Brian Russell1, Andrew McDaid2, William Toscano3, Patria Hume1. 1. Sports Performance Institute, Auckland University of Technology, Auckland 0632, New Zealand. 2. Department of Mechanical Engineering, University of Auckland, Auckland 1142, New Zealand. 3. National Aeronautics and Space Administration, Ames Research Center, Moffett Field, CA 94043, USA.
Abstract
GOAL: To develop and validate a field-based data collection and assessment method for human activity recognition in the mountains with variations in terrain and fatigue using a single accelerometer and a deep learning model. METHODS: The protocol generated an unsupervised labelled dataset of various long-term field-based activities including run, walk, stand, lay and obstacle climb. Activity was voluntary so transitions could not be determined a priori. Terrain variations included slope, crossing rivers, obstacles and surfaces including road, gravel, clay, mud, long grass and rough track. Fatigue levels were modulated between rested to physical exhaustion. The dataset was used to train a deep learning convolutional neural network (CNN) capable of being deployed on battery powered devices. The human activity recognition results were compared to a lab-based dataset with 1,098,204 samples and six features, uniform smooth surfaces, non-fatigued supervised participants and activity labelling defined by the protocol. RESULTS: The trail run dataset had 3,829,759 samples with five features. The repetitive activities and single instance activities required hyper parameter tuning to reach an overall accuracy 0.978 with a minimum class precision for the one-off activity (climbing gate) of 0.802. CONCLUSION: The experimental results showed that the CNN deep learning model performed well with terrain and fatigue variations compared to the lab equivalents (accuracy 97.8% vs. 97.7% for trail vs. lab). SIGNIFICANCE: To the authors knowledge this study demonstrated the first successful human activity recognition (HAR) in a mountain environment. A robust and repeatable protocol was developed to generate a validated trail running dataset when there were no observers present and activity types changed on a voluntary basis across variations in terrain surface and both cognitive and physical fatigue levels.
GOAL: To develop and validate a field-based data collection and assessment method for human activity recognition in the mountains with variations in terrain and fatigue using a single accelerometer and a deep learning model. METHODS: The protocol generated an unsupervised labelled dataset of various long-term field-based activities including run, walk, stand, lay and obstacle climb. Activity was voluntary so transitions could not be determined a priori. Terrain variations included slope, crossing rivers, obstacles and surfaces including road, gravel, clay, mud, long grass and rough track. Fatigue levels were modulated between rested to physical exhaustion. The dataset was used to train a deep learning convolutional neural network (CNN) capable of being deployed on battery powered devices. The human activity recognition results were compared to a lab-based dataset with 1,098,204 samples and six features, uniform smooth surfaces, non-fatigued supervised participants and activity labelling defined by the protocol. RESULTS: The trail run dataset had 3,829,759 samples with five features. The repetitive activities and single instance activities required hyper parameter tuning to reach an overall accuracy 0.978 with a minimum class precision for the one-off activity (climbing gate) of 0.802. CONCLUSION: The experimental results showed that the CNN deep learning model performed well with terrain and fatigue variations compared to the lab equivalents (accuracy 97.8% vs. 97.7% for trail vs. lab). SIGNIFICANCE: To the authors knowledge this study demonstrated the first successful human activity recognition (HAR) in a mountain environment. A robust and repeatable protocol was developed to generate a validated trail running dataset when there were no observers present and activity types changed on a voluntary basis across variations in terrain surface and both cognitive and physical fatigue levels.
Entities:
Keywords:
accelerometer; artificial intelligence; biomechanics; convolutional neural network; deep learning; human activity recognition; inertial measurement unit; wearable sensor
Authors: Joel T Fuller; Clint R Bellenger; Dominic Thewlis; John Arnold; Rebecca L Thomson; Margarita D Tsiros; Eileen Y Robertson; Jonathan D Buckley Journal: Int J Sports Physiol Perform Date: 2016-08-24 Impact factor: 4.010
Authors: Willem J R Bossers; Lucas H V van der Woude; Froukje Boersma; Erik J A Scherder; Marieke J G van Heuvelen Journal: Dement Geriatr Cogn Dis Extra Date: 2012-12-08