文献类型：期刊文献

英文题名：Impact of Sliding Window Length in Indoor Human Motion Modes and Pose Pattern Recognition Based on Smartphone Sensors

作者：Wang, Gaojing[1];Li, Qingquan[1];Wang, Lei[1];Wang, Wei[2];Wu, Mengqi[2];Liu, Tao[3]

第一作者：Wang, Gaojing

通讯作者：Li, QQ[1];Wang, L[1]

机构：[1]Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & R, Wuhan 430079, Hubei, Peoples R China;[2]Wuhan Univ, Sch Geodesy & Geomat, Wuhan 430079, Hubei, Peoples R China;[3]Henan Univ Econ & Law, Coll Resources & Environm, Zhengzhou 450002, Henan, Peoples R China

第一机构：Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & R, Wuhan 430079, Hubei, Peoples R China

通讯机构：[1]corresponding author), Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & R, Wuhan 430079, Hubei, Peoples R China.

年份：2018

卷号：18

期号：6

外文期刊名：SENSORS

收录：;EI(收录号：20182605362490);Scopus(收录号：2-s2.0-85048786958);WOS:【SCI-EXPANDED(收录号:WOS:000436774300299)】；

基金：This work was supported in part by the National Key Research Development Program of China (2016YFB0502203); by the National Natural Science Foundation of China (41371377, 91546106, 41401444, 41671387); and by the Shenzhen Future Industry Development Funding Program (201507211219247860).

语种：英文

外文关键词：human motion mode; human pose pattern; window length; machine-learning method; smartphone sensors

摘要：Human activity recognition (HAR) is essential for understanding people's habits and behaviors, providing an important data source for precise marketing and research in psychology and sociology. Different approaches have been proposed and applied to HAR. Data segmentation using a sliding window is a basic step during the HAR procedure, wherein the window length directly affects recognition performance. However, the window length is generally randomly selected without systematic study. In this study, we examined the impact of window length on smartphone sensor-based human motion and pose pattern recognition. With data collected from smartphone sensors, we tested a range of window lengths on five popular machine-learning methods: decision tree, support vector machine, K-nearest neighbor, Gaussian naive Bayesian, and adaptive boosting. From the results, we provide recommendations for choosing the appropriate window length. Results corroborate that the influence of window length on the recognition of motion modes is significant but largely limited to pose pattern recognition. For motion mode recognition, a window length between 2.5-3.5 s can provide an optimal tradeoff between recognition performance and speed. Adaptive boosting outperformed the other methods. For pose pattern recognition, 0.5 s was enough to obtain a satisfactory result. In addition, all of the tested methods performed well.