A Machine Learning Method for the Detection of Brown Core in the Chinese Pear Variety Huangguan Using a MOS-Based E-Nose

Abstract

The brown core is an internal disorder that significantly affects the palatability and economic value of Chinese pears. In this study, a framework that includes a back-propagation neural network (BPNN) and extreme learning machine (ELM) (BP-ELMNN) was proposed for the detection of brown core in the Chinese pear variety Huangguan. The odor data of pear were collected using a metal oxide semiconductor (MOS) electronic nose (E-nose). Principal component analysis was used to analyze the complexity of the odor emitted by pears with brown cores. The performances of several machine learning algorithms, i.e., radial basis function neural network (RBFNN), BPNN, and ELM, were compared with that of the BP-ELMNN. The experimental results showed that the proposed framework provided the best results for the test samples, with an accuracy of 0.9683, a macro-precision of 0.9688, a macro-recall of 0.9683, and a macro-F1 score of 0.9685. The results demonstrate that the use of machine learning algorithms for the analysis of E-nose data is a feasible and non-destructive method to detect brown core in pears.

A Machine Learning Method for the Quantitative Detection of Adulterated Meat Using a MOS-Based E-Nose

“…The stable value (SV) is a vital and simple feature of the E-nose response signal which reflects the properties of the substances in the volatile gas and can be used by pattern recognition algorithms [ 24 ]. In this study, SVs (the values from 91 s to 100 s of the response signal) were used as the input data to the SVR, RFR, and BPNN.…”

“…Generally, the first few principal components must contribute at least 85% of the variance, or else the PCA method would be considered unsuitable because too much of the original information would be lost [ 27 ]. The first few principal components to make up a cumulative contribution exceeding 95% contain nearly all the information of the original data [ 24 ]. PCA is arguably the most popular multivariate statistical technique and has been applied in nearly all scientific disciplines [ 28 ].…”

A Machine Learning Method for the Fine-Grained Classification of Green Tea with Geographical Indication Using a MOS-Based Electronic Nose

“…The sensor array can detect volatile compounds in the sample gases and provides feature information (sensor responses in the array). The E-nose has been increasingly used to analyze foods and beverages [ 15 , 16 , 17 , 18 , 19 ]. In recent years, many researchers have tried to distinguish tea categories using an E-nose system.…”

FPGA Implementation for Odor Identification with Depthwise Separable Convolutional Neural Network

“…Sigfredo et al designed an array of gas sensor and five machine learning algorithms to detect and evaluate contamination in grapevine berries and taint in wines [ 2 ]. Hao Wei et al used PEN3 e-nose for data collection and designed a back-propagation neural network (BPNN) to detect brown core in the Chinese pear variety huangguan [ 3 ]. Winston Li et al used four classifiers—MLP, SVM, KNN, and Parzen—and fusion in Dempster–Shafer to improve the accuracy of odor classification [ 4 ].…”

“…Therefore, odor identification is accelerated in FPGA. (3) The SF-KL quantization scheme is designed to reduce FPGA resource consumption and maintain the accuracy.…”