复杂网络的控制和优化

机器学习

图神经网络

水下图像处理、目标识别等

入选上海市扬帆计划、上海市海外高层次人才计划

2019年9月至今   天游线路检测中心，青年副研究员

2018年7月-2019年8月    新加坡资讯通信研究院，研究员I级

2018年6月   新加坡南洋理工大学，博士

2012年6月   哈尔滨工程大学，本科

本科生课程《自动控制原理》

研究生课程《机器学习》《现代智能控制理论》

J. Ding, C. Wen , G. Li et al.  “Target Controllability in Multilayer Networks via Minimum-Cost Maximum-Flow Method", IEEE Trans. on Neural Networks and Learning Systems,  DOI: 10.1109/TNNLS.2020.2995596, 2020.

J. Ding, C. Wen, G. Li,  X. Yang and T. Hu, “Sparsity-inspired optimal topology control of complex networks", IEEE Trans. on Network Science and Engineering, DOI: 10.1109/TNSE.2019.2954893，2019.

J. Ding, C. Wen, G. Li and Z. Chen, “Key node selection in controlling complex networks via convex optimization”, IEEE Trans. on Cybernetics,  DOI: 10.1109/TCYB.2018.2888953, 2019.

G. Li*, J. Ding*, C. Wen and J. Huang, “Minimum cost control of directed networks with selectable control inputs”, IEEE Trans. on Cybernetics,   49(12)， 4431 - 4440， 2019. (*contributed equally)

G. Li*, J. Ding*, C. Wen, L. Wang and F. Guo, “Controlling directed networks with evolving topologies”, IEEE Trans. on Control of Network Systems,  6(1)， 176 - 190, 2018. (*contributed equally)

J. Ding, C. Wen and G. Li, “Key node selection in minimum cost control of complex networks”, Physica A: Statistical Mechanics and its Applications, 486, 251-261, 2017.

J. Ding, C. Wen and G. Li, “Optimal control of weighted networks based on node connection strength”, The 27th IEEE International Symposium on Industrial Electronics, 2017.

J. Ding, C. Wen, G. Li and C. Chua, “Locality sensitive batch feature extraction for high-dimensional Data”, Neurocomputing, 171, 664-672, 2016.

G. Li, J. Ding, C. Wen and J. Pei, “Optimal control of complex networks based on matrix differentiation”, Europhysics Letters, 115(6), 68005, 2016.

G. Li, C. Wen, W. Wei, Y. Xu, J. Ding, G. Zhao and L. Shi, “Trace ratio criterion for feature extraction in classification”, Mathematical Problems in Engineering, 2014,

J. Ding, G. Li, C. Wen and C. Chua, “Min-max discriminant analysis based on gradient method for feature extraction”, 13th International Conference on Control, Automation, Robotics and Vision (ICARCV), Singapore,2014, 725204, 2014.