Jun Liu

Prof. Dr. Jun Liu

orcid

Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

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

Representative Publications

View All Publications
1 October 2019 in ISA Transactions
Verified
Journal Article
Closed access
Jun LiuJun Liu
Jun Liu
PLPing Li
Ping Li
WCWei Chen
Wei Chen
KQKaiyu Qin
Kaiyu Qin
LQLei Qi
Lei Qi

1 December 2018 in Neurocomputing
Verified
Journal Article
Closed access
Jun LiuJun Liu
Jun Liu
KQKaiyu Qin
Kaiyu Qin
PLPing Li
Ping Li
WCWei Chen
Wei Chen

3 August 2018 in IET Control Theory & Applications
Verified
Journal Article
Open access
PDF file
MSMengji Shi
Mengji Shi
KQKaiyu Qin
Kaiyu Qin
Jun LiuJun Liu
Jun Liu
The study solves multi‐agent cooperative control problems of covering irregularly‐shaped unknown areas. A sweep coverage motion scheme is proposed: the agents are arranged in a row across the area and sweep through. The formation is flexible thus the agents can be scattered across the widest part and can queue up to pass through the narrowest portion. This allows the agents to cover the region by collectively passing through it only once, which may help to improve the survivability of reconnaissance vehicles. A distributed second‐order control law is designed by modelling the agents as point masses in planar space. The approach is inspired by the motion of a string of balls connected by springs, thus virtual elastic force and potential field are applied to the agents, which introduces non‐linearity to the system. Complete coverage as well as collision avoidance among agents and borders are guaranteed by parameter constraints that provided and validated via theoretical deduction and numerical simulations. Compared with the existing unknown‐area coverage methods by randomly exploring the area, the proposed one yields more regular motion paths. Limitations of the work and future research directions are finally concluded.

8 November 2019 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
NZNan Zhou
Nan Zhou
BCBadong Chen
Badong Chen
ADAnd Yuanhua Du
And Yuanhua Du
TJTao Jiang
Tao Jiang
Jun LiuJun Liu
Jun Liu
YXYangyang Xu
Yangyang Xu
Concept factorization (CF) has shown its great advantage for both clustering and data representation and is particularly useful for image representation. Compared with nonnegative matrix factorization (NMF), CF can be applied to data containing negative values. However, the performance of CF method and its extensions will degenerate a lot due to the negative effects of outliers, and CF is an unsupervised method that cannot incorporate label information. In this article, we propose a novel CF method, with a novel model built based on the maximum correntropy criterion (MCC). In order to capture the local geometry information of data, our method integrates the robust adaptive embedding and CF into a unified framework. The label information is utilized in the adaptive learning process. Furthermore, an iterative strategy based on the accelerated block coordinate update is proposed. The convergence property of the proposed method is analyzed to ensure that the algorithm converges to a reliable solution. The experimental results on four real-world image data sets show that the new method can almost always filter out the negative effects of the outliers and outperform several state-of-the-art image representation methods.

15 February 2019 in International Journal of Robust and Nonlinear Control
Verified
Journal Article
Closed access
PDF file
MSMengji Shi
Mengji Shi
KQKaiyu Qin
Kaiyu Qin
JLJie Liang
Jie Liang
Jun LiuJun Liu
Jun Liu

1 July 2019 in Journal of the Franklin Institute
Verified
Journal Article
Closed access
Jun LiuJun Liu
Jun Liu
PLPing Li
Ping Li
LQLei Qi
Lei Qi
WCWei Chen
Wei Chen
KQKaiyu Qin
Kaiyu Qin