A Multipurpose Wearable Sensor-Based System for Weight Training

被引:14
作者
Balkhi, Parinaz [1 ]
Moallem, Mehrdad [1 ]
机构
[1] Simon Fraser Univ, Sch Mechatron Syst Engn, Surrey, BC V3T 0A3, Canada
来源
AUTOMATION | 2022年 / 3卷 / 01期
关键词
smart fitness glove; automatic weight detection; automatic activity recognition; wearable sensors; random forest; support vector machine; decision tree; KNN; neural networks; FORCE-MYOGRAPHY; PERFORMANCE; PEDOMETERS; ISSUES; HEALTH; BODY;
D O I
10.3390/automation3010007
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In recent years, there has been growing interest in automated tracking and detection of sports activities. Researchers have shown that providing activity information to individuals during their exercise routines can greatly help them in achieving their exercise goals. In particular, such information would help them to maximize workout efficiency and prevent overreaching and overtraining. This paper presents the development of a novel multipurpose wearable device for automatic weight detection, activity type recognition, and count repetition in sports activities such as weight training. The device monitors weights and activities by using an inertial measurement unit (IMU), an accelerometer, and three force sensors mounted in a glove, and classifies them by utilizing developed machine learning models. For weight detection purposes, different classifiers including Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), and Multi-layer Perceptron Neural Networks (MLP) were investigated. For activity recognition, the K nearest neighbor (KNN), Decision Tree (DT), Random Forest (RF), and SVM models were trained and examined. Experimental results indicate that the SVM classifier can achieve the highest accuracy for weight detection whereas RF can outperform other classifiers for activity recognition. The results indicate feasibility of developing a wearable device that can provide in-situ accurate information regarding the lifted weight and activity type with minimum physical intervention.
引用
收藏
页码:132 / 152
页数:21
相关论文
共 32 条
[1]   Toward Intuitive Prosthetic Control Solving Common Issues Using Force Myography, Surface Electromyography, and Pattern Recognition in a Pilot Case Study [J].
Ahmadizadeh, Chakaveh ;
Merhi, Lukas-Karim ;
Pousett, Brittany ;
Sangha, Sohail ;
Menon, Carlo .
IEEE ROBOTICS & AUTOMATION MAGAZINE, 2017, 24 (04) :102-111
[2]   A Smart Glove to Track Fitness Exercises by Reading Hand Palm [J].
Akpa, A. H. Elder ;
Fujiwara, Masashi ;
Suwa, Hirohiko ;
Arakawa, Yutaka ;
Yasumoto, Keiichi .
JOURNAL OF SENSORS, 2019, 2019
[3]  
Bashar SK, 2020, IEEE ENG MED BIO, P5888, DOI 10.1109/EMBC44109.2020.9176239
[4]   Muscle-strengthening Exercise Epidemiology: a New Frontier in Chronic Disease Prevention [J].
Bennie, Jason A. ;
Shakespear-Druery, Jane ;
De Cocker, Katrien .
SPORTS MEDICINE-OPEN, 2020, 6 (01)
[5]   Using pedometers to increase physical activity and improve health - A systematic review [J].
Bravata, Dena M. ;
Smith-Spangler, Crystal ;
Sundaram, Vandana ;
Gienger, Allison L. ;
Lin, Nancy ;
Lewis, Robyn ;
Stave, Christopher D. ;
Olkin, Ingram ;
Sirard, John R. .
JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION, 2007, 298 (19) :2296-2304
[6]  
Chatfield Chris, 2003, The Analysis of Time Series: An Introduction, DOI DOI 10.4324/9780203491683
[7]  
Das D., 2017, P 16 IEEE INT C MACH
[8]   Fabrication, Structure Characterization, and Performance Testing of Piezoelectret-Film Sensors for Recording Body Motion [J].
Fang, Peng ;
Ma, Xingchen ;
Li, Xiangxin ;
Qiu, Xunlin ;
Gerhard, Reimund ;
Zhang, Xiaoqing ;
Li, Guanglin .
IEEE SENSORS JOURNAL, 2018, 18 (01) :401-412
[9]  
Farrokhi A., 2021, SN Comput. Sci, V3, P1, DOI [10.1007/s42979-021-00940-x, DOI 10.1007/S42979-021-00940-X]
[10]   Preprocessing techniques for context recognition from accelerometer data [J].
Figo, Davide ;
Diniz, Pedro C. ;
Ferreira, Diogo R. ;
Cardoso, Joao M. P. .
PERSONAL AND UBIQUITOUS COMPUTING, 2010, 14 (07) :645-662