Daqing Zhang

Daqing Zhang

Auto-generated profile, based on publicly available information

Daqing Zhang

School of Science, University of Science and Technology Liaoning, Anshan, People’s Republic of China

Research Focus & Metrics

Academic Career Length

37Years (1990-Present)

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

Representative Publications

View All Publications
6 August 2010 in Personal and Ubiquitous Computing
Verified
Journal Article
Closed access
PDF file
BGBin Guo
Bin Guo
DZDaqing Zhang
Daqing Zhang
MIMichita Imai
Michita Imai

30 January 2014 in Personal and Ubiquitous Computing
Verified
Journal Article
Closed access
PDF file
DYDingqi Yang
Dingqi Yang
DZDaqing Zhang
Daqing Zhang
KFKorbinian Frank
Korbinian Frank
PRPatrick Robertson
Patrick Robertson
EJEdel Jennings
Edel Jennings
MLMichael Lichtenstern
Michael Lichtenstern

2 March 2021 in IEEE Transactions on Big Data
Verified
Journal Article
Closed access
CCChao Chen
Chao Chen
QLQiang Liu
Qiang Liu
XWXingchen Wang
Xingchen Wang
CLChengwu Liao
Chengwu Liao
DZDaqing Zhang
Daqing Zhang
In this paper, based on the widely available GPS trajectory big data that records the driving behaviours implicitly, we propose a multi-task learning (MTL) framework called \textsf{semi-Traj2Graph} to recognize the fine-grained driving styles in the temporal dimension accurately. The MTL framework can incorporate the learning capability of graph representation in extracting high-level and interpretable features regarding complex driving behaviours and semi-supervised in exploiting unlabelled data and reducing labelling effort. More specifically, in the graph representation learning, a multi-view graph is first built to capture a more complete view of driving behaviours from the raw GPS trajectory data, then graph convolutional neural networks (Graph-CNNs) are applied. In the semi-supervised learning, a pseudo-label labelling is adopted to make use of the unlabelled data. We evaluate the proposed framework extensively based on two taxi trajectory datasets collected from the city of Beijing and Chongqing, China, respectively. Experimental results show that \textsf{semi-Traj2Graph} outperforms compared to other baselines, achieving an overall accuracy of around 90\%. We also implement the framework on users' smartphones via the collaborative cloud-edge computation manner to demonstrate the system usability in real case

8 November 2012 in Mobile Networks and Applications
Verified
Journal Article
Closed access
PDF file
LSLin Sun
Lin Sun
DZDaqing Zhang
Daqing Zhang
CCChao Chen
Chao Chen
PCPablo Samuel Castro
Pablo Samuel Castro
SLSHIJIAN LI
SHIJIAN LI
ZWZonghui Wang
Zonghui Wang

10 March 2010 in Personal and Ubiquitous Computing
Verified
Journal Article
Closed access
PDF file
GPGang Pan
Gang Pan
JWJiahui Wu
Jiahui Wu
DZDaqing Zhang
Daqing Zhang
ZWZhaohui Wu
Zhaohui Wu
YYYingchun Yang
Yingchun Yang
SLSHIJIAN LI
SHIJIAN LI

12 September 2019 in IEEE Transactions on Fuzzy Systems
Verified
Journal Article
Closed access
SHSheng-Juan Huang
Sheng-Juan Huang
DZDa-Qing Zhang
Da-Qing Zhang
LGLiang-Dong Guo
Liang-Dong Guo
LWLi-Bing Wu
Li-Bing Wu
This paper focuses on the problems of observer based fault estimation and dynamic output feedback FTC for a class of nonlinear fuzzy systems with faults. A novel lower triangle factor based estimation observer (LTFEO) is proposed for the first time. The designed LTFEO can reduce to the traditional robust estimation observer (REO) and is superior to the adaptive estimation observer (AEO) in the relevant literature, furthermore, the designed LTFEO does not contain the output derivatives. The initial estimation accuracy is improved under the designed estimation observer. An iterative estimation algorithm based on the iterative LTFEOs is given, by which, the obtained mean sequence of state and fault estimation errors can converge to zeros (vector) and the proof is given in theoretical. Then, a new dynamic output feedback FTC is designed to stabilize the faulty system, where the output feedback gains can be determined by state feedback gains and the computational difficulty is decreased. Less conservative stability conditions for the estimation error dynamics and closed-loop system are given in terms of linear matrix inequalities (LMIs). A tunnel diode circuit system is applied to test the effectiveness and merits of the proposed methods.