基于反向传播神经网络和高光谱成像的芒果可溶性固形物含量检测

目的 比较反向传播神经网络(backpropagation algorithm neural network, BPNN)模型与偏最小二乘回归(partial least squares regression, PLSR)模型在预测芒果可溶性固形物含量(soluble solids content, SSC)方面的性能评估。方法 使用高光谱成像仪和全自动折光仪采集芒果的近红外高光谱及SSC数据建立两种预测模型, 通过采用多元散射校正(multiplicative scatter correction, MSC)进行光谱预处理, 利用遗传算法(genetic algorithm, GA)、区间变量迭代空间收缩算法(interval variable iterative space shrinkage algorithms, IVISSA)和变量组合群体分析算法(variable combination population analysis, VCPA)提取特征波长变量, 通过比较不同特征波长提取方法进一步优化对比预测模型。结果 与PLSR模型相比, BPNN模型在预测SSC方面更为有效。而在IVISSA特征波长变量提取后优化的BPNN模型预测能力最佳, 预测集判定系数 、均方根误差(root mean square error of prediction, RMSEP)、残差预测偏差(residual prediction deviation, RPD)分别为0.8641、0.3924和2.7127。结论 该模型可快速、准确地检测芒果的SSC, 并证明可见光-近红外高光谱成像与反向传播神经网络模型相结合有望预测芒果的SSC, 为开发在线芒果SSC无损检测系统奠定基础。     

基于近红外光谱技术快速检测小龙虾中的生物胺

目的 建立近红外光谱法快速检测小龙虾中总生物胺含量的方法。方法 利用近红外光谱仪采集154个不同新鲜程度小龙虾样品的近红外光谱, 使用高效液相色谱技术检测对应样品总生物胺含量; 使用KS(Kennard-Stone)算法将103个样品作为训练集, 51个样品作为预测集。采用多元散射校正(multiplicative scatter correction, MSC)、标准正态变换(standard normal variate, SNV)、小波变换(wavelet transform, WT)和1阶导数(1st)分别对样品的光谱进行处理, 利用训练集样品的光谱和生物浓度建立偏最小二乘回归(partial least squares regression, PLSR)模型, 使用竞争性自适应重加权算法(competitive adaptive reweighted sampling, CARS)进一步选择波长, 对模型进行优化。结果 经过小波变换处理之后的光谱所建立的PLSR模型具有较好的预测结果, CARS方法可以进一步提高模型的预测和解释能力, 预测集生物胺的预测均方根误差(root mean square error of prediction, RMSEP)值和决定系数(r2)分别可达55.74和0.92。结论 基于近红外光谱分析技术快速检测小龙虾总生物胺含量是可行的, 优化后的PLSR模型可以用于评价小龙虾总生物胺含量。     

近红外漫反射无损检测赣南脐橙中可溶性固形物和总酸

目的:利用近红外漫反射无损检测技术对赣南脐橙可溶性固形物和总酸含量进行相关研究。方法:通过自行设计的NIR光谱系统测定150个赣南脐橙可溶性固形物和总酸。120个赣南脐橙样品用来建模,其余30个用来验证模型的性能。采集完整赣南脐橙的近红外漫反射光谱(350～1800nm),光谱经移动窗口平滑处理、一阶微分和二阶微分预处理后,再分别采用主成分回归(PCR)和偏最小二乘法(PLS),建立赣南脐橙可溶性固形物和总酸含量的定量预测数学模型。结果:采用一阶微分结合偏最小二乘法所建模型的预测效果较好,可溶性固形物和总酸含量定量预测数学模型的相关系数分别为0.9263和0.9562,均方根误差分别为0.4102°Brix和0.018%。结论:近红外漫反射光谱作为一种无损的检测方法,可用于评价赣南脐橙的可溶性固形物和总酸含量。     

基于粒子群优化算法优化反向传播神经网络构建冷藏草鱼新鲜度的近红外光谱预测模型

目的 构建基于各种机器学习算法结合近红外光谱的模型，从而确定出更准确预测冷藏草鱼新鲜度的方法。方法 采集连续冷藏6 d的草鱼片的新鲜度指标, 并进行方差分析。选择受冷藏天数影响最大的指标: 总挥发性盐基氮(Total volatile basic nitrogen, TVB-N)进行定量预测。运用x-y距离结合的样本划分(sample set partitioning based on joint x-y distance, SPXY)方法进行数据集的划分, 并采用正交信号校正法(orthogonal signal correction, OSC)、Savitzky-Golay (SG)、一阶导数及其组合算法进行光谱预处理。再运用竞争性自适应重加权采样(competitive adaptive reweighted sampling, CARS)、连续投影算法(successive projections algorithm, SPA)、主成分分析(principal component analysis, PCA)对光谱变量进行选择和降维。最后结合偏最小二乘回归(partial least squares regression, PLSR)、反向传播神经网络(back propagation neural network, BPNN)和粒子群优化算法(particle swarm optimization, PSO)优化BP神经网络(PSO-BP)建立草鱼(Ctenopharyngodon idella)片新鲜度定量预测模型。结果 各线性和非线性模型均得到了良好的预测效果, 预测集相关系数均超过了0.95。PLSR表现较为稳定, BP神经网络虽提高了校正集预测性能, 但是预测集性能不如PLSR。PSO-BP既保证了校正集预测性能, 也提高了预测集性能。基于OSC+D1预处理和CARS变量选择后的PSO-BP模型性能最优(R2P=0.987, 预测集的均方根误差为0.108, 相对分析误差为7.778)。结论 基于PSO-BP算法和近红外光谱结合的定量预测模型, 可以很好的预测冷藏鱼肉的新鲜度指标。     

基于近红外光谱技术快速检测文山三七品质指标

目的 建立一种基于近红外光谱技术快速测定文山三七4种品质指标的方法。方法 采用GB/T 19086—2008《地理标志产品-文山三七》中规定的方法测定文山三七的水分、总灰分、酸不溶性灰分以及皂苷的含量, 建立标杆数据。采集文山三七样品的近红外光谱数据, 利用偏最小二乘回归(partial least squares regression, PLSR)方法建立模型。通过优化光谱预处理方法和变量筛选方法进一步提升模型的预测能力。结果 文山三七水分、总灰分、酸不溶性灰分以及皂苷的校正集相关系数(Rc)分别为0.9891、0.9703、0.9803、0.9462, 预测集相关系数(Rp)分别为0.9867、0.9678、0.9691、0.8122, 预测集均方根误差(root mean square error of prediction, RMSEP)分别为0.1875、0.1405、0.0662、0.6574, 性能偏差比(ratio of performance to deviation, RPD)分别为3.814、3.2300、3.9183、1.7641。结论 本方法可以快速、准确地测定文山三七中4种关键品质指标, 为文山三七的质量控制提供了一种快速有效的检测方法。     

基于高光谱成像技术无损检测芒果轻微损伤

目的 使用高光谱成像技术实现对芒果轻微损伤的无损识别。方法 在可见光-近红外波长范围内采集完好芒果和损伤芒果的高光谱图像, 并提取相应的感兴趣区域(regions of interest, ROI)获得样本高光谱数据。经过多种预处理方法比较, 选择光谱预处理方法。使用竞争性自适应重加权算法(competitive adaptive reweighted sampling, CARS)和连续投影算法(successive projections algorithm, SPA)分别对预处理后的光谱提取特征波长, 并分别建立了多元线型回归(multiple linear regression, MLR)模型和偏最小二乘回归(partial least squares regression, PLSR)模型。结果 选择多元散射校正(multiplicative scatter correction, MSC)作为光谱预处理方法。针对芒果轻微损伤识别, CARS-MLR模型识别效果最好, 其校正集相关系数为0.881, 预测集相关系数为0.821, 校正集均方根误差(calibration set root mean square error, RMSEC)为0.146, 预测集均方根误差(prediction set root mean square error, RMSEP)为0.236, 准确率为97.14%。结论 利用高光谱成像技术可以实现对芒果表面轻微损伤进行有效鉴别。     

基于微型近红外光谱仪的油菜籽含油率模型参数优化研究

为实现油菜籽含油率快速无损检测,采用微型近红外光谱仪,结合竞争性自适应重加权(CARS)、遗传算法(GA)、连续投影算法(SPA)、无信息变量消除法(UVE)、向后区间偏最小二乘法(BIPLS)、联合区间偏最小二乘法(SIPLS)等方法优选油菜籽含油率近红外光谱特征波长,建立偏最小二乘回归(PLSR)和最小二乘支持向量机(LS-SVM)定量分析模型,同时对LS-SVM模型参数进行优化。研究表明,对PLSR模型,BIPLS+GA优选的26个特征波长建模效果最好,其预测相关系数(Rp)和预测均方根误差(RMSEP)分别为0.9330和0.0075,对LS-SVM模型,SIPLS+GA优选的13个特征波长建模效果最好,预测相关系数(Rp)和预测均方根误差(RMSEP)分别0.9192和0.0055。证明了波长优选和参数优化可有效简化油菜籽含油率近红外光谱定量分析模型,提高模型预测精度和稳定性,为进一步拓展微型近红外光谱仪的应用提供技术参考。     

近红外特征光谱定量检测羊肉卷中猪肉掺假比例

利用近红外漫反射光谱技术结合化学计量学方法对解冻掺假羊肉卷,进行猪肉掺假比例的定量检测研究。按照不同肥肉占比和不同猪肉掺假比例,制备324?个样品,并利用近红外光谱仪采集其光谱数据。对原始数据进行SG（Savitzky-Golay）平滑、SG一阶导、SG二阶导、多元散射校正、中心化、标准正态变量校正等预处理,并利用偏最小二乘回归（partial least square regression,PLSR）进行建模分析,其中SG平滑结合一阶求导预处理的模型预测效果最优。针对最佳预处理光谱采用竞争性自适应加权采样（competitive adaptive reweighted sampling,CARS）算法进行波长筛选,并建立特征波长PLSR模型,模型预测效果得到提高。其中,校正集和验证集决定系数分别为0.983?6和0.972?5,校正集和验证集的均方根误差分别为0.043?7和0.057?7,范围误差比为7.62。应用该CARS-PLSR模型对检验集进行预测,真实值与预测值的相关系数为0.913?8,结果表明采用近红外光谱分析技术可以实现不同肥肉占比羊肉卷中猪肉掺假比例的定量检测。     

基于支持向量机的食醋总酸近红外光谱建模

为了得到稳定可靠的食醋总酸光谱模型,以不同产地、不同种类的95个食醋样品为研究对象,应用基于统计学原理的最小二乘支持向量机(LS-SVM)对食醋总酸含量进行光谱分析.对预处理后的光谱进行主成分分析(PCA),以主成分信号作为输入变量建立食醋总酸含量的近红外光谱模型,并与偏最小二乘法(PLS)和向后区间偏最小二乘法(biPLS)模型进行比较.结果表明,LS-SVM模型中的校正集中的相关系数(rc)和交互验证均方根误差(RMSECV)分别达到0.9614和0.2192,预测集相关系数(rp)和预测均方根误差(RMSEP)分别达到和0.919和0.3226,均优于PLS和biPLS模型.研究表明,近红外光谱与食醋总酸含量呈非线性关系,采用LS-SVM建立的模型预测性能更好,精度更高.     

融合近红外光谱和颜色参数的草莓可溶性固形物含量定量分析模型构建

草莓可溶性固形物(soluble solids content,SSC)含量是评价草莓内部品质的关键指标。为了实现对该指标的快速、无损评估,基于近红外光谱技术,构建了线性偏最小二乘(partial least squares,PLS)和非线性最小二乘支持向量机(least squares support vector machine,LS-SVM)模型,联合蒙特卡罗无信息变量消除和连续投影算法(Monte-Carlo uninformative variable elimination,successive projections algorithm,MC-UVE-SPA)从原始光谱4254个变量中提取了27个有效变量,并构建了基于有效变量的定量分析模型。同时,考虑到草莓表面颜色的影响,基于草莓RGB图像各分量获取了颜色特征参数,进一步融合光谱和颜色特征构建了多参数融合PLS和LS-SVM模型。基于相同的校正集和预测集,比较了所有模型对草莓内部SSC的预测性能。结果表明,MC-UVESPA是一种有效的草莓光谱变量选择算法,且多参数融合非线性LS-SVM模型是草莓内部SSC定量预测的最优模型。针对预测集样本,该模型相关系数RP和预测均方根误差(root mean square error of prediction,RMSEP)分别为0.9885和0.1532。该研究为基于近红外光谱技术的草莓可溶性固形物含量检测便携式仪器和在线检测设备研发奠定了基础。     

Textural Properties of Cold-set Gels Induced from Heat-denatured Whey Protein Isolates

A 9% whey protein (WP) isolate solution at pH 7.0 was heat-denatured at 80°C for 30 min. Size-exclusion HPLC showed that native WP formed soluble aggregates after heat-treatment. Additions of CaCl2 (10–40 mM), NaCl (50–400 mM) or glucono-delta-lactone (GDL, 0.4–2.0%, w/v) or hydrolysis by a protease from Bacillus licheniformis caused gelation of the denatured solution at 45°C. Textural parameters, hardness, adhesiveness, and cohesiveness of the gels so formed changed markedly with concentration of added salts or pH by added GDL. Maximum gel hardness occurred at 200 mM NaCl or pH 4.7. Increasing CaCl2 concentration continuously increased gel hardness. Generally, GDL-induced gels were harder than salt-induced gels, and much harder than the protease-induced gel.     

Occurrence of bisphenol-F-diglycidyl ether (BFDGE) in fish canned in oil

The levels of bisphenol-F-diglycidyl ether (BFDGE) were quantified as part of a European survey on the migration of residues of epoxy resins into oil from canned fish. The contents of BFDGE in cans, lids and fish collected from all 15 Member States of the European Union and Switzerland were analysed in 382 samples. Cans and lids were separately extracted with acetonitrile. The extraction from fish was carried out with hexane followed by re-extraction with acetonitrile. The analysis was performed by reverse phase HPL C with fluorescence detection. BFDGE could be detected in 12% of the fish, 24% of the cans and 18% of the lids. Only 3% of the fish contained BFDGE in concentrations considerably above 1mg/kg. In addition to the presented data, a comparison was made with the levels of BADGE (bisphenol-A-diglycidyl ether)analysed in the same products in the context of a previous study.     

Contribution of European research to risk analysis

The European Commission's, Quality of Life Research Programme, Key Action 1—Health, Food & Nutrition is mission-oriented and aims, amongst other things, at providing a healthy, safe and high-quality food supply leading to reinforced consumer confidence in the safety of European food. Its objectives also include the enhancing of the competitiveness of the European food supply. Key Action 1 is currently supporting a number of different types of European collaborative projects in the area of risk analysis. The objectives of these projects range from the development and validation of prevention strategies including the reduction of consumers risks; development and validation of new modelling approaches; harmonization of risk assessment principles, methodologies, and terminology; standardization of methods and systems used for the safety evaluation of transgenic food; providing of tools for the evaluation of human viral contamination of shellfish and quality control; new methodologies for assessing the potential of unintended effects of genetically modified (genetically modified) foods; development of a risk assessment model for Cryptosporidium parvum related to the food and water industries; to the development of a communication platform for genetically modified organism, producers, retailers, regulatory authorities and consumer groups to improve safety assessment procedures, risk management strategies and risk communication; development and validation of new methods for safety testing of transgenic food; evaluation of the safety and efficacy of iron supplementation in pregnant women; evaluation of the potential cancer-preventing activity of pro- and pre-biotic ('synbiotic') combinations in human volunteers. An overview of these projects is presented here.     

低温带皮菜籽粕微粉的不同粒级部分的功能特性

为研究低温带皮菜籽粕微粉的不同粒级部分的功能特性,以经低温脱脂的带皮菜籽粕为原料,经微粉碎后筛分成212~425μm、150~212μm和106~150μm的3个不同粒级的微粉样品,检测这些样品的吸水性、吸油性、乳化性和乳化稳定性、蛋白质体外消化率。结果表明:1 3个不同粒级的微粉样品之间的粗纤维含量存在显著差异,表明三者的结构组成成分有一定差异。23个微粉样品的乳化活性和乳化稳定性随粒度级别的减小而显著增加(P0.01)。33个微粉样品的蛋白质体外消化率随粒度级别的减小而显著增加(P0.01)。4不同粒级带皮菜籽粕微粉样品的吸水性与吸油性受其结构组成物质不同和粒度的双重影响,与粒度的相关性不明显。     

Microbiology of food taints

Fresh and processed foods are often spoilt by the presence of undesirable flavours and odours caused by microbial action. The aim of this paper is to review the current knowledge of microbiologically induced taints that occur in a wide range of foodstuffs, including meats, poultry, fish, crustaceans, milk, dairy products, fruits, vegetables, cereals and cereal products. Examples have been chosen where the compounds responsible for the taint have been identified and sufficient data obtained to demonstrate the involvement of microorganisms. However, in some cases the full identity of the causative organism may not have been elucidated. The types of microorganisms covered by this review include bacteria, fungi, yeasts, actinomycetes and cyanobacteria. Although cyanobacteria do not in general infect foods, their presence in aqueous systems and water supplies can lead to off-flavours in aquatic organisms and processed foodstuffs. Several examples of each of these processes are discussed. Wherever possible, the likely biosynthetic pathway used by the microorganism to produce the offending compound in a foodstuff is indicated.     

Analysis for organic residues from aids to polymerization used to make plastics intended for food contact

Polymers intended for food contact use have been analysed for organic residues which could be attributed to a range of substances employed as polymerization aids (e.g. initiators and catalysts). A wide range of polymers was extracted with solvents and the extracts analysed by gas chromatography-mass spectrometry (GC-MS). The overwhelming majority of substances identified were not derived from aids to polymerization but were oligomers, additives and adventitious contaminants. However, a small number of substances were identified as initiator residues. These included tetramethylsuccinonitrile (TMSN) which was observed in two polymers and it derived from recombination of two azobisisobutyronitrile (AIBN) initiator radicals. Methyl benzoate, benzoic acid, biphenyl and phenyl benzoate were detected in one poly(methyl methacrylate) sample and in two polyvinylchlorides and they are thought to be derived from benzoyl peroxide initiator. TMSN was subsequently targeted for analysis of poly-(methyl methacrylate) plastics using proton nuclear magnetic resonance spectrometry (¹     

Tests of potential functional barriers for laminated multilayer food packages. Part II: Medium molecular weight permeants

Experiments were performed to characterize the kinetics of the permeation of different medium molecular weight model permeants: bisphenol A, warfarin and anthracene, from liquid paraffin, through a surrogate potential functional barrier (25 microns-thick orientated polypropylene--OPP) into the food simulants olive oil and 3% (w/v) acetic acid. The characterization of permeation kinetics generally observed the permeation models previously reported to explain the experimental permeation results obtained for a low molecular weight group of model permeants. In general, the model permeants exhibited behaviour consistent with their relative molecular weights with respect to (a) the time taken to attain steady-state permeation into the food simulant in which they were more soluble, (b) their subsequent steady-state permeation rates, and (c) their partition between liquid paraffin and the OPP membrane.     

The development of reference materials for paralytic shellfish poisoning toxins in lyophilized mussel. I: Interlaboratory studies of methods of analysis

This paper describes the first part of a project undertaken to develop mussel reference materials for Paralytic Shellfish Poisoning (PSP) toxins. Two interlaboratory studies were undertaken to investigate the performance of the analytical methodology for several PSP toxins, in particular saxitoxin (STX) and decarbamoyl-saxitoxin (dc-STX) in lyophilized mussels, and to set criteria for the acceptance of results to be applied during the second part of the project: the certification exercise. In the first study, 18 laboratories were asked to measure STX and dc-STX in rehydrated lyophilized mussel material and to identify as many other PSP toxins as possible with a method of their choice. In the second interlaboratory study, 15 laboratories were additionally asked to determine quantitatively STX and dc-STX in rehydrated lyophilized mussel and in a saxitoxin-enriched mussel material. The first study revealed that three out of four postcolumn derivatization methods and one pre-column derivatization method sufficed in principle to determine STX and dc-STX. Most participants (13 of 18) obtained acceptable calibration curves and recoveries. Saxitoxin was hardly detected in the rehydrated lyophilized mussels and results obtained for dc-STX yielded a CV of 58% at a mass fraction of 1.86 mg/kg. Most participants (14 out of 18) identified gonyautoxin-5 (GTX-5) in a hydrolysed extract provided. The first study led to provisional criteria for linearity, recovery and separation. The second study revealed that 6 out of 15 laboratories were able to meet these criteria. Results obtained for dc-STX yielded a CV of 19% at a mass fraction of 3.49mg/kg. Results obtained for STX in the saxitoxin-enriched material yielded a CV of 19% at a mass fraction of 0.34mg/kg. Saxitoxin could not be detected in the PSP-positive material. Hydrolysis was useful to confirm the identity of GTX5 and provided indicative information about C1 and C2 toxins in the PSP-positive material. The methods used in the second interlaboratory study showed sufficiently consistent analysis results to undertake a certification exercise to assign certified values for STX and dc-STX in lyophilized mussel.     

Focus on China's Paper Industry

In the English section of this issue, 〈China Paper Newsletters〉 will introduce ＂National Development and Reform Commission Issued Announcement for Selection of Major Preliminary Research Projects for the ＇13th Five-Year Plan＇＂, ＂2013 Annual Report of China＇s Paper Industry＂, and news of projects and other policies.     

Listen to downstream & search for innovation

正Nowadays,textile enterprises are all taking efforts in transformation and upgrading,like improving producing capacity and optimizing production structure to face market downturn.It claimed a higher request to the standard of textile equipments.In the upcoming of ITMA ASIA+CITME 2014exhibition,this magazine have interviewed several branch associations and a series of relative enterprises,to summarize industrial developing status