Yanmei Yang, Yanling Lai, Jinzhong Yang, Yuan Ji, Qifei Huang, Hao Hu
With the growing demand for precise and intelligent solid waste management, developing efficient and intuitive identification and traceability technologies has become critical. Radar charts, as a multidimensional information visualization tool, integrate complex multivariate features into unique "graphical fingerprints," showing significant potential in material classification and source tracing. This mini‑review systematically examines the principles of radar charts and their application in solid waste classification, with a focus on feature fusion, fingerprint construction, and artificial intelligence (AI)‑based identification. A bibliometric analysis based on CiteSpace examines the evolution of radar chart research over the past 15 years, highlighting its shift from methodological exploration to deep integration with machine learning and intelligent sensing. The study summarizes methods for acquiring fingerprint characteristics, feature extraction and dimensionality reduction, and AI-based identification models, emphasizing the core advantage of radar charts in converting high-dimensional data into discriminative graphical profiles. A comprehensive technical framework-"data acquisition, feature extraction, intelligent modeling, and visual representation"-is proposed, offering a systematic solution for precise classification, traceability, and intelligent management of solid waste.