Moving the Lab into the Mountains: A Pilot Study of Human Activity Recognition in Unstructured Environments

被引:13
作者
Russell, Brian [1 ]
McDaid, Andrew [2 ]
Toscano, William [3 ]
Hume, Patria [1 ]
机构
[1] Auckland Univ Technol, Sports Performance Inst, Auckland 0632, New Zealand
[2] Univ Auckland, Dept Mech Engn, Auckland 1142, New Zealand
[3] NASA, Ames Res Ctr, Moffett Field, CA 94043 USA
关键词
human activity recognition; accelerometer; inertial measurement unit; wearable sensor; artificial intelligence; biomechanics; deep learning; convolutional neural network;
D O I
10.3390/s21020654
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
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.
引用
收藏
页码:1 / 14
页数:14
相关论文
共 38 条
[1]   Personalizing Activity Recognition Models Through Quantifying Different Types of Uncertainty Using Wearable Sensors [J].
Akbari, Ali ;
Jafari, Roozbeh .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2020, 67 (09) :2530-2541
[2]  
Alsheikh MA, 2016, P WORKSH 30 AAAI C A, VWS-16-01, P8
[3]   Reliability and diagnostic characteristics of clinical tests of upper limb motor function [J].
Amer, M. ;
Hubert, G. ;
Sullivan, S. J. ;
Herbison, P. ;
Franz, E. A. ;
Hammond-Tooke, G. D. .
JOURNAL OF CLINICAL NEUROSCIENCE, 2012, 19 (09) :1246-1251
[4]  
Anguita Davide, 2012, P INT WORKSH AMB ASS, P216
[5]   Window Size Impact in Human Activity Recognition [J].
Banos, Oresti ;
Galvez, Juan-Manuel ;
Damas, Miguel ;
Pomares, Hector ;
Rojas, Ignacio .
SENSORS, 2014, 14 (04) :6474-6499
[6]   A Phase Variable Approach for IMU-Based Locomotion Activity Recognition [J].
Bartlett, Harrison L. ;
Goldfarb, Michael .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2018, 65 (06) :1330-1338
[7]   PSYCHOPHYSICAL BASES OF PERCEIVED EXERTION [J].
BORG, GAV .
MEDICINE AND SCIENCE IN SPORTS AND EXERCISE, 1982, 14 (05) :377-381
[8]   Recommended Measures for the Assessment of Cognitive and Physical Performance in Older Patients with Dementia: A Systematic Review [J].
Bossers, Willem J. R. ;
Van der Woude, Lucas H. V. ;
Boersma, Froukje ;
Scherder, Erik J. A. ;
van Heuvelen, Marieke J. G. .
DEMENTIA AND GERIATRIC COGNITIVE DISORDERS EXTRA, 2012, 2 (01) :589-609
[9]  
Buckley C, 2017, INT CONF WEARAB IMPL, P197, DOI 10.1109/BSN.2017.7936040
[10]   The effects of 37 hours of continuous wakefulness on the physiological arousal, cognitive performance, self-reported mood, and simulator flight performance of F-117A pilots [J].
Caldwell, JA ;
Caldwell, JL ;
Brown, DL ;
Smith, JK .
MILITARY PSYCHOLOGY, 2004, 16 (03) :163-181