Yuan, Ye (袁野)
 |
Lecturer |
About me
I received the B.S. degree (majoring in automation) from Chongqing University in 2015, and the doctorate degree (majoring in control science and engineering) from Shanghai Jiao Tong University in 2020. From 2019 to 2020, I studied at the Queensland Brain Institute in Australia. From September 2020 to August 2022, I worked as a postdoctoral researcher at the School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University. Since August 2022, I have been working in the Institute of Machine Intelligence at the University of Shanghai for Science and Technology. My main research interests include: (1) Brain-inspired computing, i.e., brain-inspired artificial intelligence, applied in the field of computer vision to solve robot vision tasks in complex environments, such as 2D machine vision, 3D stereo vision, 6D pose estimation , multi-source fusion SLAM, and so on; (2) Computational neuroscience, i.e., data-driven biological neural network modeling, in conjunction with the Queensland Brain Institute for image processing, relationship prediction and network modeling based on neurophysiological data. Our team currently consists of two teachers (Dr. Liu Na and myself) and more than ten master's and doctorate students working on vision-related research with humanoid robots as a research platform.
Research
My research interests include:
Brain-inspired computing, i.e., brain-inspired artificial intelligence
Computational neuroscience, i.e., data-driven biological neural network modeling
Current work
Expression imitation of humanoid robot based on facial keypoint detection
This work endows humanoid robots with facial expressions, enabling them to interact emotionally with humans through facial expressions. We have initially achieved that the humanoid robot imitates human facial expressions, and will continue to optimize the algorithm to make the expression imitation smoother and more realistic. Computer vision algorithms such as face tracking and keypoint detection are applied in this work. Therefore, we welcome students who are interested in artificial intelligence, computer vision, deep learning, robotics and other knowledge to join us.
Action imitation of humanoid robot based on body keypoint detection
This work endows humanoid robots with posture action, enabling them to interact emotionally with humans through posture action. We have initially achieved that the humanoid robot imitates human arm action, and will continue to optimize the algorithm to make the action imitation smoother and more realistic. Computer vision algorithms such as human tracking and keypoint detection are applied in this work. Therefore, we welcome students who are interested in artificial intelligence, computer vision, deep learning, robotics and other knowledge to join us.
Vision tasks for home/health care robots (face recognition, behavior detection, etc.)
Relationship between neural activity and motor behavior in Caenorhabditis elegans
Recent publications
Yuan Y, Huo H, Fang T. Effects of metabolic energy on synaptic transmission and dendritic integration in pyramidal neurons[J]. Frontiers in computational neuroscience, 2018, 12: 79.
Yuan Y, Huo H, Zhao P, et al. Constraints of metabolic energy on the number of synaptic connections of neurons and the density of neuronal networks[J]. Frontiers in computational neuroscience, 2018, 12: 91.
Yuan Y, Liu J, Zhao P, et al. Structural insights into the dynamic evolution of neuronal networks as synaptic density decreases[J]. Frontiers in Neuroscience, 2019, 13: 892.
Yuan Y, Liu J, Zhao P, et al. A graph network model for neural connection prediction and connection strength estimation[J]. Journal of Neural Engineering, 2022, 19(3): 036001.
Yuan Y, Liu J, Zhao P, et al. Spike signal transmission between modules and the predictability of spike activity in modular neuronal networks[J]. Journal of Theoretical Biology, 2021, 526: 110811.
Yuan Y, Xin K, Liu J, et al. A GNN-based model for capturing spatio-temporal changes in locomotion behaviors of aging C. elegans[J]. Computers in Biology and Medicine, 2023: 106694.
Liu N, Mou H, Tang J, Yuan Y*, et al. Fully Connected Hashing Neural Networks for Indexing Large-Scale Remote Sensing Images[J]. Mathematics, 2022, 10(24): 4716.
Note: * indicates the corresponding author.
Full list of publications in Google Scholar.
Academic service
Reviewer
Frontiers in Neuroscience
Projects
Research on Neural Connection Relationship Mining and Connection Strength Measuring Method Based on Graph Network(62206175), 01.2023-Present
Proposes a graph network model and corresponding learning algorithm that can mine the neural connection relationship and measure the neural connection strength.
Investigate the neural connection strength and its changing law.
Analyze the relationship between the neural connection strength and the signal transmission of neural circuits.
Education
D.Eng., Pattern Recognition and Intelligent Systems, Shanghai Jiao Tong University, 09.2020
Main Courses: Machine Learning, Design of Neural Networks, Digital Image Processing, Time Series Analysis, Pattern Recognition.
B.E., Automation, Chongqing University, 06.2015
Main Courses: C Programming, Embedded Systems, Computer Network and Communication, Computer Control System.
Competitions and awards
National Scholarship, Shanghai Jiao Tong University, 12.2019
National Encouragement Scholarship, Chongqing University, 10.2014
National Scholarship, Chongqing University, 10.2012
Activities
Teaching Assistant, University of Shanghai for Science and Technology, 09.2022-present
Listen to lectures in class, assist teachers in managing students, and improve teaching skills.
Work experience
Lecturer, Institute of Machine Intelligence, University of Shanghai for Science and Technology, 08.2022-Present
Design brain-inspired artificial intelligence models
Realize the expression and action imitation of humanoid robot
Publish papers and apply for relevant patents for the corporation
Give lessons on artificial intelligence to the students
Postdoctor, School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, 09.2020-08.2022
Proposes a graph network model and corresponding learning algorithm that can mine the neural connection relationship and measure the neural connection strength.
Investigate the neural connection strength and its changing law.
Analyze the relationship between the neural connection strength and the signal transmission of neural circuits.