Evaluation of peach quality indices using an electronic nose by MLR, QPST and BP network

In this paper, responses of a gas sensor array were employed to establish a quality indices model evaluating the peach quality indices. The relationship between sensor signals and the firmness, the content of sugar (CS) and acidity of “Dabai” peach were developed using multiple linear regressions with stepwise procedure, quadratic polynomial step regression (QPST) and back-propagation network. The results showed that the multiple linear regression model represented good ability in predicting of quality indices, with high correlation coefficients (R² = 0.87 for penetrating force CF; R² = 0.79 for content of sugar CS; R² = 0.81 for pH) and relatively low average percent errors (ERR) (9.66%, 7.68% and 3.6% for CF, CS and pH, respectively). The quadratic polynomial step regression provides an accurate quality indices model, with high correlation (R² = 0.92, 0.87, 0.83 for CF, CS and pH, respectively) between predicted and measured values and a relatively low error (5.47%, 3.45%, 2.57% for CF, CS and pH, respectively) for prediction. The feed-forward neural network also provides an accurate quality indices model with a high correlation (R² = 0.90, 0.81, 0.87 for CF, CS and pH, respectively) between predicted and measured values and a relatively low average percent error (6.39%, 6.21%, 3.13% for CF, CS and pH, respectively) for prediction. These results prove that the electronic nose has the potential of becoming a reliable instrument to assess the peach quality indices.     

基于电子鼻区分三种致病菌的研究

旨在探讨一种快速检测致病菌的电子鼻方法。本研究利用基于金属氧化物传感器的电子鼻技术检测蜡样芽孢杆菌、单增李斯特菌和缓慢葡萄球菌三种致病菌培养液的挥发性代谢产物,结合化学计量学方法主成分分析(PCA)和聚类分析(CA)对电子鼻原始数据进行统计学分析。PCA模式识别结果显示该技术能够很好的将三种细菌在培养液中的挥发性代谢产物图谱进行区分,CA分析进一步显示单增李斯特菌与缓慢葡萄球菌的气味指纹图谱比较接近,而蜡样芽孢杆菌的图谱与它们的差异较大。研究表明该电子鼻技术有望在致病菌快速检测上得到更广泛的应用。     

An electronic nose system to diagnose illness

Recently, medical diagnostics has emerged to be a promising application area for electronic noses (e-nose). In this paper, we review work carried out at Warwick University on the use of an e-nose to diagnose illness. Specifically, we have applied an e-nose to the identification of pathogens from cultures and diagnosing illness from breath samples. These initial results suggest that an e-nose will be able to assist in the diagnosis of diseases in the near future.     

Identification of different alcoholic beverages by electronic nose coupled to GC

In this work, 21 different alcoholic beverages (beer, wines and spirits) were analyzed by an electronic nose after a dehydration and dealcoholization procedure. Principal component analysis (PCA) and discriminant factorial analysis (DFA) allowed to clearly identify differences between these various alcoholic beverages and to classify them independent of their ethanol content. The PCA showed that the sample discrimination was carried out according to the content in aroma compounds. The discrimination quality was evaluated using the leave-one out method, which allowed to quantify the percentage of samples classed correctly for a determined number of sensors.     

Mimicking the sense of olfaction: A conducting-polymer-based electronic nose

Abstract— We describe herein the construction of a simple, low-power, broadly responsive vapor sensor. Carbon-black-organic-polymer composites have been shown to swell reversibly upon exposure to vapors. Thin films of carbon-black-organic-polymer composites have been deposited across two metallic leads, with swelling-induced resistance changes of the films signaling the presence of vapors. To identify and classify vapors, arrays of such vapor-sensing elements have been constructed, with each element containing a different organic polymer as the insulating phase. The differing gas-solid partition coefficients for the various polymers of the sensor array produce a pattern of resistance changes that can be used to classify vapors and vapor mixtures. This type of sensor array has been shown to resolve all organic vapors that have been analyzed, and can even resolve H²O from D²O.     

电子鼻在气体检测中的应用研究

优选对甲烷、丙烷及氢气交叉敏感的5只半导体传感器组成气体传感器阵列,建立实时数据采集系统,结合特征提取和模式识别算法,研制出了一种对3种可燃性气体进行实时检测的电子鼻系统。提出了双重神经网络定量分析多种未知气体的方法,即先利用第一重网络对气体进行定性识别,再应用第二重网络对识别出的气体进行定量分析。通过BP神经网络分析表明:该系统对3种气体的识别率达到了100%,定量分析的最大相对误差不超过9.4%。     

A novel humid electronic nose combined with an electronic tongue for assessing deterioration of wine

We report herein the use of a combined system for the analysis of the spoilage of wine when in contact with air. The system consists of a potentiometric electronic tongue and a humid electronic nose. The potentiometric electronic tongue was built with thick-film serigraphic techniques using commercially available resistances and conductors for hybrid electronic circuits; i.e. Ag, Au, Cu, Ru, AgCl, and C. The humid electronic nose was designed in order to detect vapours that emanate from the wine and are apprehended by a moist environment. The humid nose was constructed using a piece of thin cloth sewn, damped with distilled water, forming five hollows of the right size to introduce the electrodes. In this particular case four electrodes were used for the humid electronic nose: a glass electrode, aluminium (Al), graphite and platinum (Pt) wires and an Ag-AgCl reference electrode. The humid electronic nose together with the potentiometric electronic tongue were used for the evaluation of the evolution in the course of time of wine samples. Additionally to the analysis performed by the tongue and nose, the spoilage of the wines was followed via a simple determination of the titratable (total) acidity.     

基于电子鼻技术的混合气体检测方法研究

对基于常规单一BP神经网络的电子鼻系统进行改进,提出一种基于Gabor原子神经网络的电子鼻系统,并以3种混合气体为实验对象,进行混合气体的定量分析研究.实验结果表明,应用Gabor原子神经网络的电子鼻系统的最大相对误差与单一BP神经网络相比得到减小,大大提高了定量分析精度.     

基于电子鼻的番茄种子不同储藏时间的鉴别研究

采用电子鼻对三种不同年份的番茄种子进行分析.结果表明:利用电子鼻可以很好的区分不同年份的番茄种子;利用主成分分析方法(PCA)基本上可以辨别出不同掺杂比例的种子,但是当掺杂比例为37.5%和50%时,较难利用电子鼻进行辨别区分;利用线性判别分析方法(LDA)可以很好的辨别出不同掺杂比例的番茄种子,并且每个混合种类的区域...     

基于多BP子网络的电子鼻信息融合技术

针对电子鼻技术的应用中,利用常规BP(back-propagation)网络难以对复杂的混合气味进行识别这一问题,介绍了一种采用多BP网络联合进行电子鼻多传感器数据融合处理的新方法。利用这一方法并结合气体传感器阵列在不同温度条件下的响应信号,对不同品牌的葡萄酒样本进行定性识别,仿真验证结果表明该方法的识别准确率达到100%。     

电子鼻技术在食醋识别中的应用

利用由10个掺杂纳米氧化锌厚膜气敏传感器组成的阵列对9种食醋和乙酸溶液进行了测量.并通过主元分析、聚类分析和概率神经网络对数据进行了分析和识别.主元分析表明不同的食醋在品牌、种类、酸度等方面具有一定的相似性.聚类分析进一步研究了食醋种类之间的相似程度.利用概率神经网络对所测试的食醋进行了识别,有较高的识别率.分析表明电子鼻技术是食醋分析和识别的一种具有发展前途的实用技术.     

基于金属氧化物传感器阵列的小麦霉变程度检测

研制了一套由8个金属氧化物传感器组成、用于检测小麦霉变的电子鼻系统.使用该电子鼻对不同霉变程度和掺入不同百分比含量霉麦的小麦样品进行检测.通过方差分析和主成分分析优化传感器阵列并去掉冗余传感器,对优化后的数据进行主成分分析(PCA)和线性判别分析(LDA),其中PCA的前两个主成分对两类实验结果分析的总贡献率为98.30％和99.27％,LDA前两个判别因子对两类实验结果分析的总贡献率为99.68％和93.30％,且由得分图可知两种方法均能很好地区分不同的小麦样品.利用BP神经网络建立预测模型,对样品菌落总数和掺入样品中霉麦的百分比进行预测.两种预测模型的预测值和测量值之间的相关系数分别为0.91和0.94,表明预测模型具有较好预测性能.     

Systematic studies on responses of metal-oxide sensor surfaces to straight chain alkanes, alcohols, aldehydes, ketones, acids and esters using the SOMMSA approach

Metal oxide sensors are widely used in the so-called “electronic noses”, and it is proposed that these equipment can be used to objectify food aromas.

Due to the fact that, up to now, systematic approaches to correlate the intensity of sensor responses with the structure of a given volatile have scarcely been performed [K. Suzuki, T. Takada, Highly sensitive odour sensors using various SnO₂ thick films, Sens. Actuators, B 24–25 (1995) 773–776; B. Lalauze et al., High sensitivity materials for gas detection, Sens. Actuators, B 8 (1992) 237–243; K. Fukui, Detection and measurement of odor by sintered tin oxide gas sensor, Sens. Actuators, B 5 (1991) 27–32; J.W. Gardner, A. Pike et al., Integrated array sensor for detecting organic solvents, Sens. Actuators, B 13–14 (1993) 355–357.], it is as yet not possible to predict the sensitivity and the specivity of metal oxide preparations vs. a given chemical structure.

Using the SOMMSA approach [T. Hofmann et al., High resolution gas chromatography/selective odorant measurement by multisensor array (HRGC/SOMSA): a useful approach to standardize multisensor arrays for the use in the detection of key food odorants, Sens. Actuators, B 41 (1997) 81–87.], mixtures of alkanes, alcohols, aldehydes (all with chain length of 8–14 carbon atoms) and acids (chain length of 2–10 carbon atoms) were applied to different self-prepared metal oxide mixtures and the signal intensities were monitored. In addition, quantitative experiments were performed to determine the detection threshold of sensors. E.g. (E,E)-2,4-nonadienal, one of the most important odorants in fresh cucumbers, could be clearly detected at a level below 4.0 ng/ml (He) by a sensor containing a mixture of ZnO and SnO₂.     

An electronic nose system based on a micro-machined gas sensor array to assess the freshness of sardines

An electronic nose system based on a four-element, integrated, micro-machined, metal oxide gas sensor array is used to assess, in an objective manner, the evolutionary stages of freshness in sardine samples stored up to 1-week at 4 °C. The sensors developed were based on tin oxide doped with Pt or Pd or Bi, and on tungsten oxide doped with Au. The selection of the gas sensitive materials was based on a previous identification and quantification of characteristic compounds found in the headspace of sardines determined by solid phase micro-extraction gas chromatography coupled to mass spectrometry. Principal component analysis performed on the responses of the sensor array revealed that sardine samples could be classified in three freshness states. This was in good agreement with the results of a microbiological analysis. A support vector machine-based classifier reached a 100% success rate in the identification of sardine freshness. The stability of the electronic nose classification ability was assessed by correctly classifying measurement databases gathered 1-month apart. By building and validating quantitative partial least squares models, which employed as input data the gas sensor responses, it was possible to predict with good accuracy the total viable counts (TVC) of aerobic bacteria present in sardine samples. For the validation dataset, the correlation coefficient between actual and predicted TVC was 0.91, which indicates that the electronic nose system developed is a simple and rapid technique for evaluating sardine freshness.     

基于LabVIEW平台的电子鼻系统设计

为了检测CH4,CO气体,设计了基于STM32F103和LabVIEW的智能电子鼻系统;该系统利用STM32F103作为核心控制系统,筛选出6只电化学传感器组成的阵列,传感器的响应信号经过电路放大转换后传输到上位机;利用LabVIEW开发上位机软件,将数据采集系统与神经网络模式识别系统无缝连接.经过实验验证,该系统运行稳定可靠,通过对9种不同比例混合的CH4和CO气体进行检测,CO的平均误差为5.52×10-6,CH4的平均误差为7.15×10-6,测试结果满足要求.     

电子鼻温度控制系统的设计

针对目前电子鼻中温度控制系统存在的不足,提出了一种使用简便、控制速度快,且精度高的温控系统.系统利用半导体制冷片的快速制热和制冷功能,通过控制制冷片两端的电流方向,同时使用PID控制算法和环境温度补偿方法,实现气室温度控制.通过实验,进一步验证了温度对湿度和传感器的影响.实验结果表明:系统能够达到的控温精度为±0.3℃...     

基于电子鼻技术的花椒品种鉴别方法研究

本文针对不同花椒品种的快速鉴别方法进行研究,以花椒的气味信息检测为研究对象,利用自行研制的电子鼻系统采集了6类花椒样品气味数据,对这些数据样本进行特征提取,得到了56组训练样本和32组测试样本。利用BP神经网络、概率神经网络和支持向量机对特征数据进行鉴别,正确识别率分别为89.58%、93.23%、94.27%,相对于BP神经网络和概率神经网络识别,支持向量机具有更好的分类效果。 本文研制的电子鼻系统能能无损、快速、准确鉴别花椒的品种,为农产品无损检测的研究提供了一种新的思路。     

用电子鼻鉴别卷烟的方法

用四单元金属氧化物传感器阵列构成电子鼻系统,采用运算复杂度较小的特征提取与模式识别方法实现了三种卷烟的鉴别,并通过一系列比较实验研究了特征提取方法、气室、卷烟样品温度以及载气流量等对识别结果的影响。     

Use of electronic nose technology for identifying rice infestation by Nilaparvata lugens

Plant-emitted volatiles can change after herbivore attack. Monitoring the change in volatile profiles can offer a non-destructive method for determining plant health. An electronic nose (E-nose) equipped with a headspace sampling unit was used to discriminate between volatile profiles emitted by uninfested rice plants and those emitted by rice plants exposed to different numbers of Nilaparvata lugens adults. Principal component analysis (PCA) and linear discriminant analysis (LDA) were used to investigate whether the E-nose was able to distinguish among the different pest treatments. The results indicate that it is possible to separate differently treated rice plants using E-nose signals. The stepwise discriminant analysis (SDA) and a 3-layer back-propagation neural network (BPNN) were developed for pattern recognition models. Calculations show that the discrimination rates were over 92.5% for the training data set and 70% for the testing set using SDA. The correlation coefficient between predicted and real numbers of the pest was found to be over 0.78 using BPNN. Moreover, gas chromatography–mass spectrometry (GC–MS) analysis confirmed the E-nose results. These studies demonstrate that the E-nose technology has clear potential for use as an effective insect monitoring method.     

基于PCA和LVQ混合神经网络算法的电子鼻系统

为了对食物品质进行非接触式评价,采用6种费加罗金属氧化物半导体传感器阵列设计并研制了可对被测食物进行无损检测的电子鼻系统.系统主要由采样模块、控制模块和上位机组成,并采用主成分分析(PCA)和学习矢量量化(LVQ)混合神经网络模式识别算法对气体“指纹信息”数据库进行分析.实验结果表明,利用该电子鼻系统可以对5种不同的食用酱进行检测,并且具有对未知酱品进行识别的功能.