Terahertz Spectroscopic Identification of Roast Degree and Variety of Coffee Beans

Abstract

In this study, terahertz time-domain spectroscopy (THz-TDS) was proposed to identify coffee of three different varieties and three different roasting degrees of one variety. Principal component analysis (PCA) was applied to extract features from frequency-domain spectral data, and the extracted features were used for classification prediction through linear discrimination (LD), support vector machine (SVM), naive Bayes (NB), and k-nearest neighbors (KNN). The classification effect and misclassification of the model were analyzed via confusion matrix. The coffee varieties, namely Catimor, Typica 1, and Typica 2, under the condition of shallow drying were used for comparative tests. The LD classification model combined with PCA had the best effect of dimension reduction classification, while the speed and accuracy reached 20 ms and 100%, respectively. The LD model was found with the highest speed (25 ms) and accuracy (100%) by comparing the classification results of Typica 1 for three different roasting degrees. The coffee bean quality detection method based on THz-TDS combined with a modeling analysis method had a higher accuracy, faster speed, and simpler operation, and it is expected to become an effective detection method in coffee identification.

Distributed Consensus for Global Matrix Formation in the Principal Component Pursuit Scenario

“…There are many applications where PCA is relevant; some examples are video surveillance, face recognition [12], latent semantic indexing [13], ranking and collaborative filtering to anticipate tastes, image analysis including fluid dynamics [14], machine learning and food identification [15], among others. Examples of PCA applied to face image processing and fluid flows are shown in Figures 1 and 2.…”