Zhelong Wang

Zhelong Wang

Auto-generated profile, based on publicly available information

Zhelong Wang

Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education, Dalian University of Technology, Dalian, China

Research Focus & Metrics

Academic Career Length

24Years (2003-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 May 2015 in IEEE/ASME Transactions on Mechatronics
Verified
Journal Article
Closed access
ZWZhelong Wang
Zhelong Wang
HZHongyu Zhao
Hongyu Zhao
SQSen Qiu
Sen Qiu
QGQin Gao
Qin Gao
Zero velocity updates (ZUPT) is an effective way for the foot-mounted inertial pedestrian navigation systems. For the ZUPT technique to work properly, it is necessary to correctly detect the stance phase of each gait cycle. An adaptive stance-phase detection method is proposed based solely on an inertial sensor, which deals with the measurement fluctuations in swing and stance phases differently, and applies a clustering algorithm to partition the potential gait phases into true and false clusters, thereby yielding a time threshold to eliminate the false gait phases. The roles of the detection parameters and the relationship between them are analyzed to offer some suggestions for parameter tuning. Detection performance is evaluated with multisubject experimental data collected at varying walking speeds. The evaluation results show that the proposed detection method performs well in the presence of measurement fluctuations, which can make the detection of stance phases more robust and the choice of detection parameters more flexible.

11 February 2016 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
SQSen Qiu
Sen Qiu
ZWZhelong Wang
Zhelong Wang
HZHongyu Zhao
Hongyu Zhao
Huosheng HuHuosheng Hu
Huosheng Hu
This paper presents a wearable sensor approach to motion measurements of human lower limbs, in which subjects perform specified walking trials at self-administered speeds so that their level walking and stair ascent capacity can be effectively evaluated. After an initial sensor alignment with the reduced error, quaternion is used to represent 3-D orientation and an optimized gradient descent algorithm is deployed to calculate the quaternion derivative. Sensors on the shank offer additional information to accurately determine the instances of both swing and stance phases. The Denavit-Hartenberg convention is used to set up the kinematic chains when the foot stays stationary on the ground, producing state constraints to minimize the estimation error of knee position. The reliability of this system, from the measurement point of view, has been validated by means of the results obtained from a commercial motion tracking system, namely, Vicon, on healthy subjects. The step size error and the position estimation accuracy change are studied. The experimental results demonstrated that the extensively existed sensor misplacement and sensor drift problems can be well solved. The proposed self-contained and environment-independent system is capable of providing consistent tracking of human lower limbs without significant drift.

16 May 2012 in IEEE Transactions on Information Technology in Biomedicine
Verified
Journal Article
Closed access
ZWZhelong Wang
Zhelong Wang
MJMing Jiang
Ming Jiang
YHYaohua Hu
Yaohua Hu
HLHongyi Li
Hongyi Li
Human activity recognition by using wearable sensors has gained tremendous interest in recent years among a range of health-related areas. To automatically recognize various human activities from wearable sensor data, many classification methods have been tried in prior studies, but most of them lack the incremental learning abilities. In this study, an incremental learning method is proposed for sensor-based human activity recognition. The proposed method is designed based on probabilistic neural networks and an adjustable fuzzy clustering algorithm. The proposed method may achieve the following features. 1) It can easily learn additional information from new training data to improve the recognition accuracy. 2) It can freely add new activities to be detected, as well as remove existing activities. 3) The updating process from new training data does not require previously used training data. An experiment was performed to collect realistic wearable sensor data from a range of activities of daily life. The experimental results showed that the proposed method achieved a good tradeoff between incremental learning ability and the recognition accuracy. The experimental results from comparison with other classification methods demonstrated the effectiveness of the proposed method further.

19 January 2016 in IEEE Sensors Journal
Verified
Journal Article
Closed access
ZWZhelong Wang
Zhelong Wang
DWDonghui Wu
Donghui Wu
JCJianming Chen
Jianming Chen
AGAhmed Ghoneim
Ahmed Ghoneim
MHMohammad Anwar Hossain
Mohammad Anwar Hossain
In recent years, sensor-based human activity recognition has attracted lots of studies. This paper presents a single wearable triaxial accelerometer-based human activity recognition system, which can be used in the real life of activity monitoring. The sensor is attached around different parts of the body: waist and left ankle, respectively. In order to improve the accuracy and reduce the computational complexity, the ensemble empirical mode decomposition (EEMD)-based features and the feature selection (FS) method are introduced, respectively. Considering the feature interaction, a game theory-based FS method is proposed to evaluate the features. Relevant and distinguished features that are robust to the placement of sensors are selected. In the experiment, the data acquired from the two different parts of the body, waist and ankle, are utilized to evaluate the proposed FS method. To verify the effectiveness of the proposed method, k-nearst neighbor and support vector machine are used to recognize the human activities from waist and ankle. Experiment results demonstrate the effectiveness of the introduced EEMD-based features for human activity recognition. Compared with the representative FS methods, including Relief-F and minimum-redundancy maximum-relevance, the proposed FS approach selects fewer features and provides higher accuracy. The results also show that the triaxial accelerometer around the waist produces optimal results.

22 April 2023 in Computers in Biology and Medicine
Verified
Journal Article
Closed access
TFTianqi Fan
Tianqi Fan
SQSen Qiu
Sen Qiu
ZWZhelong Wang
Zhelong Wang
HZHongyu Zhao
Hongyu Zhao
JJJunhan Jiang
Junhan Jiang
NJNan Jiang
Nan Jiang

27 September 2021 in International Journal of Intelligent Systems
Verified
Journal Article
Closed access
PDF file
SQSen Qiu
Sen Qiu
HZHongkai Zhao
Hongkai Zhao
NJNan Jiang
Nan Jiang
DWDonghui Wu
Donghui Wu
GSGuangcai Song
Guangcai Song
ZWZhelong Wang
Zhelong Wang