Qingjun Song

Shandong University of Science and Technology

Papers

Total Citations

H-Index

About

Qingjun Song is a researcher advancing the frontiers of machine learning and robotics, with key contributions in classification algorithms and bipedal locomotion. Their most cited work, "Hybrid Metric K-Nearest Neighbor Algorithm and Applications" (2022, 19 citations), addresses a critical limitation of traditional KNN methods—reliance on a single metric and poor handling of repeated values in K ranges—by introducing a hybrid metric approach that significantly improves classification accuracy, particularly for fault diagnosis applications. This work has become a reference point for researchers seeking to enhance classical algorithms. In robotics, Song's 2024 study "Optimization of Biped Robot Walking Based on the Improved Particle Swarm Algorithm" tackles the challenge of gait generation using central pattern generators (CPGs). By developing an improved particle swarm optimization (PSO) algorithm that better balances exploration and exploitation, Song enables more stable and efficient biped walking patterns. Though early in its citation life, this work demonstrates Song's commitment to solving real-world optimization problems. Their research elegantly bridges theoretical algorithm improvement with practical engineering applications, making their work valuable for students and researchers in both machine learning and robotics communities.