Ferber, ReedClermont, Christian Arthur2019-06-252019-06-252019-06-21Clermont, C. A. (2019). Making Sense of Sensor Data for Recreational and Competitive Runners: Detecting Typical and Atypical Running Biomechanics (Doctoral thesis, University of Calgary, Calgary, Canada). Retrieved from https://prism.ucalgary.ca.http://hdl.handle.net/1880/110524Running-related injuries can result from a combination of intrinsic and extrinsic risk factors (e.g., running biomechanics, performance level, fatigue). Unfortunately, running biomechanics research has traditionally been performed in the lab. Therefore, the main objectives of this thesis were to establish novel methods to quantify typical running biomechanics for competitive and recreational runners and identify atypical changes due to fatigue and muscle soreness from a marathon race. In Chapter Three, it was found that competitive and recreational runners can be classified with greater than 80% accuracy using machine learning and lower-limb kinematic data. The translation of these methods to wearable sensor data can improve the generalizability of these findings. Therefore, in Chapter Four, centre of mass (CoM) acceleration data was used to classify competitive and recreational runners in sex-specific subgroups with greater than 80%. Thus, these experiments sought to establish specific subgroup running gait patterns both inside and out of the laboratory setting. Chapter Five expanded upon these findings and used a commercially-available wearable sensor and new statistical methods to detect alterations in subject-specific running biomechanics over the course of a fatigue-inducing marathon race. The culmination of these studies was Chapter Six wherein CoM acceleration data identified subject-specific typical running patterns prior to the marathon and determined whether fatigue-induced changes in gait patterns persist in the days following the race. The findings indicated an atypical shift in the runners’ CoM motion toward the mediolateral axis with only two days of recovery. In conclusion, it is evident that wearable sensor data, signal processing, and sophisticated analyses can be used to detect typical and atypical running biomechanics that may be associated with changes in performance and/or potential heightened risks of injury.engUniversity of Calgary graduate students retain copyright ownership and moral rights for their thesis. You may use this material in any way that is permitted by the Copyright Act or through licensing that has been assigned to the document. For uses that are not allowable under copyright legislation or licensing, you are required to seek permission.BiomechanicsRunningWearable TechnologyGait AnalysisEducation--HealthEducation--Technologydoctoral thesis10.11575/PRISM/36655