Yufei Chen , Jun Fu , Xin Weng , Jiaoni Chen , Ruifen Hu , Yunfang Zhu
{"title":"基于并行长短期记忆网络的电子鼻时间数据特征提取器在中国醋风味鉴别中的应用","authors":"Yufei Chen , Jun Fu , Xin Weng , Jiaoni Chen , Ruifen Hu , Yunfang Zhu","doi":"10.1016/j.jfoodeng.2024.112132","DOIUrl":null,"url":null,"abstract":"<div><p>Volatile flavor is a key indicator of food quality which can directly affect consumer preference and purchase intention. Electronic nose is considered as a promising intelligent sensory analysis tool for food flavor assessment, however, extracting effective features from the gas sensor array is still a major challenge, which largely determines the performance of subsequent classifiers. Here, a parallel long short-term memory (LSTM) network is proposed as a feature extractor for automatically extracting features from the whole time series of sensor responses in flavor discrimination of five Chinese vinegars. The network was trained by the temporal data from the sensor array and yielded different feature patterns corresponding to different vinegars, which were then fed to other conventional classifiers for pattern recognition. We also evaluated the influence of the extracted feature dimension that is related to the dimension of the hidden state of the LSTM layer on the classification performance. The results indicate that a larger dimension of extracted feature is unnecessary for promoting classification accuracy, instead, the optimum dimension 4 of the hidden state gives the highest accuracy of 95.8% in this application under the softmax evaluator. Moreover, much higher accuracies were obtained when combined with other sophisticated classifiers such as support vector machine. The results demonstrate that the proposed network is competent to extract features directly and automatically from the temporal data of the electronic nose.</p></div>","PeriodicalId":359,"journal":{"name":"Journal of Food Engineering","volume":null,"pages":null},"PeriodicalIF":5.3000,"publicationDate":"2024-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A feature extractor for temporal data of electronic nose based on parallel long short-term memory network in flavor discrimination of Chinese vinegars\",\"authors\":\"Yufei Chen , Jun Fu , Xin Weng , Jiaoni Chen , Ruifen Hu , Yunfang Zhu\",\"doi\":\"10.1016/j.jfoodeng.2024.112132\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Volatile flavor is a key indicator of food quality which can directly affect consumer preference and purchase intention. Electronic nose is considered as a promising intelligent sensory analysis tool for food flavor assessment, however, extracting effective features from the gas sensor array is still a major challenge, which largely determines the performance of subsequent classifiers. Here, a parallel long short-term memory (LSTM) network is proposed as a feature extractor for automatically extracting features from the whole time series of sensor responses in flavor discrimination of five Chinese vinegars. The network was trained by the temporal data from the sensor array and yielded different feature patterns corresponding to different vinegars, which were then fed to other conventional classifiers for pattern recognition. We also evaluated the influence of the extracted feature dimension that is related to the dimension of the hidden state of the LSTM layer on the classification performance. The results indicate that a larger dimension of extracted feature is unnecessary for promoting classification accuracy, instead, the optimum dimension 4 of the hidden state gives the highest accuracy of 95.8% in this application under the softmax evaluator. Moreover, much higher accuracies were obtained when combined with other sophisticated classifiers such as support vector machine. The results demonstrate that the proposed network is competent to extract features directly and automatically from the temporal data of the electronic nose.</p></div>\",\"PeriodicalId\":359,\"journal\":{\"name\":\"Journal of Food Engineering\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":5.3000,\"publicationDate\":\"2024-05-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Food Engineering\",\"FirstCategoryId\":\"97\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0260877424001985\",\"RegionNum\":2,\"RegionCategory\":\"农林科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENGINEERING, CHEMICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Food Engineering","FirstCategoryId":"97","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0260877424001985","RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, CHEMICAL","Score":null,"Total":0}
A feature extractor for temporal data of electronic nose based on parallel long short-term memory network in flavor discrimination of Chinese vinegars
Volatile flavor is a key indicator of food quality which can directly affect consumer preference and purchase intention. Electronic nose is considered as a promising intelligent sensory analysis tool for food flavor assessment, however, extracting effective features from the gas sensor array is still a major challenge, which largely determines the performance of subsequent classifiers. Here, a parallel long short-term memory (LSTM) network is proposed as a feature extractor for automatically extracting features from the whole time series of sensor responses in flavor discrimination of five Chinese vinegars. The network was trained by the temporal data from the sensor array and yielded different feature patterns corresponding to different vinegars, which were then fed to other conventional classifiers for pattern recognition. We also evaluated the influence of the extracted feature dimension that is related to the dimension of the hidden state of the LSTM layer on the classification performance. The results indicate that a larger dimension of extracted feature is unnecessary for promoting classification accuracy, instead, the optimum dimension 4 of the hidden state gives the highest accuracy of 95.8% in this application under the softmax evaluator. Moreover, much higher accuracies were obtained when combined with other sophisticated classifiers such as support vector machine. The results demonstrate that the proposed network is competent to extract features directly and automatically from the temporal data of the electronic nose.
期刊介绍:
The journal publishes original research and review papers on any subject at the interface between food and engineering, particularly those of relevance to industry, including:
Engineering properties of foods, food physics and physical chemistry; processing, measurement, control, packaging, storage and distribution; engineering aspects of the design and production of novel foods and of food service and catering; design and operation of food processes, plant and equipment; economics of food engineering, including the economics of alternative processes.
Accounts of food engineering achievements are of particular value.