Gangqiang Zhang

Chongqing University of Posts and Telecommunications

Papers

Total Citations

H-Index

About

Gangqiang Zhang is a researcher whose work lies at the intersection of machine learning, decision theory, and human-computer interaction, with a particular focus on social touch gesture recognition. His most-cited paper, "An Ensemble Classifier Based on Three-Way Decisions for Social Touch Gesture Recognition" (2018), introduces a novel framework that combines ensemble learning with three-way decision theory—a granular computing approach that handles uncertainty by deferring ambiguous classifications. This work addresses the challenge of interpreting subtle, non-verbal human gestures in social robotics and affective computing, where misclassification can undermine user trust. By integrating multiple classifiers with a tripartite decision boundary (accept, reject, or defer), Zhang’s method improves recognition accuracy and robustness, offering a practical solution for real-world applications like assistive technologies and interactive systems. While his citation count is modest, the paper’s focus on a niche yet growing field—social touch recognition—positions him as a contributor to advancing human-robot interaction. His research bridges theoretical decision models with applied gesture analysis, demonstrating how three-way decisions can enhance the reliability of machine perception in socially sensitive contexts.