Evaluation of E-nose data analyses for discrimination of tea plants with different damage types

Abstract

This study employed electronic nose (E-nose) to detect tea plants with different types of damage (undamaged, mechanically damaged, damages caused by Ectropis obliqua and Ectropis grisescens). Gas chromatography–mass spectrometry was employed as an auxiliary technique for proving the potential of E-nose detection. A new feature extraction method was applied for obtaining comprehensive features of E-nose dataset. Feature selection method based on principal component analysis (PCA) was applied for further feature selection. Four dimensionality reduction methods [PCA, locality preserving projections (LPP), kernel principal component analysis and locally linear embedding] and three classification algorithms [multilayer perceptron neural network, extreme learning machine and support vector machine (SVM)] were employed, and the best combination of dimensionality reduction method and classification algorithm was determined. The results showed that the combination of LPP and SVM was the best, and its correct discrimination rate was as high as 100%, which proved the advantage of the new signal processing method and the feasibility of E-nose in discriminating among tea plants with different types of damage.