Rapid method for prediction of Escherichia coli numbers using an electronic sensor array and an artificial neural network

An electronic sensor array with 12 nonspecific metal oxide sensors was evaluated for its ability to monitor volatile compounds in super broth alone and in super broth inoculated with Escherichia coli (ATCC 25922) at 37 degrees C for 2 to 12 h. Using discriminant function analysis, it was possible to differentiate super broth alone from that containing E. coli when cell numbers were 10(5) CFU or more. There was a good agreement between the volatile profiles from the electronic sensor array and a gas chromatography-mass spectrometer method. The potential to predict the number of E. coli and the concentration of specific metabolic compounds was investigated using an artificial neural network (ANN). The artificial neural network was composed of 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 = 0.999) between actual and predicted data.     

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.     

Use of digital aroma technology and SPME GC-MS to compare volatile compounds produced by bacteria isolated from processed poultry

Digital aroma technology, solid-phase micro-extraction (SPME) and gas chromatographic mass spectral (GC-MS) analysis of the headspace volatile organic compounds were used to compare bacterial species important for food safety and common to biofilms in the poultry processing environment. The instrument for digital aroma technology, called the electronic nose, measured changes in resistance of polymer sensors caused by volatile gases from the headspace of samples. Graphical output by the Sammon mapping technique produced patterns of differences or similarities among the samples. Artificial neural network software was used to model groups of samples and classify subsequent unknowns. Compounds isolated from the headspace of sealed cultures using polydimethylsiloxane SPME fibres and identified by GC-MS analyses were predominantly alcohols and indole. These qualitative profiles were repetitive for specific organisms in relation to purity and repeatability of the cultures, differed by species and were used as objective standards to compare the graphical outputs of the electronic nose. © 1998 Society of Chemical Industry.     

Behavior of enterohemorrhagic Escherichia coli O157:H7 on alfalfa sprouts during the sprouting process as influenced by treatments with various chemicals.

The behavior of Escherichia coli O157:H7 on alfalfa seeds subjected to conditions similar to those used commercially to grow and market sprouts as it is affected by applications of NaOCl, Ca(OCl)2, acidified NaClO2, acidified ClO2, Na3PO4, Vegi-Clean, Tsunami, Vortexx, or H2O2 at various stages of the sprouting process was determined. Application of 2,000 ppm of NaOCl, 200 and 2,000 ppm of Ca(OCl)2, 500 ppm of acidified ClO2, 10,000 ppm of Vegi-Clean, 80 ppm of Tsunami, or 40 and 80 ppm of Vortexx to germinated seeds significantly reduced the population of E. coli O157:H7. With the exception of acidified NaOCl2 at 1,200 ppm, spray applications of these chemicals did not significantly reduce populations or control the growth of E. coli O157:H7 on alfalfa sprouts during the sprouting process. Populations of E. coli on alfalfa sprouts peaked at 6 to 7 log10 CFU/g 48 h after initiation of the sprouting process and remained stable despite further spraying with chemicals. The population of E. coli O157:H7 on sprouts as they entered cold storage at 9 +/- 2 degrees C remained essentially unchanged for up to 6 days. None of the chemical treatments evaluated was able to eliminate or satisfactorily reduce E. coli O157:H7 on alfalfa seeds and sprouts. Observations on the ability of E. coli O157:H7 to grow during production of alfalfa sprouts not subjected to chemical treatments are similar to those from a previous study in our laboratory on the behavior of Salmonella Stanley. Our results do not reveal a chemical treatment method to eliminate the pathogen from alfalfa sprouts. We have demonstrated that currently recommended procedures for sanitizing alfalfa seeds fail to eliminate E. coli O157:H7 and that the pathogen can grow to populations exceeding 7 1og10 CFU/g of sprouts produced using techniques not dissimilar to those used in the sprout industry.     

Inactivation of Escherichia coli O157:H7 and Salmonella by gamma irradiation of alfalfa seed intended for production of food sprouts

Inonizing irradiation was determined to be a suitable method for the inactivation of Salmonella and Escherichia coli O157:H7 on alfalfa seed to be used in the production of food sprouts. The radiation D (dose resulting in a 90% reduction of viable CFU) values for the inactivation of Salmonella and E. coli O157:H7 on alfalfa seeds were higher than the D-values for their inactivation on meat or poultry. The average D-value for the inactivation of Salmonella on alfalfa seeds was 0.97 +/- 0.03 kGy; the D-values for cocktails of meat isolates and for vegetable-associated isolates were not significantly different. The D-values for nonoutbreak and outbreak isolates of E. coli O157:H7 on alfalfa seeds were 0.55 +/- 0.01 and 0.60 +/- 0.01 kGy, respectively. It was determined that the relatively high D-values were not due to the low moisture content or the low water activity of the seed. The D-values for Salmonella on alfalfa seeds from two different sources did not differ significantly, even though there were significant differences in seed size and water activity. The increased moisture content of the seed after artificial inoculation did not significantly alter the D-value for the inactivation of Salmonella. The results of this study demonstrate that 3.3- and 2-log inactivations can be achieved with a 2-kGy dose of ionizing radiation, which will permit satisfactory commercial yields of sprouts from alfalfa seed contaminated with E. coli O157:H7 and Salmonella, respectively.     

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.     

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.     

Artificial neural network approach to simultaneously predict shelf life of two varieties of packaged rice snacks

Actual storage shelf life test by storing a packaged product under typical storage conditions is costly and time consuming. A new approach using an artificial neural network (ANN) algorithm for shelf life prediction of two varieties of moisture-sensitive rice snacks packaged in polyethylene and polypropylene bags and stored at various storage conditions was established. The ANN used to predict the shelf life was based on multilayer perceptron with back propagation algorithm. The ANN algorithm employed the data of product characteristics, package properties and storage conditions. The neural network comprised an input, one hidden and one output layers. The network was trained using Bayesian regularisation. The performance of ANN was measured using regression coefficient ( R ² = 0.23–0.28) and root mean square error (RMSE = 0.96–0.99). The ANN-predicted shelf lives agreed very well with actual shelf life data. ANN could be used as an alternative method for shelf life prediction of moisture-sensitive food products as well as product/package optimisation.     

Survey of retail alfalfa sprouts and mushrooms for the presence of Escherichia coil O157:H7, Salmonella,and Listeria with BAX,and evaluation of this polymerase chain reaction-based system with experimentally contaminated samples

BAX, a polymerase chain reaction (PCR)-based pathogen detection system, was used to survey retail sprouts and mushrooms for contamination with Escherichia coli O157:H7, Salmonella, Listeria spp., and Listeria monocytogenes. No Salmonella or E. coli O157:H7 was detected in the 202 mushroom and 206 alfalfa sprout samples screened. L. monocytogenes was detected in one sprout sample, and seven additional sprout samples tested positive for the genus Listeria. BAX also detected Listeria species in 17 of the mushroom samples. Only 6 of 850 PCR assays (0.7%) failed to amplify control DNA, and therefore reagent failures and the inhibition of PCR by plant compounds were rare. The sensitivity of the detection system was evaluated by assaying samples inoculated with 10 CFU of each of the pathogens. One hundred seventy-two alfalfa sprout samples were inoculated with E. coli O157:H7, and two sets of 130 samples were experimentally contaminated with Salmonella Enteritidis and L. monocytogenes. The frequency of detection depended on the protocols used for inoculation and culturing. Inoculation of samples with approximately 10 CFU from frozen stocks yielded detection rates of 87.5 and 94.5% for L. monocylogenes and Salmonella Enteritidis, respectively, in mushrooms. The corresponding rates for alfalfa sprouts were 94.5 and 76.3%. The E. coli O157:H7 detection rate was 100% for mushrooms but only 48.6% for sprouts when standard BAX culture protocols were used. The substitution of an overnight incubation in modified E. coli medium for the 3-h brain heart infusion incubation increased the rate of E. coli O157:H7 detection to 75% for experimentally contaminated sprouts. The detection rate was 100% when E. coli O157:H7 cells from a fresh overnight culture were used for the inoculation. Test sensitivity is therefore influenced by the type of produce involved and is probably related to the growth of pathogens in the resuscitation and enrichment media.     

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...     

Chemical and irradiation treatments for killing Escherichia coli O157:H7 on alfalfa,radish, and mung bean seeds

In this study, the effectiveness of dry-heat treatment in combination with chemical treatments (electrolyzed oxidizing [EO] water, califresh-S, 200 ppm of active chlorinated water) with and without sonication in eliminating Escherichia coli O157:H7 on laboratory-inoculated alfalfa, radish, and mung bean seeds was compared with that of dry-heat treatment in combination with irradiation treatment. The treatment of mung bean seeds with EO water in combination with sonication followed by a rinse with sterile distilled water resulted in reductions of approximately 4.0 log10 CFU of E. coli O157:H7 per g. whereas reductions of ca. 1.52 and 2.64 log10 CFU/g were obtained for radish and alfalfa seeds. The maximum reduction (3.70 log10 CFU/g) for mung bean seeds was achieved by treatment with califresh-S and chlorinated water (200 ppm) in combination with sonication and a rinse. The combination of dry heat, hot EO water treatment, and sonication was able to eliminate pathogen populations on mung bean seeds but was unable to eliminate the pathogen on radish and alfalfa seeds. Other chemical treatments used were effective in greatly reducing pathogen populations on radish and alfalfa seeds without compromising the quality of the sprouts, but these treatments did not result in the elimination of pathogens from radish and alfalfa seeds. Moreover, a combination of dry-heat and irradiation treatments was effective in eliminating E. coli O157:H7 on laboratory-inoculated alfalfa, radish, and mung bean seeds. An irradiation dose of 2.0 kGy in combination with dry heat eliminated E. coli O157:H7 completely from alfalfa and mung bean seeds, whereas a 2.5-kGy dose of irradiation was required to eliminate the pathogen completely from radish seeds. Dry heat in combination with irradiation doses of up to 2.0 kGy did not unacceptably decrease the germination percentage for alfalfa seeds or the length of alfalfa sprouts but did decrease the lengths of radish and mung bean sprouts.     

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.     

基于傅里叶近红外光谱和电子鼻技术的苹果霉心病无损检测

为研究傅里叶近红外光谱技术(Fourier transform near infrared spectroscopy,FT-NIRS)和电子鼻技术分别结合化学计量学方法对苹果霉心病的判别效果,以“红富士”霉心病苹果和健康苹果为试材,利用近红外光谱技术,基于主成分分析建立Fisher判别和多层感知器(multi-layer perceptron,MLP)神经网络模型;同时利用电子鼻技术分别结合Fisher判别、MLP神经网络和径向基函数神经网络3种化学计量学的方法建立判别模型。根据建模集和验证集的预测准确率综合考虑,基于主成分分析建立的MLP神经网络模型和电子鼻结合MLP神经网络模型对苹果霉心病的判别效果最好,验证集中的正确判别率分别达到87.7%和86.2%。说明电子鼻和近红外光谱技术均可以较好地判别苹果霉心病。     

Reduction of Salmonella spp. and strains of Escherichia coli O157:H7 by gamma radiation of inoculated sprouts

There have been several recent outbreaks of salmonellosis and infections with Escherichia coli O157:H7 linked to the consumption of raw sprouts. Use of ionizing radiation was investigated as a means to reduce or to totally inactivate these pathogens, if present, on the sprouts. The radiation D value, which is the amount of irradiation in kilograys for a 1-log reduction in cell numbers, for these pathogens was established using a minimum of five doses at 19 +/- 1 degrees C. Before inoculation, the sprouts were irradiated to 6 kGy to remove the background microflora. The sprouts were inoculated either with Salmonella spp. cocktails made with either meat or vegetable isolates or with E. coli O157:H7 cocktails made with either meat or vegetable isolates. The radiation D values for the Salmonella spp. cocktails on sprouts were 0.54 and 0.46 kGy, respectively, for the meat and vegetable isolates. The radiation D values for the E. coli O157:H7 cocktails on sprouts were 0.34 and 0.30 kGy, respectively, for the meat and vegetable isolates. Salmonella was not detected by enrichment culture on sprouts grown from alfalfa seeds naturally contaminated with Salmonella after the sprouts were irradiated to a dose of 0.5 kGy or greater. Ionizing radiation is a process that can be used to reduce the population of pathogens on sprouts.     

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.     

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。     

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。     

Thermal inactivation of Salmonella and Escherichia coli O157:H7 on alfalfa seeds

Alfalfa seeds inoculated with five strains of Salmonella or Escherichia coli O157:H7 were subjected to dry heat at 55 degrees C for up to 8 days. Five-log reductions in Salmonella or E. coli O157:H7 on seeds were observed. No pathogens were detected on the sprouted seeds, which were initially inoculated with ca. 2 log CFU/g of Salmonella or more than 8 log CFU/g of E. coli O157:H7. The percentages of germination of the alfalfa seeds did not significantly decrease after 6 days of heating at 55 degrees C. These results showed that heat treatment of alfalfa seeds at 55 degrees C for up to 6 days was effective in enhancing the safety of alfalfa sprouts without affecting germination significantly.     

Factors influencing the detection and enumeration of Escherichia coli O157:H7 on alfalfa seeds.

Isolating Escherichia coli O157:H7 from batches of alfalfa seeds used to produce sprouts implicated in human illness has been difficult, perhaps due to nonhomogenous and very low-level contamination and inaccessibility of the pathogen entrapped in protected areas of the seed coat. We evaluated the effectiveness of various treatments in releasing E. coli O157:H7 from seeds. The influence of homogenization (blending or stomaching for 1 or 2 min), rinsing method (shaking for 5 min), soaking time (0. 1, 3, 6, or 15 h), soaking temperature (4 or 21 degrees C), and the addition of surfactants (0.1%, 0.5%, or 1.0% Tween 80 or Span 20) to rinse water was determined. Blending or stomaching for 1 or 2 min, and soaking for 1 h or longer at 4 or 21 degrees C, respectively, resulted in maximum release of E. coli O157:H7 from seeds. Soaking seeds at 37 degrees C for 15 h increased cell populations of E. coli O157:H7 by approximately 3.6 log10 CFU/g, likely due to bacterial growth. The maximum number of cells released from seeds by rinse water containing 1.0% Span 20 was at 21 degrees C, whereas at 37 degrees C, 0.1% or 0.5% Tween 80 was more effective. Detection of E. coli O157:H7 on seeds stored at 37 degrees C for up to 13 weeks and on sprouts derived from these seeds was compared. E. coli O157:H7 inoculated on seeds at 2.0 log10 CFU/g was detected after storage of seeds for up to 8 weeks at 37 degrees C and in sprouts produced from the seeds. The pathogen was not detected on seeds stored for 13 weeks at 37 degrees C and was not isolated from sprouts produced from these seeds. Identifying seed treatment methods that enhance removal of E. coli O157:H7 from alfalfa seeds can aid the isolation and enumeration of the pathogen on seeds. With a combination of optimal conditions for detecting the pathogen, i.e. soaking seeds for 1 h and pummeling seeds for 1 min, an enrichment step in modified tryptic soy broth (TSB), and the use of immunomagnetic beads for separation of E. coli O157:H7 cells, E. coli O157:H7 was detected in alfalfa seeds incubated at 37 degrees C for up to 8 weeks as effectively as in sprouts produced from the seeds.