Qunshan He (何群山)

Qunshan He's photo 


Master Student

College of Control Science and Engineering
Zhejiang University

Office: 517, No.9 Teaching Building, Yuquan Campus
Address: No.38 Zheda Road, Hangzhou, Zhejiang 310027, China

Email: hequnshan2000 [@] 163 [DOT] com
WeChat: JazzingMountain

Biography

I am now a M.Eng. student from College of Control Science and Engineering, Zhejiang University.
Prior to this, I received my bachelor's degree from Department of Communication Engineering, Jilin University. During my B.Eng. journey, I joined JRobot Laboratory and participated in RoboMaster Robotics Competition as the group head of Robotic Vision since 2019, supervised by Yubo Xuan.
I also took charge of a National College Student Innovation Training Project, served as a Research Intern in State Key Laboratory of Applied Optics of CIOMP since 2020, supervised by Dayu Li.

Currently, my research interests include

  • Graph Neural Network

  • Time Series Processing

  • Computational Imaging

Eduacation

   Zhejiang University's logo 

Zhejiang UniversityHangzhou, China

M.Eng. in Electronic InformationSept. 2022 - Mar. 2025 (expected)

State Key Laboratory of Industrial Control Technology

   Jilin University's logo 

Jilin UniversityChangchun, China

B.Eng. in Communication EngineeringAug. 2018 - Jun. 2022

GPA: 4.00/4.00, ranking: 1/334

Group Head of Robotic Vision for RoboMaster Robotic Competition in JRobot Laboratory, supervised by Yubo Xuan. Jan. 2019 - Jun. 2022

Publications

  1. BioSTGC: A Spatial-Temporal Graph Convolution Soft Sensor Framework for Bio-Intelligent Manufacturing
    Qunshan He, Wei Zeng, Hong Zhang, Yichen Song, Zijian Tian, Changdi Li, Xinggao Liu*
    The 35th Chinese Process Control Conference(CPCC) (CAA-A), 2024

  2. Human-in-the-loop: Human involvement in enhancing medical inquiry performance in large language models
    Linpin Shu#, Qunshan He#, Bing Yan#, Di Wu, Menglin Wang, Chengshuo Wang, Luo Zhang*
    # Contributed Equally, Allergy (CiteScore Q1, IF=12.6), 2023

  3. Graph-based Multiscale Stacked Autoencoder for Biopharmaceutical Processes Soft Sensor
    Qunshan He#, Zhichao Chen, Yichen Song, Changdi Li, Xinggao Liu*
    Manuscript Submitted to IEEE Transaction on Instrumentation and Measurement (CiteScore Q1, IF=5.6)

  4. Causality Enhanced Global-Local Graph Neural Network for Bioprocess Factor Forecasting
    Ziyue Sun, Yinlong Li, Qunshan He, HuXu, Wenhai Wang, and Xinggao Liu*
    IEEE Transactions on Industrial Informatics (CiteScore Q1, IF=11.7), 2024

  5. HMT: Hybrid mechanistic Transformer for bio-fabrication prediction under complex environmental conditions
    Yichen Song, Hu Xu, Changdi Li, Qunshan He, Zijian Tian, Xinggao Liu*
    Expert Systems With Applications (CiteScore Q1, IF=7.5), 2024

  6. Fast forest fire detection and segmentation application for UAV-assisted mobile edge computing system
    Changdi Li, Guangye Li, Yichen Song, Qunshan He, Zijian Tian, Hu Xu and Xinggao Liu*
    IEEE Internet of Things Journal (CiteScore Q1, IF=8.2), 2023

  7. Hidformer: Hierarchical dual-tower transformer using multi-scale mergence for long-term time series forecasting
    Zhaoran Liu, Yizhi Cao, Hu Xu, Yuxin Huang, Qunshan He, Xinjie Chen, Xiaoyu Tang, Xinggao Liu*
    Expert Systems With Applications (CiteScore Q1, IF=7.5), 2024

Project Experience

hpp Robot Automatic Recognition and Aiming Algorithm (JLURoboVision)

    In the RoboMaster Robotics Competition, participants need to control their robots to attack enemy’s robots by launching projectiles. And the only effective attacks are made by striking the Armor module, which is highly characterized by two bright light-bars (red or blue). We come up with a machine vision method to recognize enemy’s armor and aim at the targeted one to realize robot automatic attack.
    First we extract specific color area to construct light-bar instance, then we use spatial feature to construct armor instance, next we crop the armor area as the input of a SVM model to classify the corresponding robot. Finally we calculate the yaw and pitch angles based on perspective transformation principle to control the robot aiming at the targeted robot.
    This algorithm has been running in our robots and shows nice performance with high accuracy (95%) and speed (200~300fps). And it has also been open sourced in GitHub and Gitee.

hpp Computational Imaging Microscope

    Standard microscope is limited by the Numerical Aperture (NA) of physical lenses, if we want to see a feature with a higher resolution, we must switch to a different microscope objective, with a reduced field of view.
    However, by applying LED matrix as Illumination, combined with computational optics, we can boost the resolving power of standard microscopes by more than an order of magnitude.
    Here I develop a computational optical microscope based on the concepts of Aperture Synthesis and Phase Retrieval, realizing wide-field and high-resolution quantitative phase imaging, for which I also proposed a Dynamic Sampling Denoise Algorithm based on LMS.
    This microscope is currently applied to optical lens inspection to present tiny and transparent defects of optical lens.

Professional Experiences

Massachusetts Institute of Technology's logo 

Massachusetts Institute of TechnologyMassachusetts, United States

Winter Camp Participatant of Deep Learning for Autonomous Driving Course(Online) with A level certificate in CSAIL. Feb 2021 - Mar 2021

   Univerisity of Chinese Academy of Sciences's logo 

University of Chinese Academy of ScienceChangchun, China

Research Intern at State Key Laboratory of Applied Optics, CIOMP, developing Computational Imaging Microscope, supervised by Dayu Li. Oct 2020 - Jun. 2022

   Sungkyunkwan University's logso 

Sungkyunkwan UniversitySeoul, South Korea

Academic Visitor at the Robotics Innovatory Laboratory, delivering presentation "Robots Enriching my Youth" Nov. 3 2019

 IEEE International Conference on Computer Vision's logo 

IEEE International Conference on Computer VisionSeoul, South Korea

ICCV2019 Student Participants and group member of JLU-Thunder for Large-Scale Video Object Segmentation Challenge. Oct. 27 - Nov. 2 2019

   Univerisity of Goettingen's logo 

University of GoettingenGoettingen, Germany

Visiting Student at the Computer Networks Group, supervised by Prof. Xiaoming Fu (member of Academia Europaea). Jul. 2016 - Sep. 2016

Selected Awards

  • First Prize of RoboMaster 2020 Robotics Competition (Robotics Vision)2020
  • Open Source Award of RoboMaster 2020 Robotics Competition2020
  • Silver Award of the 7th China International College Student "Internet+" Innovation and Entrepreneurship Competition (Project leader)2021
  • Elite Students on Innovation and Entrepreneurship of Jilin University (Only 2 students per year)2022
  • QiAnXin Scholarship2022
  • Excellent Completion of the National College Student Innovation Training Project (Project leader)2022
  • Excellent Completion of the Science and Technology Innovation Plan in University Chinese Academy of Sciences (UCAS) (Project leader)2022
  • Bronze Award of the 8th China International College Student "Internet+" Innovation and Entrepreneurship Competition2023
  • Special Prize in Jilin University's "Challenge Cup" Academic Competition2021
  • Gold Award of the 7th Jilin Province "Internet+" Innovation and Entrepreneurship Competition2021
  • Honorable Mention of Interdisciplinary Contest in Modeling (MCM) 2021
  • First Prize of Jilin Province in Contemporary Undergraduate Mathematical Contest in Modeling(CUMCM) 2020
  • First Prize Scholarship, Jilin University 2019 - 2022
  • Outstanding Acadamic Scholarship, Jilin Univeristy 2019 - 2022
  • Outstanding Student, Jilin University 2019 - 2022