Fan Zhou

Prof. Dr. Fan Zhou


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
1 January 2025
Verified
Conference Paper
Open access
PDF file
KLKai Liu
Kai Liu
ZCZe Chen
Ze Chen
ZFZhihang Fu
Zhihang Fu
WZWei Zhang
Wei Zhang
RJRongxin Jiang
Rongxin Jiang
JYJieping Ye
Jieping Ye
Kai Liu, Ze Chen, Zhihang Fu, Wei Zhang, Rongxin Jiang, Fan Zhou, Yaowu Chen, Yue Wu, Jieping Ye. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

20 February 2025 in Brain Sciences
Verified
Journal Article
Open access
PDF file
JZJiaqi Zheng
Jiaqi Zheng
YLYuan Li
Yuan Li
LCLiangliang Chen
Liangliang Chen
FWFei Wang
Fei Wang
BGBoxuan Gu
Boxuan Gu
FZFan Zhou
Fan Zhou
Background: In brain–computer interfaces, neural decoding plays a central role in translating neural signals into meaningful physical actions. These signals are transmitted to processors for decoding via wired or wireless channels; however, they are often subject to data loss, commonly referred to as “packet loss”. Despite their importance, the effects of different types and degrees of packet loss on neural decoding have not yet been comprehensively studied. Understanding these effects is critical for advancing neural signal processing. Methods: This study addresses this gap by constructing four distinct packet loss models that simulate the congestion, distribution, and burst loss scenarios. Using macaque superior arm movement decoding experiments, we analyzed the effects of the aforementioned packet loss types on decoding performance across six parameters (position, velocity, and acceleration in the x and y dimensions). The performance was assessed using the R2 metric and statistical comparisons across different loss scenarios. Results: Our results indicate that sudden, consecutive packet loss significantly degraded decoding performance. For the same packet loss probability, burst loss led to the largest decrease in the R2 value. Notably, when the packet loss rate reached 10%, the decoding performance for acceleration dropped to 73% of the original R2 value. On the other hand, when the packet loss rate was within 2%, the neural signal decoding results across all packet loss models remained largely unaffected. However, as the packet loss rate increased, the impact became more pronounced. These findings highlight the varying degrees to which different packet loss models affect decoding outcomes. Conclusions: This study quantitatively evaluated the relationship between packet loss and neural decoding outcomes, highlighting the differential effects of loss patterns on decoding parameters, and it proposed some methods and devices to solve the problem of packet loss. These findings offer valuable insights for the development of resilient neural signal acquisition and processing systems capable of mitigating the impact of packet loss.

24 September 2024 in Preprints.org
Verified
Preprint
Open access
PDF file
JZJiaqi Zheng
Jiaqi Zheng
YLYuan Li
Yuan Li
LCLiangliang Chen
Liangliang Chen
FWFei Wang
Fei Wang
BGBoxuan Gu
Boxuan Gu
FZFan Zhou
Fan Zhou
Background: In the field of brain-computer interfaces, neural decoding plays a crucial role in translating neural signals into meaningful physical actions. These signals are transmitted to processors for decoding via wired or wireless channels, often encountering data loss, commonly referred to as "packet loss." Despite its importance, the impact of different types and degrees of packet loss on neural decoding has yet to be comprehensively studied. Understanding this impact is critical for advancing neural signal processing and data filtering. Methods: This paper addresses this gap by constructing four distinct packet loss models, simulating congestion packet loss, distributed packet loss, and burst packet loss scenarios. Using macaque superior arm-movement decoding experiments, we evaluate the effects of these packet loss types on decoding performance. Results: Our findings reveal that continuous burst packet loss significantly degrades decoding performance at the same packet loss probability, and decoding parameters that are sensitive to data continuity are more heavily impacted by packet loss. Conclusions: This study provides an analysis of the relationship between packet loss and neural decoding results, offering valuable insights for future strategies aimed at preventing and handling packet loss in neural signal acquisition.

11 August 2026 in Electronics
Verified
Journal Article
Open access
PDF file
HCHaoze Chen
Haoze Chen
HWHongyu Wang
Hongyu Wang
XGXiang Gao
Xiang Gao
FZFan Zhou
Fan Zhou
Scalp electroencephalography (EEG) could support low-burden monitoring of Parkinson’s disease (PD), but participant leakage, electrode count, and dataset shift can overstate performance. We tested whether a Gumbel selector could reduce eight candidate inputs to four without using outer test data, then retrained every setting with the same backend, which fused a bidirectional long short-term memory multiple instance learning (LSTM-MIL) temporal branch with a participant-level spectral random forest. OpenNeuro ds004584 included 144 participants (97 PD and 47 controls) and 7000 four-second epochs evaluated by five-fold participant-wise cross-validation across five seeds. Among the four primary fused input settings, Full8 had the highest mean balanced accuracy (BA), area under the receiver operating characteristic curve (AUC), and F1 score (0.6698 ± 0.0337, 0.7349 ± 0.0110, and 0.7431 ± 0.0166), while Learned4 achieved BA 0.6596 ± 0.0502 compared with 0.6338 ± 0.0450 for Fixed4 and 0.6367 ± 0.0202 for Random4; exact paired tests found no clear ranking. In event-defined eye-open ds003490 (25 PD-OFF and 25 controls), a separate eight-input benchmark trained within the cohort under Fixed19, using LR/ET spectral models and fixed fusion and decision rules, had the highest observed BA of 0.5760 (95% CI, 0.4520–0.6960). Under Fixed19, direct application of the frozen Learned4 source models yielded BA 0.5592 (95% CI, 0.5184–0.6024) and AUC 0.6417 (0.5460–0.7355). Learned4 produced 18 input sets across 25 combinations of fold and seed, and every paired transfer contrast with the other settings included zero. Taken together, Learned4 achieved a source cohort mean BA 0.0102 below Full8 and showed modest discrimination when the frozen source models were transferred under Fixed19, without a clear paired advantage over the controls. Because both datasets used 16-channel average referencing, their quality control procedures differed, and the selected subsets were unstable; acquisition-compatible validation with a predefined montage is needed before sparse model inputs can inform practical electrode reduction.