Zhicheng Wu

Beijing Forestry University, Quanzhou Normal University

Papers

Total Citations

H-Index

About

Zhicheng Wu’s research bridges artificial intelligence and robotics, with a focus on sequence modeling and autonomous inspection systems. His most cited work, “Long Short-Term Memory Projection Recurrent Neural Network Architectures for Piano’s Continuous Note Recognition” (2017, 31 citations), advances LSTM variants for time-series tasks, demonstrating how LSTMP networks optimize both speed and accuracy in musical note recognition—a contribution with implications for speech and image processing. Wu further extends deep learning to robotics in “Obstacle Detection and Identification Algorithm for Transmission Line Inspection Robot Based on H-CNN” (2021), where he proposes a hybrid convolutional neural network (H-CNN) that enables robots to reliably detect and classify obstacles along power lines. This work addresses a critical need for long-duration, high-reliability inspection in energy infrastructure. Though early in his career, Wu’s integration of recurrent and convolutional architectures for real-world applications shows clear impact: his LSTM work has been cited in subsequent neural network optimization studies, while his H-CNN approach offers a practical blueprint for autonomous line inspection. For students and researchers, Wu exemplifies how specialized neural network designs can solve domain-specific challenges in both creative computing and industrial robotics.