Weiguo Sheng
Papers
2
Total Citations
47
H-Index
2
About
Weiguo Sheng is a leading researcher in computational intelligence, with key contributions spanning evolutionary optimization, multimodal problem-solving, and medical image analysis. His most cited work, "Adaptive memetic differential evolution with niching competition and supporting archive strategies for multimodal optimization" (2021, 41 citations), introduces a groundbreaking algorithm that combines memetic computation with adaptive niching techniques to locate multiple optimal solutions simultaneously—a critical capability for real-world engineering design problems. This work has become a foundational reference in the field of multimodal optimization. More recently, Sheng has applied his expertise to pressing challenges in medical robotics. His 2023 paper on "Dense Depth Completion Based on Multi-Scale Confidence and Self-Attention Mechanism for Intestinal Endoscopy" (6 citations) addresses a critical bottleneck in minimally invasive surgery: the sparse, incomplete depth data from stereo and ToF endoscopes. By developing a deep learning framework that fuses multi-scale confidence maps with self-attention mechanisms, Sheng enables dense, accurate, and real-time depth estimation—vital for surgeons navigating the complex intestinal environment during one-way endoscopy. This work bridges the gap between evolutionary computation and practical medical imaging, demonstrating his ability to translate algorithmic innovation into life-saving clinical tools.
Research Focus
Key Achievements
Top Papers
- 1
- 2