Mining Feature of Data Fusion in the Classification of Beer Flavor Information Using E-Tongue and E-Nose.

Hong Men,Yanan Jiao,Yan Shi,Yu Qiao,Songlin Fu,Jingjing Liu

doi:10.3390/s17071656

Abstract

Multi-sensor data fusion can provide more comprehensive and more accurate analysis results. However, it also brings some redundant information, which is an important issue with respect to finding a feature-mining method for intuitive and efficient analysis. This paper demonstrates a feature-mining method based on variable accumulation to find the best expression form and variables’ behavior affecting beer flavor. First, e-tongue and e-nose were used to gather the taste and olfactory information of beer, respectively. Second, principal component analysis (PCA), genetic algorithm-partial least squares (GA-PLS), and variable importance of projection (VIP) scores were applied to select feature variables of the original fusion set. Finally, the classification models based on support vector machine (SVM), random forests (RF), and extreme learning machine (ELM) were established to evaluate the efficiency of the feature-mining method. The result shows that the feature-mining method based on variable accumulation obtains the main feature affecting beer flavor information, and the best classification performance for the SVM, RF, and ELM models with 96.67%, 94.44%, and 98.33% prediction accuracy, respectively.

Highlights

The consumption of beer, as a beverage, ranks third in the world after water and tea
(1) Compared with the single e-tongue and single e-nose, the classification accuracy rate of beer flavor flavor information was improved by using multi-sensor data fusion, and the classification information was improved by using multi-sensor data fusion, and the classification accuracy rate accuracy rate of support vector machine (SVM) was 88.89%, random forests (RF) was 88.89%, and extreme learning machine (ELM) was 88.33%; of SVM was 88.89%, RF was 88.89%, and ELM was 88.33%; (2) The feature selection method based on principal component analysis (PCA) did not obtain the best form of beer flavor
The feature selection method based on improved the beer flavor classification ratebest and classification rate and reduced the feature dimension obviously, and SVM showed the reduced the performance feature dimension obviously, and SVM

Summary

Introduction

The consumption of beer, as a beverage, ranks third in the world after water and tea. It is rich in various amino acids, vitamins, and other nutrients needed by the human body [1,2], which is euphemistically known as ‘liquid bread’. Barley germination is the main raw material for beer brewing, which makes beer a low-alcohol and high-nutrition drink It promotes digestion, spleen activity, appetite, and other functions [3,4,5]. Accurately and efficiently identifying different beers, and finding important features, are significant. It is meaningful for quality control, storage, and authenticity recognition. It is difficult to distinguish apple and potato, red wine and coffee

Results

Discussion

Conclusion