Go to the NASA Homepage
Search >
Click to Search
Human Systems Integration Division homepageHuman Systems Integration Division homepage Organization pageOrganization page Technical Areas pageTechnical Areas page Outreach and Publications pageOutreach and Publications page Contact pageContact page
Human Systems Integration Division Homepage
Outreach & Publications Sidebar Header
Go to the Outreach & Publications pageGo to the Outreach & Publications page
Go to Awards pageGo to Awards page
Go to News pageGo to News page
Go to Factsheets pageGo to Factsheets page
Go to Multimedia pageGo to Multimedia page
Go to Human Factors 101 pageGo to Human Factors 101 page
What is Human System Integration? Website
Publication Header
Moving the Lab into the Mountains: A Pilot Study of Human Activity Recognition in Unstructured Environments  (2021)
Abstract Header
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.
Private Investigators Header
Authors Header
Groups Header
Keywords Header
accelerometer, activity, artificial, biomechanics, convolutional, deep, human, inertial, intelligence, learning, measurement, network, neural, recognition, sensor, wearable
References Header
Sensors 2021, 21, 654. https://doi.org/10.3390/s21020654
Download Header
Adobe PDF Icon  sensors_21_00654_web.pdf (Download Acrobat Reader Click to download Adobe Acrabat Reader)
  (530KB) (application/pdf)
Go to the First Gov Homepage
Go to the NASA - National Aeronautics and Space Administration Homepage
Curator: Phil So
NASA Official: Jessica Nowinski
Last Updated: August 15, 2019