A feature-selection algorithm based on Support Vector Machine-Multiclass for hyperspectral visible spectral analysis

• Published in: Journal of food engineering Vol. 119; no. 1; pp. 159 - 166
• Main Authors: Deng, Shuiguang, Xu, Yifei, Li, Li, Li, Xiaoli, He, Yong
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.11.2013
• Subjects: Accuracy; Algorithms; Feature selection; food inspection; food quality; Food quality inspection; Foods; Hyperspectral visible and near infrared (Vis–NIR); Inspection; Mathematical analysis; Mathematical models; prediction; rapid methods; regression analysis; Sesame oil; Spectra; spectral analysis; Support Vector Machine-Multiclass Forward Feature Selection (SVM-MFFS); Vectors (mathematics); wavelengths; Sesame oil; Support Vector Machine-Multiclass Forward Feature Selection (SVM-MFFS); Food quality inspection; Feature selection; Hyperspectral visible and near infrared (Vis–NIR)
• ISSN: 0260-8774; 1873-5770
• DOI: 10.1016/j.jfoodeng.2013.05.024

•A total novel feature selection algorithm called SVM-MFFS is proposed.•A novel indicator called CS is proposed to evaluate the ability of models.•SVM-MFFS outperforms other methods with classifying different sesame oils. Quality and safety of foods is one of the world’s top topics. Using high-precision spectral devices is a main technology trends by its high accuracy and nondestructive of food inspection, but the common obstacle is how to extract informative variables from raw data without losing significant information. This article proposes a novel feature selection algorithm named Support Vector Machine-Multiclass Forward Feature Selection (SVM-MFFS). SVM-MFFS adopts the wrapper and forward feature selection strategy, explores the stability of spectral variables, and uses classical SVM as classification and regression model to select the most relevant wavelengths from hundreds of spectral data. We compare SVM-MFFS with Successive Projection Analysis and Uninformative Variable Elimination in the experiment of identifying different brands of sesame oil. The results show that SVM-MFFS outperforms in accuracy, Receiver Operating Characteristic curve, Prediction and Cumulative Stability, and it will provide a reliable and rapid method in food quality inspection.