Xi Chen

Prof. Dr. Xi Chen

College of Control Science and Engineering, Zhejiang University, Zheda Road 38, Hangzhou 310027, China

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

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

Representative Publications

View All Publications
20 March 2023 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
ZLZhengxuan Ling
Zhengxuan Ling
YZYu Zhang
Yu Zhang
Xi ChenXi Chen
Xi Chen
The rapid development of logistics and navigation has led to increasing demand for solving route optimization problems in real-time. The traveling salesman problem (TSP) tends to require fast and reliable online solutions, which may not be met by traditional iterative optimization algorithms. In this work, a real-time solution policy is proposed for TSP. The idea is to build a mapping between city information and optimal solutions using deep neural networks. Therefore, when given a new set of city coordinates, the optimal route can be directly and quickly calculated without iteration. Considering the recent advancement in computer vision with deep convolutional neural networks (DCNNs), an image representation is proposed to convert TSP to a computer vision problem. A problem decomposition method is introduced to reduce the mapping complexity. Taking advantage of the powerful fitting capabilities of DCNN, a deep reinforcement learning method is designed without any labeling requirement. The proposed method is superior for real-time applications compared with other algorithms.

11 February 2020 in IEEE Transactions on Systems, Man, and Cybernetics: Systems
Verified
Journal Article
Closed access
ZLZhengxuan Ling
Zhengxuan Ling
XTXinyu Tao
Xinyu Tao
YZYu Zhang
Yu Zhang
Xi ChenXi Chen
Xi Chen
In the new wave of artificial intelligence, deep learning is impacting various industries. As a closely related area, optimization algorithms greatly contribute to the development of deep learning. But the reverse applications are still insufficient. Is there any efficient way to solve certain optimization problem through deep learning? The key is to convert the optimization to a representation suitable for deep learning. In this article, a traveling salesman problem (TSP) is studied. Considering that deep learning is good at image processing, an image representation method is proposed to transfer a TSP to an image. Based on samples of a ten city TSP, a fully convolutional network (FCN) is used to learn the mapping from a feasible region to an optimal solution. The training process is analyzed and interpreted through stages. A visualization method is presented to show how an FCN can understand the training task of a TSP. Once the training is completed, no significant effort is required to solve a new TSP and the prediction is obtained on the scale of milliseconds. The results show good performance in finding the global optimal solution. Moreover, the developed FCN model has been demonstrated on TSP’s with different city numbers, proving excellent generalization performance.

23 August 2017 in Journal of Global Optimization
Verified
Journal Article
Closed access
PDF file
KZKai Zhou
Kai Zhou
MKMustafa R. Kılınç
Mustafa R. Kılınç
Xi ChenXi Chen
Xi Chen
NSNikolaos Sahinidis
Nikolaos Sahinidis


29 July 2017 in Clinical and Experimental Pharmacology and Physiology
Verified
Journal Article
Open access
PDF file
YLYunrong Lu
Yunrong Lu
YZYan Zhang
Yan Zhang
YRYing‐Bo Rao
Ying‐Bo Rao
Xi ChenXi Chen
Xi Chen
HLHan‐Fen Lou
Han‐Fen Lou
LHLi‐Wei Hu
Li‐Wei Hu
Summary: There is strong evidence of roles of the hypothalamus‐pituitary‐adrenal axis and nitric oxide (NO) synthase‐NO system in depression, but the relationship between them is unknown. The aim of this study, therefore, was to elucidate whether there is any correlation between NO and corticotropin‐releasing hormone (CRH) in major depressive disorder (MDD) patients. In 16 outpatients with MDD and 18 healthy controls, the plasma amino acids citrulline (Cit) and arginine (Arg) were determined by high‐performance liquid chromatography, and CRH levels was measured by radioimmunoassay. The Cit/Arg ratio was calculated as an index of NO synthesis. Correlations between NO and CRH were examined with the Spearman test. Before treatment, no significant correlation was observed between the plasma NO level and CRH levels in MDD patients. The plasma NO levels were significantly higher in MDD patients. A significant correlation was found between NO levels and Hamilton Depression Rating Scale (HAMD) scores in MDD patients. The plasma CRH levels were significantly higher in MDD patients than in controls. After monotherapy for 2 months, the NO levels had dramatically declined but were also higher than those in the controls. This study is the first report of the absence of a significant correlation between plasma NO and CRH levels, although both levels are elevated in MDD patients. Furthermore, the strong links between the plasma NO levels and the HAMD scores, as well as the increased NO reduction after remission, suggest that NO plays a key role in depression and may be an indicator of therapeutic success.

30 November 2022 in Industrial & Engineering Chemistry Research
Verified
Journal Article
Closed access
CCCheng Chang
Cheng Chang
LFLian-Fang Feng
Lian-Fang Feng
XGXue-Ping Gu
Xue-Ping Gu
CZCai-Liang Zhang
Cai-Liang Zhang
LDLian-Kui Dai
Lian-Kui Dai
GHGuo-Hua Hu
Guo-Hua Hu