机器视觉和电子鼻融合的番茄成熟度检测方法

目的:探索机器视觉与电子鼻融合法在果蔬成熟度检测中的应用能力,实现番茄不同成熟度的检测.方法:基于机器视觉和电子鼻采集系统,提出了一种基于多源信息融合的番茄成熟度检测方法.以机器视觉筛选出的6个颜色特征和电子鼻筛选出的10个气味特征为基础,建立番茄成熟度检测的最小二乘支持向量机模型.通过试验对融合方法和单一方法进行对比...     

电子鼻无损检测柑橘成熟度的实验研究

电子鼻技术在水果的无损检测中得到了不断的研究与发展。文中运用电子鼻对柑橘的成熟度进行了无损检测分析,建立了电子鼻响应与成熟度之间的关系,证明了建立在化学传感器和模式识别软件上的电子鼻能够检测区分不同成熟度的柑橘。同时,研究表明电子鼻传感器阵列可以得到进一步的优化,文中也为这种优化提供了一个具体的实例,这为进一步进行电子鼻的检测商业化提供一个依据。     

基于电子鼻/舌融合技术的白酒类别辨识

为实现白酒质量的快速鉴别,本研究采用两个不同的电子鼻和电子舌融合系统采集不同品牌白酒样品的气-味信息,采用主成分分析法、K均值法对检测结果进行聚类分析,采用支持向量机法对白酒的品牌进行预测分类分析。经主成分分析聚类分析后,应用基于TGS型气敏传感器的电子鼻和电子舌融合系统可以将3种酒进行很好的区分,其余5种酒有交叉,而应用基于MQ、MP型气敏传感器的电子鼻和电子舌融合系统可以将8种白酒基本区分开来;K均值法分别用于两融合系统,前融合系统的错分类概率为33.3%,后融合系统的错分类概率为23.75%。采用支持向量机法对白酒的品牌进行预测分类,应用前融合系统的识别率为93.75%,而应用后融合系统的识别率为98.75%。结果表明:气-味信息融合技术可以实现对白酒品牌的鉴别,且应用基于MQ、MP型气敏传感器的电子鼻和电子舌融合系统对白酒类别的识别结果较好于应用基于TGS型气敏传感器的电子鼻和电子舌融合系统。     

1-MCP处理对甜柿贮藏品质的影响和电子鼻分析

在常温货架期、低温贮藏期和贮后货架期,研究不同处理对甜柿贮藏品质的影响,并利用电子鼻对不同处理甜柿挥发性成分进行判别分析。结果表明,LDA方法有效区分不同常温货架期和贮后货架期的甜柿,对低温贮藏期间的甜柿区分效果稍差。1-MCP处理可以延缓果皮L*和b*、果实质地（果皮强度、果皮脆性和果肉平均硬度）的下降,在贮后货架期间作用效果更为明显。在常温货架期和低温贮藏期,1-MCP处理组和对照组甜柿挥发性成分差异较小,在贮后货架期间差异较大,电子鼻可以有效区分贮后货架期间1-MCP处理组和对照组。      

Maturity sorting index of dragon fruit: Hylocereus polyrhizus

The purpose of this research was to investigate maturity prediction of red flesh dragon fruit based on non-destructive measures. Specific weight, sphericity, color value L, a, b and light reflectance spectrum were linearly combined by partial least squares regression (PLSR) analysis. The PLSR models could predict days after fruit set, weight ratio and total soluble solids relatively well with standard deviation divided by standard error of prediction (RPD) of 2.86, 2.45 and 2.38, respectively. Date after fruit set, total soluble solids, total acid, ratio of total soluble solids and total acidity and weight ratio were transformed into a principal component 1 (PC1) by the principal component analysis and used to represent a single maturity index. The PLSR model with non-destructive parameters resulted in an improved performance in the prediction of the maturity index (PC1) with a RPD increase to 3.49. The model could be further simplified but retained a comparable accuracy by the application of a log (R680/R550) in place of the light reflectance spectrum.     

不同品种苹果采后品质和挥发性物质的差异分析

为明确不同品种苹果采后品质和挥发性物质的差异,本文通过电子鼻结合顶空固相微萃取及气相-质谱联用技术(HS-SPME-GC-MS)分别测定不同品种(‘金冠’、‘嘎啦’、‘乔纳金’、‘寒富’)挥发性物质成分和含量,并对品质指标进行探讨。结果表明,‘金冠’呈现明亮绿黄色,果形指数最高,‘嘎啦’为有光泽红色,但可食率不高,‘乔纳金’为红黄色,果形指数最低,‘寒富’为红橙色,果实质量最大;‘寒富’可溶性固形物含量最大,而‘金冠’可滴定酸含量和维生素C含量最高,‘金冠’苹果和‘嘎啦’苹果硬度和脆性较高。电子鼻主成分分析和线性判别分析表明,可将4个品种苹果完全区分。GC-MS结果表明,共检测到7类33种化合物,主要挥发性物质为醇类、醛类、酯类。4个品种都具有的特征性香气成分是己醛(青草味)、2-己烯醛(绿苹果味)、乙酸己酯(果香味),1-己醇(青草味)是‘嘎啦’、‘金冠’苹果的特征挥发性成分,乙酸丁酯(果香)是‘嘎啦’苹果的独有特征挥发性成分,总体上‘嘎啦’苹果香气浓郁,‘寒富’苹果香气较淡,这与电子鼻分析结果相吻合。     

Discrimination of storage shelf-life for mandarin by electronic nose technique

Over the past years, electronic nose technology opened the possibility to exploit information on aroma attribute to assess fruit ripening stage during storage. The objective in this study was to evaluate the capacity of electronic nose in monitoring the change in volatile production of mandarin during different storage treatments, and storage shelf-life of mandarin was evaluated by measuring the change in volatile production of mandarin using electronic nose device (PEN 2). By comparing, storage shelf-life of mandarin was better distinguished using Linear Discriminant Analysis (LDA) than Principal Component Analysis (PCA). PCA and LDA analysis were efficient to classify mandarin with the same storage time in its respective groups; but the methods are not efficient to separate the mandarins by different storage times. The correlation between the measured and predicted values of fruit quality attribute (such as soluble solid content, acidity and compression force) shows poor to reasonable prediction performance by means of electronic nose signals. The results prove that sensors 2, 7 and 9 in the electronic nose PEN 2 for mandarin have a higher influence in the current pattern file. Hence, nearly a subset of few sensors can be chosen to explain all the variance. This result could be used in further studies to optimize the number of sensors and find better performance.     

基于电子鼻和电子舌技术对不同品种红枣香气和滋味的差异分析

以12种红枣（酸枣、大平顶枣、圆铃枣、灵武长枣、壶瓶枣、狗头枣、金丝小枣、灰枣、灵宝大枣、木枣、石门大枣、骏枣）所破碎的红枣汁为试验对象,探讨了其在香气和滋味上的差异。结果表明,经电子鼻检测发现,电子鼻各传感器对不同品种红枣香气成分的差异显著（P<0.05）;经主成分分析（PCA）和线性判别式分析（LDA）发现,电子鼻能够明显的区别不同品种的红枣。经电子舌检测发现,电子舌5个基本味对不同品种红枣的滋味差异显著（P<0.05）,而3个回味对不同品种红枣的滋味差异不显著（P>0.05）;经主成分分析发现,电子舌不能有效的区别不同品种的红枣。     

臭氧处理对不同成熟度葡萄保鲜效果

为确定臭氧保鲜葡萄的最佳采摘期,以臭氧处理七、八、九成熟的3种不同成熟度的果实,测定其贮藏过程中相关理化指标的变化,包括可溶性糖含量、维生素C、可溶性固形物含量、可滴定酸、耐压力以及失重率和腐烂率等。结果表明:采用臭氧水处理葡萄时,八成熟果实在21d时的可溶性糖含量为13.84%,维生素C为5.18mg/100g,可溶性固形物含量为11.6%,可滴定酸为0.55%,耐压力为0.11MPa,失重率为0.75%,腐烂率为0.70%,贮藏保鲜效果最好,可为臭氧保鲜处理条件下的葡萄采摘时期提供技术参考。      

1-MCP处理对磨盘柿减压贮藏品质及生理变化的影响

以磨盘柿为试材,通过对不同浓度1-甲基环丙烯(1-MCP)处理果实在减压冷藏期间主要生理生化指标、贮藏品质变化规律的分析,探讨了1-MCP处理对果实减压冷藏保鲜效果的影响。结果表明:1-MCP处理明显抑制了减压贮藏果实硬度、可溶性单宁含量的下降;同时也较好的抑制了果实可溶性固形物(去除单宁后)、丙二醛、膜相对透性和PPO活性的升高,并且能使果实在贮藏期间保持较高的SOD活性,但对可滴定酸含量的变化没有显著影响;减压贮藏果实适宜的1-MCP处理浓度为1.0μL/L。     

基于电子鼻技术鉴别陇南初榨橄榄油

为了快速简便地鉴别同一品种不同果实成熟度和不同品种同一果实成熟度的初榨橄榄油,运用电子鼻传感器分析技术结合Loadings负荷加载分析、线性判别分析（LDA）等数据处理技术对结果图谱进行解析,并通过欧氏距离分析（EDA）、相关性分析（CA）、马氏距离分析（MDA）和判别函数分析（DFA）验证模型的准确性。结果显示：电子鼻响应值雷达图及Loadings负荷加载分析均表明W5S、W2W、W1W、W1S传感器对样品有较好的信号响应,通过LDA分析建立的特征图谱可有效鉴别区分被试样品,其识别确定性大于96%,所建模型准确可靠,电子鼻技术可用于同一品种不同果实成熟度和不同品种同一果实成熟度初榨橄榄油的识别。     

Nondestructive estimation of maturity and textural properties on tomato ‘Momotaro’ by near infrared spectroscopy

Near infrared spectroscopy offers the possibility to classify and predict the internal quality of fruits and vegetables. The objective of this study was to evaluate the ability of near infrared spectroscopy to classify the maturity level and to predict textural properties of tomatoes variety “Momotaro”. Principal component analysis (PCA) and Soft independent modeling of class analogy (SIMCA) were used to distinguish among different maturities (mature green, pink and red). Partial least squares (PLS) regression was used to estimate textural properties, alcohol insoluble solids and soluble solids content of the tomatoes. The PCA calibration model with mean normalization pretreatment spectra of mature green tomatoes, gave the highest distinguishability (96.85%). It could classify 100.00% of red and pink tomatoes. The SIMCA model could not give better accuracy in maturity classification than individual PCA models. Among the textural parameters measured, the bioyield force from the puncture test with the near infrared (NIR) spectra (between 1100 and 1800 nm) pretreated by multiplicative scatter correction (MSC) had the highest correlation coefficient between NIR predicted and reference values (r = 0.95) and lowest standard error of prediction (SEP = 0.35 N) and bias of 0.19 N. The ratio of standard deviation of reference data of prediction set to standard error of prediction (RPD) was 2.71. In the case of Momotaro tomato, NIR spectroscopy by using PLS regression could not predict alcohol insoluble solids in fresh weight accurately but could predict soluble solids content well with r of 0.80, SEP of 0.210 %Brix and bias of 0.022 %Brix.     

Measurement of Soluble Solids Content and pH of Yogurt Using Visible/Near Infrared Spectroscopy and Chemometrics

Visible/near infrared spectroscopy (Vis/NIRs) technique was applied to non-destructive quantification of sugar and pH value in yogurt. Partial least squares (PLS) analysis and least squares support vector machine (LS-SVM) were implemented for calibration models. In this paper, three brands (Mengniu, Junyao, and Guangming) were set as the calibration, and the remaining two brands (Yili and Shuangfeng) were used as prediction set. In the LS-SVM model, the correlation coefficient (r), root mean square error of prediction, and bias in prediction set were 0.9427, 0.2621°Brix, 1.804e−09 for soluble solids content, and 0.9208, 0.0327, and 1.094e−09 for pH, respectively. The correlation spectra corresponding to the soluble solids content and pH value of yogurt were also analyzed through PLS method. LS-SVM model was better than PLS models for the measurements of soluble solids content and pH value. The results showed that the Vis/NIRs combined with LS-SVM models could predict the soluble solids content and pH value of yogurt.     

融合不同成熟度的苹果可溶性固形物预测模型研究

目的为实现对不同成熟度的苹果可溶性固形物的预测,建立普适性强的混合分析模型。方法选取甘肃静宁241个不同成熟度的苹果作为研究对象,利用近红外光谱采集系统获取苹果漫反射光谱信息,并对苹果可溶性固形物含量进行测定。利用S-G卷积平滑、多元散射校正(multiplicative scatter correction,MSC)、以及标准正态变量变换(standard normal variable transformation,SNV)等预处理方法结合竞争自适应加权算法(competitive adaptive reweighted sampling,CARS)、随机蛙跳(random frog,RF)算法提取苹果可溶性固形物的特征变量,然后利用偏最小二乘回归(partial least squares regression,PLS R)和支持向量机(support vector machine,SVM)算法建立分析模型。结果对比发现,采用RF选取的特征波长变量数更少且预测精度优于CARS,原始波长点由1251个减少到55个,MSC-RF-PLSR建立的模型预测结果最好,其预测相关系数r和预测均方根误差分别为0.906和0.744。结论采用近红外光谱方法构建的苹果可溶性固形物混合分析模型可以实现对苹果不同成熟度的预测,为建立适用于不同成熟度苹果的可溶性固形物便携设备提供理论依据。     

电子鼻在水果品质评价体系中应用的研究进展

人工智能技术电子鼻具有客观、准确、快捷、全面地评价气味并且具有不破坏样品和重复性好的特点,可运用于对水果品质评价体系中。本文介绍了电子鼻技术工作原理和常用的模式识别技术,并综述了电子鼻在水果成熟度监控、货架期预测、区分不同品种以及危害分析中的应用,剖析总结了电子鼻技术存在的问题,并提出了电子鼻技术的发展趋势和方向。     

涩柿MAP保鲜技术研究

软化和褐变是柿果保鲜两大技术难题,实验以桂林涩柿为材料,研究(0±0.3)℃下,在不同贮运保鲜期高压PE膜、微孔PE膜、KMS膜(自制防雾PE膜)等MAP的保鲜效果,定期检测果肉硬度(FF)、可溶性固形物(SSC)、可滴定酸含量(TA)、褐变指数(BI)和好果率。结果表明:桂林柿果MA贮藏120d,KMS膜保鲜效果最好,袋内气体浓度达到平衡时,O2为5.5%、CO2为7.0%,FF为11.14kg/cm2,SSC为12.91%,TA为0.59%,BI增加了0.72,好果率为82.9%,均显著优于对照。     

Non-destructive evaluation of maturity and quality parameters of pomegranate fruit by visible/near infrared spectroscopy

In this study, the potential of visible and near infrared spectroscopy was investigated to classify the maturity stage and to predict the quality attributes of pomegranate variety “Ashraf” such as total soluble solids content, pH, and titratable acidity during four distinct maturity stages between 88 and 143 days after full bloom. Principal component analysis was used to distinguish among different maturities. The prediction models of internal quality attributes of the pomegranate were developed by partial least squares regression. The transmission spectra of pomegranate were obtained in the wavelength range from 400 to 1100 nm. In this research several preprocessing methods were utilized including centering, smoothing (Savitzky–Golay algorithm, median filter), normalization (multiplicative scatter correction and standard normal variate) and differentiation (first derivative and second derivative). It concluded that different preprocessing techniques had effects on the classification performance of the model using the principal component analysis method. In general, standard normal variate and multiplicative scatter correction gave better results than the other pretreatments. The correlation coefficients (r), root mean square error of calibration and ratio performance deviation for the calibration models were calculated: r = 0.93, root mean square error of calibration = 0.22 °Brix and ratio performance deviation = 6.4 °Brix for total soluble solids; r = 0.84, root mean square error of calibration = 0.064 and ratio performance deviation = 4.95 for pH; r = 0.94, root mean square error of calibration = 0.25 and ratio performance deviation = 5.35 for titratable acidity.     

红肉火龙果贮藏期间气味监测及桃吉尔霉对气味的影响

目的 监测贮藏条件下火龙果挥发性气味变化及桃吉尔霉(Gilbertella persicaria)侵染果实后气味的改变。方法 以红肉火龙果“紫红龙”为实验材料, 采用电子鼻对室温贮藏条件下火龙果和接种G. persicaria病原菌后的火龙果的挥发性气味变化进行检测。对不同传感器的响应值进行主成分分析(principal component analysis, PCA)、线性判别分析(linear discriminant analysis, LDA), 并通过载荷分析(loading analysis, LA)明确了传感器的贡献率。结果 PCA和LDA均能准确判别出火龙果果实在贮藏期间的挥发性气味变化以及果实被G.persicaria侵染后气味的改变, 载荷分析方法显示出W1S和W1W传感器在火龙果贮藏期间起主要作用, 而在识别病原菌感染后气味改变时起作用的主要是W1W和W2W传感器。结论 电子鼻检测技术可以快速区分火龙果果实贮藏时间及G. persicaria侵染后果实气味的变化。     

基于电子鼻技术鉴别蜂蜜掺入果葡糖水的研究

采用电子鼻对掺假蜂蜜样品进行分析,对所获得的数据进行主成分分析和偏最小二乘回归分析,对掺假蜂蜜样品建立了偏最小二乘回归分析预测模型。结果表明:电子鼻响应信号和果葡糖水掺入比例之间有很好的相关性(决定系数R2为0.980 3),偏最小二乘回归分析模型预测误差均≤8%(掺入比例20%~70%)。试验证明当果葡糖水掺入比例较高时,电子鼻可用于掺假蜂蜜的识别。     

CARS-SVM预测哈密瓜可溶性固形物含量

采用近红外光谱技术结合数据降维的方法,建立了哈密瓜可溶性固形物含量的预测模型：对比多种光谱预处理方法,确定二阶求导用于处理原始光谱;经预处理的光谱数据分别结合特征选择竞争性自适应重加权采样法（CARS）、蒙特卡罗无信息变量消除法（MC-UVE）提取特征波长,以及利用主成分分析进行降维;再使用特征选择和特征提取的光谱数据作为模型的输入变量,建立哈密瓜可溶性固形物含量预测模型。结果显示,CARS+SVM建立的预测模型最优,模型的校正集相关系数为0.981 4,预测集相关系数为0.900 2,模型能够准确预测哈密瓜可溶性固形物含量。