Human Action Recognition based on LSTM Model using Smartphone Sensor

被引：0

作者：

Han, Yull Kyu ^{[1
]}

Choi, Young Bok ^{[1
]}

机构：

[1] Tongmyong Univ, Dept Eelect Engn, Busan, South Korea

来源：

2019 ELEVENTH INTERNATIONAL CONFERENCE ON UBIQUITOUS AND FUTURE NETWORKS (ICUFN 2019) | 2019年

基金：

新加坡国家研究基金会;

关键词：

human action recognition; disasters detection; deep learning; LSTM;

D O I：

10.1109/icufn.2019.8806065

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We propose a deep learning model for human action recognition in order to quickly detect occurrence of disasters such as fire and terrorism. Using the acceleration and gyroscope sensors built in the smartphone, four kinds of data on human behavior were obtained and human behavior was classified through the LSTM deep learning model. As an experiment, it was confirmed that the LSTM model can be classified 95.47% accurately.

引用

页码：748 / 750

页数：3

共 7 条

[1] Joong Soo Han, 2018, KIISE Transactions on Computing Practices, V24, P358, DOI 10.5626/KTCP.2018.24.7.358
[2] Smart approach to liquid electrolyte-based multi-colored electrochemiluminescence for lighting applications
Kim, J. Y.
Cheon, S.
Lee, H.
Oh, J. -Y.
Lee, J. -I.
Ryu, H.
Kim, Y. -H.
Hwang, C. -S.
[J]. JOURNAL OF MATERIALS CHEMISTRY C, 2017, 5 (17) : 4214 - 4218
[3] Lee Myeong-Chun, 2011, KOREA INFORM SCI SOC, V38, P263
[4] An Automatic User-Adapted Physical Activity Classification Method Using Smartphones
Li, Pengfei
Wang, Yu
Tian, Yu
Zhou, Tian-Shu
Li, Jing-Song
[J]. IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2017, 64 (03) : 706 - 714
[5] 박종영, 2018, 전기학회논문지, V67, P1536
[6] Learning Actionlet Ensemble for 3D Human Action Recognition
Wang, Jiang
Liu, Zicheng
Wu, Ying
Yuan, Junsong
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2014, 36 (05) : 914 - 927
[7] Sensor-based adaptive activity recognition with dynamically available sensors
Wen, Jiahui
Wang, Zhiying
[J]. NEUROCOMPUTING, 2016, 218 : 307 - 317

← 1 →