Random forest algorithms for recognizing daily life activities using plantar pressure information: a smart-shoe study

被引:12
作者
Ren, Dian [1 ,2 ]
Aubert-Kato, Nathanael [3 ,4 ]
Anzai, Emi [5 ]
Ohta, Yuji [1 ]
Tripette, Julien [1 ,2 ,4 ,6 ]
机构
[1] Ochanomizu Univ, Dept Human & Environm Sci, Tokyo, Japan
[2] Ochanomizu Univ, Leading Grad Sch Promot Ctr, Tokyo, Japan
[3] Ochanomizu Univ, Dept Comp Sci, Tokyo, Japan
[4] Ochanomizu Univ, Ctr Interdisciplinary AI & Data Sci, Tokyo, Japan
[5] Nara Womens Univ, Dept Human Life & Environm, Nara, Japan
[6] Natl Inst Biomed Innovat Hlth & Nutr, Dept Phys Act Res, Tokyo, Japan
基金
日本学术振兴会;
关键词
Smart shoes; Activity tracker; Sensor; Activity recognition; Physical behavior; Random forest; Plantar pressure; Physical activity; Health promotion; Wearable; PHYSICAL-ACTIVITY; HIP; SENSORS; HEALTH;
D O I
10.7717/peerj.10170
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
Background: Wearable activity trackers are regarded as a new opportunity to deliver health promotion interventions. Indeed, while the prediction of active behaviors is currently primarily relying on the processing of accelerometer sensor data, the emergence of smart clothes with multi-sensing capacities is offering new possibilities. Algorithms able to process data from a variety of smart devices and classify daily life activities could therefore be of particular importance to achieve a more accurate evaluation of physical behaviors. This study aims to (1) develop an activity recognition algorithm based on the processing of plantar pressure information provided by a smart-shoe prototype and (2) to determine the optimal hardware and software configurations. Method: Seventeen subjects wore a pair of smart-shoe prototypes composed of plantar pressure measurement insoles, and they performed the following nine activities: sitting, standing, walking on a flat surface, walking upstairs, walking downstairs, walking up a slope, running, cycling, and completing office work. The insole featured seven pressure sensors. For each activity, at least four minutes of plantar pressure data were collected. The plantar pressure data were cut in overlapping windows of different lengths and 167 features were extracted for each window. Data were split into training and test samples using a subject-wise assignment method. A random forest model was trained to recognize activity. The resulting activity recognition algorithms were evaluated on the test sample. A multi hold-out procedure allowed repeating the operation with 5 different assignments. The analytic conditions were modulated to test (1) different window lengths (1-60 seconds), (2) some selected sensor configurations and (3) different numbers of data features. Results: A window length of 20 s was found to be optimum and therefore used for the rest of the analysis. Using all the sensors and all 167 features, the smart shoes predicted the activities with an average success of 89%. "Running" demonstrated the highest sensitivity (100%). "Walking up a slope" was linked with the lowest performance (63%), with the majority of the false negatives being "walking on a flat surface" and "walking upstairs." Some 2- and 3-sensor configurations were linked with an average success rate of 87%. Reducing the number of features down to 20 does not alter significantly the performance of the algorithm. Conclusion: High-performance human behavior recognition using plantar pressure data only is possible. In the future, smart-shoe devices could contribute to the evaluation of daily physical activities. Minimalist configurations integrating only a small number of sensors and computing a reduced number of selected features could maintain a satisfying performance. Future experiments must include a more heterogeneous population.
引用
收藏
页数:30
相关论文
共 38 条
[11]   Instrumented shoes for activity classification in the elderly [J].
el Achkar, Christopher Moufawad ;
Lenoble-Hoskovec, Constanze ;
Paraschiv-Ionescu, Anisoara ;
Major, Kristof ;
Buela, Christophe ;
Aminian, Kamiar .
GAIT & POSTURE, 2016, 44 :12-17
[12]   An Overview of Smart Shoes in the Internet of Health Things: Gait and Mobility Assessment in Health Promotion and Disease Monitoring [J].
Eskofier, Bjoern M. ;
Lee, Sunghoon Ivan ;
Baron, Manuela ;
Simon, Andre ;
Martindale, Christine F. ;
Gassner, Heiko ;
Klucken, Jochen .
APPLIED SCIENCES-BASEL, 2017, 7 (10)
[13]   The Effect of Physical Activity Interventions Comprising Wearables and Smartphone Applications on Physical Activity: a Systematic Review and Meta-analysis [J].
Gal, Roxanne ;
May, Anne M. ;
van Overmeeren, Elon J. ;
Simons, Monique ;
Monninkhof, Evelyn M. .
SPORTS MEDICINE-OPEN, 2018, 4
[14]   The Pediatric SmartShoe: Wearable Sensor System for Ambulatory Monitoring of Physical Activity and Gait [J].
Hegde, Nagaraj ;
Zhang, Ting ;
Uswatte, Gitendra ;
Taub, Edward ;
Barman, Joydip ;
Mckay, Staci ;
Taylor, Andrea ;
Morris, David M. ;
Griffin, Angi ;
Sazonov, Edward S. .
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, 2018, 26 (02) :477-486
[15]   New Horizons in Sensor Development [J].
Intille, Stephen S. ;
Lester, Jonathan ;
Sallis, James F. ;
Duncan, Glen .
MEDICINE AND SCIENCE IN SPORTS AND EXERCISE, 2012, 44 :S24-S31
[16]   UWALK: the development of a multi-strategy, community-wide physical activity program [J].
Jennings, Cally A. ;
Berry, Tanya R. ;
Carson, Valerie ;
Culos-Reed, S. Nicole ;
Duncan, Mitch J. ;
Loitz, Christina C. ;
McCormack, Gavin R. ;
McHugh, Tara-Leigh F. ;
Spence, John C. ;
Vallance, Jeff K. ;
Mummery, W. Kerry .
TRANSLATIONAL BEHAVIORAL MEDICINE, 2017, 7 (01) :16-27
[17]  
Jones E., 2001, SciPy: Open Source Scientific Tools for Python, DOI DOI 10.1002/MP.16056
[18]   Comparison of physical activity assessed using hip- and wrist-worn accelerometers [J].
Kamada, Masamitsu ;
Shiroma, Eric J. ;
Harris, Tamara B. ;
Lee, I-Min .
GAIT & POSTURE, 2016, 44 :23-28
[19]   Comparison of two waist-mounted and two ankle-mounted electronic pedometers [J].
Karabulut, M ;
Crouter, SE ;
Bassett, DR .
EUROPEAN JOURNAL OF APPLIED PHYSIOLOGY, 2005, 95 (04) :335-343
[20]   Improving Hip-Worn Accelerometer Estimates of Sitting Using Machine Learning Methods [J].
Kerr, Jacqueline ;
Carlson, Jordan ;
Godbole, Suneeta ;
Cadmus-Bertram, Lisa ;
Bellettiere, John ;
Hartman, Sheri .
MEDICINE AND SCIENCE IN SPORTS AND EXERCISE, 2018, 50 (07) :1518-1524