Rong Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Rong Wang has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Fankai Sun
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China
1 shared publication - Haoxin Cui
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China
1 shared publication - Li Zhang
Tsinghua University
1 shared publication - Nan Cheng
The Sixth Medical Center of PLA General Hospital, Beijing, China
1 shared publication - Nan Zheng
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China
1 shared publication - Shuo Wang
Department of Engineering Physics, Key Laboratory of Particle and Radiation Imaging, Ministry of Education, Tsinghua University, Beijing 100084, China, China
1 shared publication
Latest Publications
- 20 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75 (00189456) , 1-14
DI-SESCINet: A Domain-Invariant Squeeze-and-Excitation SCI Network for Robotic Surgical Task Classification
Robotic surgery demands exceptional precision and stability, requiring surgeons to engage in continuous complex decision-making and coordination. This high cognitive load necessitates sustained concentration, accurate judgment, and strong psychological resilience, resulting in intricate neural activities within the surgeon’s brain. Consequently, investigating brain activity during various robotic surgical tasks is crucial for evaluating and enhancing surgical skills. However, effectively leveraging the spatial distribution of energy within the brain and the intrinsic connections between different brain regions presents significant challenges. This paper introduces a Domain-Invariant Squeeze-and-Excitation SCI Network (DI-SESCINet) designed for the classification of robotic surgical tasks. DI-SESCINet extracts and integrates spatial features derived from energy distribution and the intrinsic connections among different electroencephalogram (EEG) channels, effectively capturing the temporal patterns inherent in dynamic cognitive processes. Additionally, integrating a domain-invariant component aids in reducing sample-specific variability stemming from both individual differences and state changes, particularly in small sample sizes. Experimental results demonstrate that DI-SESCINet achieves superior classification performance, reaching 94.13%, underscoring its efficacy in enhancing the assessment of surgical skills.
- 20 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75 (00189456) , 1-14
DI-SESCINet: A Domain-Invariant Squeeze-and-Excitation SCI Network for Robotic Surgical Task Classification
Robotic surgery demands exceptional precision and stability, requiring surgeons to engage in continuous complex decision-making and coordination. This high cognitive load necessitates sustained concentration, accurate judgment, and strong psychological resilience, resulting in intricate neural activities within the surgeon’s brain. Consequently, investigating brain activity during various robotic surgical tasks is crucial for evaluating and enhancing surgical skills. However, effectively leveraging the spatial distribution of energy within the brain and the intrinsic connections between different brain regions presents significant challenges. This paper introduces a Domain-Invariant Squeeze-and-Excitation SCI Network (DI-SESCINet) designed for the classification of robotic surgical tasks. DI-SESCINet extracts and integrates spatial features derived from energy distribution and the intrinsic connections among different electroencephalogram (EEG) channels, effectively capturing the temporal patterns inherent in dynamic cognitive processes. Additionally, integrating a domain-invariant component aids in reducing sample-specific variability stemming from both individual differences and state changes, particularly in small sample sizes. Experimental results demonstrate that DI-SESCINet achieves superior classification performance, reaching 94.13%, underscoring its efficacy in enhancing the assessment of surgical skills.
- 17 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Computer Graphics and Applications
- Vol. 46 (1) , 52-65
Adaptive Cardiac Dynamics in Surgical Simulation: A Human–AI Interaction Framework for Robotic Internal Mammary Artery Harvesting
Virtual surgical simulation offers promising training for complex procedures like robotic internal mammary artery (IMA) harvesting. Building upon previous work on dynamic virtual simulation with haptic feedback, we present an adaptive human-AI interaction (HAI) framework that dynamically adjusts cardiac pulsation parameters based on surgeon behavior analysis. Our system captures surgical tool movements and performance metrics to create personalized training through dynamic difficulty adjustment, context-aware parameter selection, personalized learning paths, and real-time feedback. In a study with three cardiac surgeons across 24 sessions, our adaptive approach showed significant improvements over static simulations: 18% reduction in spatial asymmetry, 22% faster completion, and 48% fewer tissue trauma events. The system demonstrated consistent benefits across different skill levels and sustained learning progression, preventing performance plateaus seen in fixed-difficulty conditions.
- 17 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Computer Graphics and Applications
- Vol. 46 (1) , 52-65
Adaptive Cardiac Dynamics in Surgical Simulation: A Human–AI Interaction Framework for Robotic Internal Mammary Artery Harvesting
Virtual surgical simulation offers promising training for complex procedures like robotic internal mammary artery (IMA) harvesting. Building upon previous work on dynamic virtual simulation with haptic feedback, we present an adaptive human-AI interaction (HAI) framework that dynamically adjusts cardiac pulsation parameters based on surgeon behavior analysis. Our system captures surgical tool movements and performance metrics to create personalized training through dynamic difficulty adjustment, context-aware parameter selection, personalized learning paths, and real-time feedback. In a study with three cardiac surgeons across 24 sessions, our adaptive approach showed significant improvements over static simulations: 18% reduction in spatial asymmetry, 22% faster completion, and 48% fewer tissue trauma events. The system demonstrated consistent benefits across different skill levels and sustained learning progression, preventing performance plateaus seen in fixed-difficulty conditions.