Jun Fu

Jun Fu

Auto-generated profile, based on publicly available information

Jun Fu

Beijing Electronic Science and Technology Institute, Beijing 100070, P. R. China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
17 April 2024 in International Journal of Neural Systems
Verified
Journal Article
Closed access
JFJun Fu
Jun Fu
HPHong Peng
Hong Peng
BLBing Li
Bing Li
ZLZhicai Liu
Zhicai Liu
RLRikong Lugu
Rikong Lugu
Antonio Ramírez de Arellano MarreroAntonio Ramírez de Arellano Marrero
Antonio Ramírez de Arellano Marrero

20 November 2024 in Expert Systems with Applications
Verified
Journal Article
Closed access
JFJun Fu
Jun Fu
HPHong Peng
Hong Peng
BLBin Li
Bin Li
JWJun Wang
Jun Wang
ZLZhicai Liu
Zhicai Liu

28 February 2026 in International Journal of Neural Systems
Verified
Journal Article
Closed access
JFJun Fu
Jun Fu
JZJianyi Zhang
Jianyi Zhang
HPHong Peng
Hong Peng
WZWenxuan Zhang
Wenxuan Zhang
KHKaiying Han
Kaiying Han
XHXiali Hei
Xiali Hei

31 August 2026 in International Journal of Neural Systems
Verified
Journal Article
Open access
JFJun Fu
Jun Fu
HPHong Peng
Hong Peng
BLBing Li
Bing Li
ZZZiyin Zhou
Ziyin Zhou
Nonlinear spiking neural P (NSNP) systems offer a biologically inspired framework for modeling nonlinear temporal dynamics via spike consumption and generation. Existing NSNP-based recurrent architectures, such as the long short-term memory model inspired from spiking neural P systems (LSTM-SNP), primarily rely on implicit gating mechanisms and lack explicit state correction during recurrent propagation, which can lead to unstable state evolution and excessive information decay in long-term temporal modeling. To address this limitation, a compensation-balanced LSTM-SNP (CBLSTM-SNP) architecture is proposed. The model introduces a compensation-driven regulation mechanism, comprising a regulation branch and an adaptive compensation branch, to dynamically adjust hidden state evolution. From a nonlinear dynamical systems perspective, CBLSTM-SNP establishes a balanced recurrent state transition integrating memory preservation, nonlinear spike processing, and adaptive state restoration. Theoretical analysis confirms the boundedness and Lipschitz continuity of the proposed recurrent dynamics. Empirical evaluations on five benchmark time series datasets demonstrate that CBLSTM-SNP produces smoother hidden state trajectories and achieves comparable forecasting performance compared with several representative recurrent and hybrid models.

12 November 2026 in International Journal of Neural Systems
Verified
Journal Article
Closed access
JFJun Fu
Jun Fu
HPHong Peng
Hong Peng
BLBing Li
Bing Li
YLYilong Li
Yilong Li