Bin Guo

Prof. Bin Guo

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
7 November 2025 in Ocean Engineering
Verified
Journal Article
Closed access
JLJianchun Liao
Jianchun Liao
BGBin Guo
Bin Guo
YZYufeng Zhang
Yufeng Zhang
XMXiangai Miao
Xiangai Miao
TZTing Zheng
Ting Zheng

9 September 2025 in Sensors
Verified
Journal Article
Open access
PDF file
YXYicheng Xie
Yicheng Xie
BGBin Guo
Bin Guo
The cognitive load of drivers directly affects the safety and practicality of advanced driving assistant systems, especially in autonomous driving scenarios where drivers need to quickly take control of the vehicle after performing non-driving-related tasks (NDRTs). However, existing driver cognitive load detection methods have shortcomings such as the inability to deploy invasive detection equipment inside vehicles and limitations to eye movement detection, which restrict their practical application. To achieve more efficient and practical cognitive load detection, this study proposes a multi-task non-contact cognitive load and physiological state estimation model based on RGB video, named CogMamba. The model utilizes multimodal features extracted from facial video and introduces the Mamba architecture to efficiently capture local and global temporal dependencies, thereby further jointly estimating cognitive load, heart rate (HR), and respiratory rate (RR). Experimental results demonstrate that CogMamba exhibits superior performance on two public datasets and shows excellent robustness under the cross-dataset generalization test. This study provides insights for non-contact driver state monitoring in real-world driving scenarios.

5 December 2025 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
BGBin Guo
Bin Guo
JFJiawei Feng
Jiawei Feng
YZYuzhong Zhong
Yuzhong Zhong
YZYuqi Zhu
Yuqi Zhu
Songyi DianSongyi Dian
Songyi Dian
For physical human–robot interaction (pHRI), this article proposes a variable admittance control method that integrates both direct human intent and indirect human intent, aimed at enhancing interactive experiences. This method employs a sigmoid function to analyze interaction force signals, enabling the recognition of direct intent. This facilitates a smooth transition between preferences for rapid motion and precise motion. For indirect intent, it draws inspiration from the speed–curvature–torsion pattern reflecting human motion laws in 3-D space. An expected force model is constructed to characterize the long-term motion objectives of indirect intent. Based on a directional admittance guidance mechanism, the estimated indirect intent enables the robot to collaborate with the operator and provide motion guidance. Experimental results demonstrate that, compared to fixed admittance control and other variable admittance control methods, the proposed method achieves significant improvements in 3-D spatial path tracking regarding accuracy, smoothness, effort reduction, and task time.

4 December 2025 in Journal of the Franklin Institute
Verified
Journal Article
Closed access
YZYuqi Zhu
Yuqi Zhu
Xingxing YouXingxing You
Xingxing You
HQHu Qiang
Hu Qiang
QXQuan Xiao
Quan Xiao
ZLZhongping Li
Zhongping Li
Songyi DianSongyi Dian
Songyi Dian

26 March 2026 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
YZYuzhong Zhong
Yuzhong Zhong
MLMing Lei
Ming Lei
XZXuke Zhong
Xuke Zhong
BGBin Guo
Bin Guo
Songyi DianSongyi Dian
Songyi Dian
Reconstruction-based anomaly detection is appealing for industrial inspection because it reconstructs anomaly-free references and produces interpretable pixel-level residual maps. However, in multiclass settings, it often suffers from, first, identity mapping, where abnormal regions are overreconstructed and residuals vanish, and second, cross-category feature entanglement, which introduces artifacts and weakens localization. Residual scoring is further biased because it mixes true defect discrepancies with model-induced reconstruction errors, causing false alarms and confusing explanations. We propose a semantically guided counterfactual model (SGCAD) for multiclass anomaly detection and localization. SGCAD applies a masking intervention to a candidate region, reconstructs the intervened input, and contrasts factual and intervened residuals to estimate reconstruction bias, yielding a debiased anomaly map by treating consistent differences as anomalies. To stabilize reconstruction, we introduce a dual-branch bottleneck with latent constraints to mitigate identity mapping while preserving normal details, and a hierarchical adaptive prompt to reduce cross-category confusion during decoding without class priors. Extensive experiments on four public benchmarks demonstrate that while SGCAD maintains competitive image-level detection performance, it achieves superior state-of-the-art results in pixel-level localization. By effectively mitigating bias-induced false positives, SGCAD offers a more precise and reliable solution for practical industrial inspection.

19 February 2026 in Communications in Nonlinear Science and Numerical Simulation
Verified
Journal Article
Closed access
JLJianchun Liao
Jianchun Liao
BGBin Guo
Bin Guo
YZYuqi Zhu
Yuqi Zhu
CLChangming Li
Changming Li
YLYaning Long
Yaning Long
SDSongyi Dian
Songyi Dian