Taste Recognition in E-Tongue Using Local Discriminant Preservation Projection

Abstract

Electronic tongue (E-Tongue), as a novel taste analysis tool, shows a promising perspective for taste recognition. In this paper, we constructed a voltammetric E-Tongue system and measured 13 different kinds of liquid samples, such as tea, wine, beverage, functional materials, etc. Owing to the noise of system and a variety of environmental conditions, the acquired E-Tongue data shows inseparable patterns. To this end, from the viewpoint of algorithm, we propose a local discriminant preservation projection (LDPP) model, an under-studied subspace learning algorithm, that concerns the local discrimination and neighborhood structure preservation. In contrast with other conventional subspace projection methods, LDPP has two merits. On one hand, with local discrimination it has a higher tolerance to abnormal data or outliers. On the other hand, it can project the data to a more separable space with local structure preservation. Further, support vector machine, extreme learning machine (ELM), and kernelized ELM (KELM) have been used as classifiers for taste recognition in E-Tongue. Experimental results demonstrate that the proposed E-Tongue is effective for multiple tastes recognition in both efficiency and effectiveness. Particularly, the proposed LDPP-based KELM classifier model achieves the best taste recognition performance of 98%. The developed benchmark data sets and codes will be released and downloaded in http://www.leizhang.tk/tempcode.html.

Sensing fermentation degree of cocoa (Theobroma cacao L.) beans by machine learning classification models based electronic nose system

“…In previous studies, the application of subspace learning and support vector machine algorithms in electronic tongue (Zhang, Wang, Huang, Liu, & Tan, 2019) and electronic nose (Zhang, Liu, & Deng, 2017) have been investigated, and good prediction (98% accuracy) was achieved. However, detection and of cocoa fermentation in natural condition using e-nose was not reported.…”

A data-driven methodology for the classification of different liquids in artificial taste recognition applications with a pulse voltammetric electronic tongue

“…As an example, the MSPV is proved to be the best waveform for classifying different yogurts. 17 In 2018, the study by Zhang et al 10 showed an electronic tongue based on an MLAPV technique. This electronic tongue followed the electrodes setup of Tian et al 16 In the e-tongue, five electrodes, made of gold, platinum, palladium, tungsten, and silver, were chosen as working electrodes, whose responses are illustrated in Figure 3.…”

“…In 2018, Zhang et al 10 conducted a research, where they showed that due to the noise of the system and a variety of environmental conditions, the data acquired by an electronic tongue show inseparable patterns. To solve this phenomenon, from the point of view of the algorithm, they proposed an LDPP model.…”

“…In the study by Zhang et al, 10 an electronic tongue based on an array of five different sensors applies the technique of MLAPV. The pulse signal (excitation) comprises three individual frequencies: 1, 3, and 5 Hz, and five amplitudes of voltage: 4.10, 3.85, 3.60, 3.35, and 3.10 V for each frequency.…”

Fuzzy Evaluation Output of Taste Information for Liquor Using Electronic Tongue Based on Cloud Model

“…The local discriminant preservation projection (LDPP) model was proposed from the perspective of algorithm. Kernelized extreme learning machine (KELM) classifier model based on LDPP achieved optimal taste recognition performance with an accuracy of 98% [22]. Some researchers have improved the accuracy of fruit juice recognition through the fusion of electronic tongue and electronic nose [23].…”