Discrimination of Beer Based on E-tongue and E-nose Combined with SVM: Comparison of Different Variable Selection Methods by PCA, GA-PLS and VIP

Abstract

Multi-sensor data fusion of E-tongue and E-nose can provide a more comprehensive and more accurate analysis results. However, it also brings some redundant information, it is a hot issue to reduce the feature dimension for pattern recognition. In this paper, the taste-olfactory data fusion based on E-tongue and E-nose combined with Support Vector Machine (SVM) was used to classify five different beers. First, the taste and olfactory feature information were obtained based on E-tongue and E-nose. Second, the original feature data of single system were fused, then Principal Component Analysis (PCA) was applied to extract principal components, Genetic Algorithm-Partial Least Squares (GA-PLS) was used to select the characteristic variables, 20 subsets were generated with those variables based on the best Variable Importance of Projection (VIP) score. Finally, the classification models based on SVM were established, also c and g of SVM were calculated by Grid Search (GS), Genetic Algorithm (GA), and Particle Swarm Optimization (PSO), the classification results of all subsets were obtained. The results showed that the classification accuracy using data fusion was much higher over single E-tongue and single E-nose, and the variable selection method by VIP had the best classification performance in #12 subset coupled with GA-SVM.

High freezing rate improves flavor fidelity effect of hand grab mutton after short-term frozen storage

“…Electronic nose (E-nose) analysis was performed using a PEN 3.5 E-nose (Airsense, Schwerin, Germany) according to the existing methods with minor modifications ( 25 – 27 ). The PEN3.5 system contains 10 metal oxide gas sensors (namely W1C, W5S, W3C, W6S, W5C, W1S, W1W, W2S, W2W, and W3S), which can detect olfactory cross-sensitive information ( 28 – 30 ). The response characteristics of each sensor are as follows: W1C (aromatic), W5S (broad range), W3C (aromatic), W6S (hydrogen), W5C (arom-aliph), W1S (broad-methane), W1W (sulphur-organic), W2S (broad-alcohol), W2W (sulph-chlor) and W3S (methane-aliph).…”

Recent Progress in Electronic Noses for Fermented Foods and Beverages Applications

“…With a focus on applications in the food and beverage industry, E-nose systems have been used for both direct/indirect identification via odor analysis for multiple purposes, such as product quality inspection [88], batch-to-batch uniformity studies [89], contamination detection [90], spoilage detection [91][92][93], adulteration detection [13,94], the detection of pathogenic bacteria [95,96], the study of storage conditions/shelf life [97][98][99][100] and the creation of specific sensory profiles [101,102]. In terms of food business competition, they have been used to analyze aromas and compare them with competitor products [103,104], evaluate the impact of changes in the production process and components that affect organoleptic characteristics [105,106] and compare different food formulations [84,107]. Moreover, E-nose systems have showed high performance in identifying the quality of many products, including wine [108], beer [109], coffee [110], carbonated drinks [111], dairy products Nowadays, E-nose systems based on a diversity of gas sensor arrays are applied in all major sectors, such as agriculture and forestry [64][65][66], industrial processes [67], environmental toxin/pollutant analysis [68][69][70], space stations [71,72], medical/healthcare [73][74][75]...…”

Electronic Nose, Tongue and Eye: Their Usefulness for the Food Industry

“…Another disadvantage of the electronic tongue is the relatively short lifespan of sensor materials, especially biomaterials. It requires users to examine the electronic tongue's performance frequently; also, a large amount of the sample size is often required (71).…”