., Clermont, Christian A., Osis, Sean T., Ferber, Reed
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 14.02.2019; Elsevier Limited
• Subjects: Accelerometer; Accuracy; Age; Biomechanical Phenomena; Biomechanics; Braking; Classification; Female; Gait; Humans; Humidity; Inclination; Injuries; Laboratories; Learning algorithms; Machine Learning; Male; Marathons; Middle Aged; Model accuracy; Models, Biological; Monitoring, Physiologic - instrumentation; Neuromuscular diseases; Pattern classification; Pelvis; Precipitation; Random forest; Running; Running - physiology; Variables; Vertical oscillations; Wearable computers; Wearable Electronic Devices; Wearable technology; United States > US; Biomechanics; Accelerometer; Random forest; Gait; Inclination
• ISSN: 0021-9290; 1873-2380; 1873-2380
• DOI: 10.1016/j.jbiomech.2019.01.001

The objective of this study was to determine whether subject-specific or group-based models provided better classification accuracy to identify changes in biomechanical running gait patterns across different inclination conditions. The classification process was based on measurements from a single wearable sensor using a total of 41,780 strides from eleven recreational runners while running in real-world and uncontrolled environment. Biomechanical variables included pelvic drop, ground contact time, braking, vertical oscillation of pelvis, pelvic rotation, and cadence were recorded during running on three inclination grades: downhill, −2° to −7°; level, −0.2° to +0.2°; and uphill, +2° to +7°. An ensemble and non-linear machine learning algorithm, random forest (RF), was used to classify inclination condition and determine the importance of each of the biomechanical variables. Classification accuracy was determined for subject-specific and group-based RF models. The mean classification accuracy of all subject-specific RF models was 86.29%, while group-based classification accuracy was 76.17%. Braking was identified as the most important variable for all the runners using the group-based model and for most of the runners based on a subject-specific models. In addition, individual runners used different strategies across different inclination conditions and the ranked order of variable importance was unique for each runner. These results demonstrate that subject-specific models can better characterize changes in gait biomechanical patterns compared to a more traditional group-based approach.