Enhanced Hand-Oriented Activity Recognition Based on Smartwatch Sensor Data Using LSTMs

被引:41
作者
Mekruksavanich, Sakorn [1 ]
Jitpattanakul, Anuchit [2 ]
Youplao, Phichai [3 ,4 ]
Yupapin, Preecha [3 ,4 ]
机构
[1] Univ Phayao, Sch Informat & Commun Technol, Dept Comp Engn, Phayao 56000, Thailand
[2] King Mongkuts Univ Technol North Bangkok, Intelligent & Nonlinear Dynam Innovat Res Ctr, Dept Math, Fac Sci Appl, Bangkok 10800, Thailand
[3] Ton Duc Thang Univ, Adv Inst Mat Sci, Computat Opt Res Grp, Dist 7, Ho Chi Minh City 729000, Vietnam
[4] Ton Duc Thang Univ, Fac Sci Appl, Dist 7, Ho Chi Minh City 729000, Vietnam
来源
SYMMETRY-BASEL | 2020年 / 12卷 / 09期
关键词
smartwatch sensor; time-series data; smart sensor; human activity recognition; deep learning; long short-term memory;
D O I
10.3390/sym12091570
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
The creation of the Internet of Things (IoT), along with the latest developments in wearable technology, has provided new opportunities in human activity recognition (HAR). The modern smartwatch offers the potential for data from sensors to be relayed to novel IoT platforms, which allow the constant tracking and monitoring of human movement and behavior. Recently, traditional activity recognition techniques have done research in advance by choosing machine learning methods such as artificial neural network, decision tree, support vector machine, and naive Bayes. Nonetheless, these conventional machine learning techniques depend inevitably on heuristically handcrafted feature extraction, in which human domain knowledge is normally limited. This work proposes a hybrid deep learning model called CNN-LSTM that employed Long Short-Term Memory (LSTM) networks for activity recognition with the Convolution Neural Network (CNN). The study makes use of HAR involving smartwatches to categorize hand movements. Using the study based on the Wireless Sensor Data Mining (WISDM) public benchmark dataset, the recognition abilities of the deep learning model can be accessed. The accuracy, precision, recall, and F-measure statistics are employed using the evaluation metrics to assess the recognition abilities of LSTM models proposed. The findings indicate that this hybrid deep learning model offers better performance than its rivals, where the achievement of 96.2% accuracy, while the f-measure is 96.3%, is obtained. The results show that the proposed CNN-LSTM can support an improvement of the performance of activity recognition.
引用
收藏
页数:19
相关论文
共 33 条
[1]   Classification of Human Daily Activities Using Ensemble Methods Based on Smartphone Inertial Sensors [J].
Abd Rahim, Ku Nurhanim Ku ;
Elamvazuthi, I. ;
Izhar, Lila Iznita ;
Capi, Genci .
SENSORS, 2018, 18 (12)
[2]  
[Anonymous], 2020, SENSORS BASEL
[3]   Performance Evaluation of Convolutional Neural Network for Hand Gesture Recognition Using EMG [J].
Asif, Ali Raza ;
Waris, Asim ;
Gilani, Syed Omer ;
Jamil, Mohsin ;
Ashraf, Hassan ;
Shafique, Muhammad ;
Niazi, Imran Khan .
SENSORS, 2020, 20 (06)
[4]   A Comparison of Machine Learning and Deep Learning Techniques for Activity Recognition using Mobile Devices [J].
Baldominos, Alejandro ;
Cervantes, Alejandro ;
Saez, Yago ;
Isasi, Pedro .
SENSORS, 2019, 19 (03)
[5]   Stride Segmentation during Free Walk Movements Using Multi-Dimensional Subsequence Dynamic Time Warping on Inertial Sensor Data [J].
Barth, Jens ;
Oberndorfer, Caecilia ;
Pasluosta, Cristian ;
Schuelein, Samuel ;
Gassner, Heiko ;
Reinfelder, Samuel ;
Kugler, Patrick ;
Schuldhaus, Dominik ;
Winkler, Juergen ;
Klucken, Jochen ;
Eskofier, Bjoern M. .
SENSORS, 2015, 15 (03) :6419-6440
[6]   A Tutorial on Human Activity Recognition Using Body-Worn Inertial Sensors [J].
Bulling, Andreas ;
Blanke, Ulf ;
Schiele, Bernt .
ACM COMPUTING SURVEYS, 2014, 46 (03)
[7]  
Burmaoglu S., 2018, EVOLUTION MAP WEARAB, P275, DOI [10.1016/B978-0-12-811810-8.00014-2, DOI 10.1016/B978-0-12-811810-8.00014-2]
[8]   A Study of the Use of Gyroscope Measurements in Wearable Fall Detection Systems [J].
Casilari, Eduardo ;
Alvarez-Marco, Moises ;
Garcia-Lagos, Francisco .
SYMMETRY-BASEL, 2020, 12 (04)
[9]   Wrist-worn and chest-strap wearable devices: Systematic review on accuracy and metrological characteristics [J].
Cosoli, Gloria ;
Spinsante, Susanna ;
Scalise, Lorenzo .
MEASUREMENT, 2020, 159
[10]  
Devanne M, 2019, IEEE SYS MAN CYBERN, P3318, DOI [10.1109/smc.2019.8914457, 10.1109/SMC.2019.8914457]