Solid-phase microextraction, gas chromatography, and mass spectrometry coupled with discriminant factor analysis and multilayer perceptron neural network for detection of Escherichia coli

This study was performed to investigate the ability of using discriminant factor analysis (DFA) and an artificial neural network (ANN) to identify and quantify the number of Escherichia coli (ATCC 25922) in nutrient media from data generated by analysis of E. coli volatile metabolic compounds using solid-phase microextraction (SPME) coupled with gas chromatography (GC) and mass spectrometry (MS). E. coli was grown in super broth and incubated at 37 degrees C for 2 to 12 h. Numbers of E. coli were followed using a colony counting method. An SPME device was used to collect the volatiles from the headspace above the samples, and the volatiles were identified using GC-MS. DFA was used to classify the samples from different incubation times. From DFA, it was possible to differentiate super broth from media containing E. coli when cell numbers were 10(5) CFU or more. The potential to predict the number of E. coli from the SPME-GC-MS data was investigated using a multilayer perceptron (MLP) neural network with back propagation training. The MLP comprised an input layer, one hidden layer, and an output layer, with a hyperbolic tangent sigmoidal transfer function in the hidden layer and a linear transfer function in the output layer. Good prediction was found as measured by a regression coefficient (R2 = 0.996) between actual and predicted data.     

Detection of Escherichia coli in packaged alfalfa sprouts with an electronic nose and an artificial neural network

A rapid method for the detection of Escherichia coli (ATCC 25922) in packaged alfalfa sprouts was developed. Volatile compounds from the headspace of packaged alfalfa sprouts, inoculated with E. coli and incubated at 10 degrees C for 1, 2, and 3 days, were collected and analyzed. Uninoculated sprouts were used as control samples. An electronic nose with 12 metal oxide electronic sensors was used to monitor changes in the composition of the gas phase of the package headspace with respect to volatile metabolites produced by E. coli. The electronic nose was able to differentiate between samples with and without E. coli. To predict the number of E. coli in packaged alfalfa sprouts, an artificial neural network was used, which included an input layer, a hidden layer, and an output layer, with a hyperbolic tangent sigmoidal transfer function in the hidden layer and a linear transfer function in the output layer. The network was shown to be capable of correlating voltametric responses with the number of E. coli. A good prediction was possible, as measured by a regression coefficient (R2 = 0.903) between the actual and predicted data. In conjunction with the artificial neural network, the electronic nose proved to have the ability to detect E. coli in packaged alfalfa sprouts.     

Monitoring sausage fermentation using an electronic nose

In this study a sensor array and pattern recognition routines (an electronic nose) were used to monitor a sausage fermentation in order to follow the changes in emitted volatile compounds during the fermentation process and to compare the electronic nose results with a sensory analysis. From the sensor array responses the fermentation time could be predicted using different methods, where principal component regression and an artificial neural network based on all sensors in the electronic nose performed best. A sensory panel evaluated the final product and these results were compared with the electronic nose measurements in the early stage of the process and on the final sausages. A principal component analysis showed that one of the sausage batches clearly deviated from the other using both the sensory panel data and the electronic nose responses. The deviating batch was different already after 4 h and the difference was consistent during the process. © 1998 SCI.     

近红外光谱协同BP神经网络的泰国茉莉香米掺伪含量快速鉴定

利用近红外光谱协同BP神经网络算法,对泰国茉莉香米及其掺伪样品的近红外光谱进行多元散射校正预处理,挑选出48个特征波长;以特征波长的吸光度为BP神经网络输入层神经元,以样品中泰国茉莉香米的含量为输出层神经元,获得BP神经网络算法的最优结构模型,即为单层隐含层、隐含层神经元数7、隐含层传递函数logsig、输出层传递函数...     

红景天苷缓释微囊神经网络建模

本文在确定输入层和输出层单元、预处理网络数据、选择激活函数、选择训练方法的基础上,建立了红景苷缓释微囊制作参数与性能之间的神经网络模型,网络结构为5-12-3。该模型能较为精确的拟合输入的样本数据,其最大相对误差不超过4%,模型准确可信,可以代替真实试验,该模型的建立为工艺参数的优化打下基础。     

Comparative analyses of apple aroma by a tin-oxide gas sensor array device and GC/MS

The apple cultivars “fuji”, “jina” and “huaniu” aroma volatiles were collected and analyzed using a tin-oxide gas sensor array device and the gas chromatography combined with mass spectrometry (GC-MS). Twenty two of the most abundant volatile compounds were taken into account for further study. Eight compounds were found in every cultivar. The principal components analysis (PCA), partial least squares (PLS) and back-propagation feed-forward artificial neural network (BP-ANN) were used to analyze the sensor array and SPME-GC-MS measurements. From the plots of the first two PCs by PCA, different apple cultivars could be clearly distinguished by SPME-GC-MS measurements, while there was slight overlap by sensor array measurements. BP-ANN was used to distinguish different cultivars based on gas sensor array responses, and the accuracy was 87%. Due to the composition of gas sensors in the array, results of PLS models showed that the correlation between fourteen gas sensor array responses and the two PCs of twenty-two compounds were better than the correlation between those and each volatile compound. Furthermore, an ANN was used to build the relationship between the two predicted PCs by PLS model and the three cultivars. The recognition probability was increased to 97%.     

木糖醇发酵液脱色过程的模拟

运用人工神经网络模拟木糖醇发酵液的脱色过程 .借助均匀设计法确定人工神经网络的隐层神经元数、学习速度、动量因子 ,构建一个能很好地用于预测、优化木糖醇发酵液脱色过程的三层 5 6 2的网络模型 .     

Application of Image Analysis and Artificial Neural Network to Predict Mass Transfer Kinetics and Color Changes of Osmotically Dehydrated Kiwifruit

The objectives of this study were to use image analysis and artificial neural network to predict mass transfer kinetics and color changes of osmotically dehydrated kiwifruit slices. Kiwifruits were dehydrated implementing four different sucrose concentrations, at three processing temperatures and during four osmotic time periods. A multilayer neural network was developed by using the operation conditions as inputs to estimate water loss, solid gain, and color changes. It was found that artificial neural network with 16 neurons in hidden layer gives the best fitting with the experimental data, which made it possible to predict solid gain, water loss, and color changes with acceptable mean-squared errors (1.005, 2.312, and 2.137, respectively). These results show that artificial neural network could potentially be used to estimate mass transfer kinetics and color changes of dehydrated kiwifruit.     

Experimental use of a gas sensor-based instrument for differentiation of Escherichia coli O157:H7 from non-O157:H7 Escherichia coli field isolates

The rapid and economical detection of human pathogens in animal and food production systems would enhance food safety efforts. An instrument based on gas sensors coupled with an artificial neural network (ANN) was developed for the detection of and differentiation between laboratory isolates of Escherichia coli O157:H7 and non-O157:H7 E. coli. The purpose of this study was to use field isolates of E. coli to further evaluate the sensor system. This gas sensor-based, computer-controlled detection system was used to monitor gas emissions from 12 isolates of E. coli O157:H7 and 8 non-O157:H7 E. coli isolates. A standard concentration of each isolate was grown in 10 ml of nutrient broth at 37 degrees C for 16 h, and gas sampling was carried out every 5 min. Readings were continuously plotted to generate gas signatures. A back-propagation ANN algorithm was used to interpret the gas patterns. By analysis of the response of the ANN, the sensitivity and specificity of the instrument were calculated. Detectable differences between the gas signatures of the E. coli O157:H7 isolates and the non-O157:H7 isolates were observed. The instruments degree of sensitivity was high for E. coli O157:H7 isolates, but a lower degree of accuracy was observed for non-O157:H7 isolates because of increased strain variation. The sensitivity of the detection system was improved by the normalization of the data generated from the gas sensors. Because of its ability to detect differences in gas patterns, this instrument has a broad range of potential food safety applications.     

A neuro-computing approach for modeling of residence time distribution (RTD) of carrot cubes in a vertical scraped surface heat exchanger (SSHE)

A neuro-computing approach was used for modeling two residence time distribution (RTD) functions — the time-specific (E-type distribution) and the cumulative particle concentration function (F-type distribution) — of carrot cubes in starch solutions in a vertical scraped surface heat exchanger (SSHE) of a pilot scale aseptic processing system. Experimental data obtained for E (t) and F(t) under various test conditions were used for both training and evaluation. Multi-layered artificial neural network (ANN) models with four input and two output neurons were trained. The network was optimized by the varying number of hidden layers, number of neurons in each hidden layer and learning runs, and a combination of learning rule and transfer functions, using a back-propagation algorithm. The trained ANN model was validated by a set of independent experimental data. The ANN models were also compared with conventional models developed based on multiple regression techniques. The results indicated that there was better agreement between experimental and ANN model predicted values for both E (t) and F (t) functions. The average modeling errors associated with ANN were 5.7 and 3.0%, respectively, for E(t) and F(t), while they were 15.5 and 12.3%, respectively, with the multiple regression models.     

A novel technique for rapid evaluation of fish freshness using colorimetric sensor array

An olfaction system based on colorimetric sensor array was developed for fish freshness evaluation. Nine chemically responsive dyes were selected according to their sensitivity to volatile compounds typically occurring during spoilage in fish. The colorimetric sensor array was made by printing selected dyes on a reverse phase silica gel plate. Detection on fish of chub was made every 24 h within seven days. A color change profile for each sample was obtained by differentiating the images of the sensor array before and after exposure to the odor of sample. The digital data representing the color change profiles for the fish samples were analyzed using principal component analysis. The chub samples were classified into three freshness groups using a radial basis function neural network, with an overall classification accuracy of 87.5%. This research suggests that the system is useful for quality evaluation of fish and perhaps other food containing high protein.     

Modelling of solid-phase tea waste extraction for the removal of manganese from food samples by using artificial neural network approach

In this study, a three-layer artificial neural network (ANN) model was employed to develop prediction model for removal of manganese from food samples using tea waste as a low cost adsorbent. After removal of manganese from food samples with acetic acid (5 mol L⁻¹), manganese was adsorbed to a small amount of tea waste, desorbed with nitric acid as a eluent solvent, and determined by flame atomic absorption spectrometry. The input parameters chosen of the model was pH, amount of tea waste, extraction time and eluent concentration. After backpropagation (BP) training, the ANN model was able to predict extraction efficiency of manganese with a tangent sigmoid transfer function at hidden layer and a linear transfer function at output layer. Under the optimum conditions, the detection limit was 0.6 ng g⁻¹. The method was applied to the separation, pre-concentration and determination of manganese in food samples and one reference material.     

基于量子卷积神经网络算法的微小零件识别

设计了量子卷积神经网络表示层、隐藏层神经元和输出层神经元模型；采用修正线性激活函数ReLu作为激活函数，并通过训练误差函数优化量子旋转角度和神经连接权值。8种微小零件的仿真试验表明，量子卷积神经网络算法的识别准确率较高，耗时少且识别效果较好。     

Characterization of Volatile Organic Compounds of Vinegars with Novel Electronic Nose System Combined with Multivariate Analysis

A novel electronic nose system (also called artificial olfaction system) based on colorimetric sensor array was developed for characterization and identification of the volatile organic compounds (VOCs) of vinegars fermented from different raw materials. Fifteen chemo-responsive dyes including nine metalloporphyrins and six pH indicators were selected according to their sensitivity to volatile compounds from vinegar samples. The colorimetric sensor array was made by printing selected chemo-responsive dyes on a silica gel plate. A color change profile for each sample was obtained by differentiating the images of the colorimetric sensor array before and after exposure to the odorant of vinegar sample. The digital data (i.e., red, green, and blue components of the image) representing the color change profiles for the vinegar samples were analyzed. Genetic algorithm partial least squares was employed to select sensitive image digital variable to build a calibration model. Several methods (i.e., linear discrimination analysis, LDA; partial least square discrimination analysis; artificial neural network) were also used comparatively for classification, the result was evaluated by the % correct identification of samples. The optimal model was achieved by LDA model with 14 image digital variables used, and all the vinegar samples were correctly identified both in training and testing sets. This research suggests that the system shows significant potential in vinegar VOCs characterization and discrimination.     

饮用水中挥发性有机物色谱保留时间的神经网络研究

研究饮用水中挥发性有机物的色谱保留时间与分子结构之间的定量结构-保留相关关系,基于分子结构和邻接矩阵,计算了56?个挥发性有机物的分子连接性指数、形状指数、电性拓扑状态指数和电性距离矢量,建立挥发性有机物的保留时间与0X、1X、2X、3X、K1、E43和M91指数的定量结构-保留相关性（quantitative structure-retention relationship,QSRR）模型。将这7 种结构参数作为BP（back propagation）人工神经网络法的输入变量,采用7∶4∶1的神经网络结构,建立了令人满意的QSRR预测模型,模型的总相关系数r总为0.999 1,利用本模型计算得到色谱保留时间的预测值与相关实验值相对平均误差2.17%,吻合度较为理想。结果表明,饮用水中挥发性有机物的色谱保留时间与7 种结构参数之间具有良好的非线性关系,本研究对快速评价水质对生态环境的影响具有参考价值。     

Evaluation of chicken freshness using a low-cost colorimetric sensor array with AdaBoost–OLDA classification algorithm

This paper attempted to evaluate chicken freshness using a low-cost colorimetric sensor array with the help of a classification algorithm. We fabricated a novel and low-cost colorimetric sensors array, with a specific colorific fingerprint to volatile compounds, using printing chemically responsive dyes on a C2 reverse silica-gel flat plate. In addition, we proposed a novel classification algorithm for sensors data classification – orthogonal linear discriminant analysis (OLDA) and adaptive boosting (AdaBoost) algorithm, namely AdaBoost–OLDA. And we compared it with two classical classification algorithms – linear discriminant analysis (LDA) and back propagation artificial neural network (BP-ANN). Experimental results showed classification results by AdaBoost–OLDA algorithm is superior to BP-ANN and LDA algorithms, the classification results by which are both 100% in the calibration and prediction sets. This study sufficiently demonstrated that the colorimetric sensors array with a classification algorithm has a high potential in evaluating chicken freshness, and AdaBoost–OLDA algorithm has a strong performance in solution to a complex data classification.     

Effect of postmortem aging time on flavor profile of stewed pork rib broth

The objective of this study was to investigate changes in flavor components in broth prepared by pork ribs that were aged for 1 d, 3 d, and 7 d. The contents of free amino acids (FAAs), nucleic acid-related compounds, organic acids, and volatile compounds in broth were measured. The overall taste and aroma profiles were evaluated by electronic tongue, electronic nose, and sensory panelists. The results showed that the FAAs and succinic acid contents increased, while the 5?-guanosine monophosphate, 5?-inosine monophosphate, and 5?-adenosine monophosphate contents decreased as the aging time increased. These changes led to the taste characteristics of broth being more savory. However, the results of gas chromatography-mass spectrometry, electronic nose, and sensory test all showed that there were no significant differences in aroma among the samples, where the main volatile compounds of broth were aldehydes, including hexanal, nonanal, octanal, heptanal, (Z)-2-heptanal, and (E)-2-decenal. Hence, postmortem aging affected the taste rather than the aroma of pork rib broth, and extending aging time can improve the taste of broth.     

基于BP神经网络的电子鼻羊奶贮藏时间的预测

利用电子鼻PEN3系统判定室温和冷藏条件下羊奶的贮藏时间。通过电子鼻系统采集羊奶室温贮藏及冷藏期间挥发性成分的响应值,并采用PCA(主成分分析法)、LDA(线性判别分析法)和LM算法优化的BP神经网络(LM-BP)、遗传算法优化的神经网络(GANN)、4层BP神经网络进行模式识别。结果表明PCA和LDA均可区分室温贮藏及冷藏1～6d的生鲜羊奶,LDA方法还可以明显体现出羊奶贮藏期间挥发性成分的变化趋势,并且与羊奶酸度的变化有很好的一致性。采用LM-BP神经网络、GANN神经网络和4层神经网络均能较好地预测不同贮藏时间的羊奶,其中4层神经网络的预测正确率高于LM-BP神经网络和GANN神经网络。     

基于电子鼻和改进无监督鉴别投影算法的大闸蟹新鲜度识别方法

通过自制电子鼻系统采集活体大闸蟹的气味信息,采用流行学习算法对大闸蟹样本的多维特征响应进行降维,提取样本的低维特征向量,再利用反向传播神经网络实现对大闸蟹新鲜度的识别,并与理化指标挥发性盐基氮进行比较。结果表明,基于该算法的大闸蟹新鲜度识别的准确度可达到98.1%,且依据电子鼻技术与依据理化指标判断结果基本一致,因此采用电子鼻技术的大闸蟹新鲜度无损识别方法是可行的。     

Artificial neural network modeling and optimization of ultrahigh pressure extraction of green tea polyphenols

In this study, the ultrahigh pressure extraction of green tea polyphenols was modeled and optimized by a three-layer artificial neural network. A feed-forward neural network trained with an error back-propagation algorithm was used to evaluate the effects of pressure, liquid/solid ratio and ethanol concentration on the total phenolic content of green tea extracts. The neural network coupled with genetic algorithms was also used to optimize the conditions needed to obtain the highest yield of tea polyphenols. The obtained optimal architecture of artificial neural network model involved a feed-forward neural network with three input neurons, one hidden layer with eight neurons and one output layer including single neuron. The trained network gave the minimum value in the MSE of 0.03 and the maximum value in the R² of 0.9571, which implied a good agreement between the predicted value and the actual value, and confirmed a good generalization of the network. Based on the combination of neural network and genetic algorithms, the optimum extraction conditions for the highest yield of green tea polyphenols were determined as follows: 498.8 MPa for pressure, 20.8 mL/g for liquid/solid ratio and 53.6% for ethanol concentration. The total phenolic content of the actual measurement under the optimum predicated extraction conditions was 582.4 ± 0.63 mg/g DW, which was well matched with the predicted value (597.2 mg/g DW). This suggests that the artificial neural network model described in this work is an efficient quantitative tool to predict the extraction efficiency of green tea polyphenols.