Shenglin Geng
Papers
2
Total Citations
9
H-Index
2
About
Shenglin Geng is a researcher at the forefront of intelligent robotics and machine learning, with a focused expertise in deep learning architectures and hybrid classification systems for robotic perception. Geng’s most impactful work centers on developing advanced neural network models that enable robots to intelligently recognize and interpret their environments without relying on subjective human analysis. Their seminal 2021 paper, "Deep Convolution and Gated Recurrent Unit Network for Robot Perceptual Intelligent Recognition," which has garnered 7 citations, introduces a novel fusion of Convolutional Neural Networks (CNNs) and Gated Recurrent Units (GRUs) to enhance pattern recognition accuracy in dynamic settings. In a complementary 2021 study on "Application of Decision Tree Integrated Hybrid Classifier in Feature-Fused Robot Big Data," Geng leverages the LightGBM framework—a high-performance gradient boosting tool—to achieve robust terrain classification for mobile robots. By integrating decision tree algorithms with feature fusion techniques, this work addresses critical challenges in real-time robotic navigation and data-driven decision-making. Though early in their career, Geng’s contributions are already shaping how robots perceive and interact with complex environments, bridging the gap between theoretical deep learning and practical autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2