avatar

Yu Hang

Phd in BCI & SNN field.

Hang Yu is a Ph.D. student at the Pervasive & Cyborg Intelligence Lab, Zhejiang University. His research interests include neural computing, artificial intelligence and brain-computer interface.

During my doctoral studies, my research focused on spatiotemporal signal processing and neural network design under the supervision of Professor Gang Pan.
My primary work involved studying SSVEP (Steady-State Visual Evoked Potential) recognition algorithms and systems in brain-computer interfaces, as well as investigating online spike sorting algorithms based on biomimetic chips in neuromorphic computing.

Education Experience

  • Zhejiang University
    Doctor of Computer Science and Technology
    Sep. 2018 – Now

  • Zhejiang University of Technology
    Bachelor of Computer Science and Technology
    Sep. 2014 – Jun. 2018

Publications

Article

[1] Yu, H., Qi, Y., & Pan, G. (2023). NeuSort: An automatic adaptive spike sorting approach with neuromorphic models. Journal of Neural Engineering, 20(5), 056006. https://doi.org/10.1088/1741-2552/acf61d. An unsupervised SNN spike sorting automation algorithm.
[2] Wang, H., Qi, Y., Yu, H., Wang, Y., Liu, C., Hu, G., & Pan, G. (2022). RCIT: An RSVP-Based Concealed Information Test Framework Using EEG Signals. IEEE Transactions on Cognitive and Developmental Systems, 14(2), 541–551. https://doi.org/10.1109/TCDS.2021.3053455. EEG lie detection.
[3] Yu, H., Qi, Y., Wang, H., & Pan, G. (2021). Secure typing via BCI system with encrypted feedback. 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 4969–4973. https://doi.org/10.1109/EMBC46164.2021.9630645. SSVEP-BCI encrypted interaction system.
[4] Pan, G., Li, J.-J., Qi, Y., Yu, H., Zhu, J.-M., Zheng, X.-X., Wang, Y.-M., & Zhang, S.-M. (2018). Rapid Decoding of Hand Gestures in Electrocorticography Using Recurrent Neural Networks. Frontiers in Neuroscience, 12. https://www.frontiersin.org/articles/10.3389/fnins.2018.00555. LSTM decoding of ECoG cortex gesture signals.
[5] Xu, Q., Qi, Y., Yu, H., Shen, J., Tang, H., & Pan, G. (2018). CSNN: An Augmented Spiking based Framework with Perceptron-Inception. Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, 1646–1652. https://doi.org/10.24963/ijcai.2018/228. A CNN-SNN hybrid network.
[6] Qi, Y., Shen, J., Wang, Y., Tang, H., Yu, H., Wu, Z., & Pan, G. (2018). Jointly Learning Network Connections and Link Weights in Spiking Neural Networks. https://doi.org/10.24963/ijcai.2018/221. SNN sparse pruning strategy.
[7] Ultra-low-cost fully automatic spike sorter via scale-adaptive neuromorphic model. SCIS. 2025 (under review). A scale-adaptive method for spike sorting.

Patent:

[1] ZL202210849758.7 - An online neuron classification method based on neuromorphic computing.

Projects

  1. Brain-like Computing Project with Zhejiang University & ChiNext Lab Apr. 2020 – Oct. 2020
  • Developed a brain-computer interface (BCI) typing system based on Steady-State Visual Evoked Potentials (SSVEP).
  • Designed the visual stimulation panel, implemented core recognition algorithms, and built the closed-loop system.
  • Successfully demonstrated the “mind-typing” functionality, enabling users to input text using neural signals.
  1. Non-invasive BCI Applications with Zhejiang University & iFLYTEK Jul. 2019 – Aug. 2019
  • Conducted research on deception detection using non-invasive brain-computer interfaces.
  • Participated in designing key closed-loop paradigms and data acquisition systems.
  • Collected over 50 hours of EEG data, providing a solid foundation for further studies on BCI-based lie detection.
  1. Internship at Nokia Shanghai Bell Lab Jul. 2017
  • Participated in internal IM (Instant Messaging) research focusing on enterprise communication needs.
  • Investigated employee usage patterns and collected requirements for an H5-based instant messaging application.
  • Contributed to the design reference of the final product by summarizing user feedback and functional expectations.