No abstract

A new and accurate approach for classifying sesame oil adulterated with corn oil using the information fusion of synchronous and asynchronous 2D NIR‐MIR correlation spectroscopy combined with least squares support vector machines (LS‐SVM). N‐way partial least square discriminant analysis (NPLS‐DA) was adopted to extract the principal components of synchronous and asynchronous 2D NIR‐MIR correlation matrices. And the score matrices of synchronous and asynchronous 2D NIR‐MIR correlation spectroscopy were emerged. Both separate and emerged score matrices were input LS‐SVM to construct discriminate models for adulterated sesame oil. The ratios of correct classification were 98.1 and 100% for calibration set and prediction set, respectively, based on information fusion combined with LS‐SVM. Comparison results showed that the LS‐SVM model could provide higher discriminant accuracy for adulterated sesame soil based on the information fusion of synchronous and asynchronous 2D NIR‐MIR correlation spectroscopy than both separate spectra information. Practical applications: The proposed method not only contains NIR and MIR spectral information, but also contains the similar and dissimilar variation spectral information with the perturbation. Thus, the method can provide better discriminate results of adulterated sesame oil in comparison with conventional spectral methods; can also be applied to other food safety detection areas. The information fusion of synchronous and asynchronous 2D NIR‐MIR correlation spectroscopy is proposed for classifying adulterated sesame oil.

No abstract

Abstract. Plant disease has been a major constraining factor in the production of cucumber，the traditional diagnostic methods usually take a long time, and the control period is often missed. We take computer image processing as a method, preprocessing the images of more than 100 sheets of collected samples of cucumber leaves, using the region growing method to extract scab area of leaves to get three feature parameters of shape, color and texture. And then, through the establishment of BP neural network pattern, the model identification accuracy of cucumber leaf disease can reach 80%. The experiment shows that by using this method, the diseases of cucumber leaves can be identified more quickly and accurately. And the feature extraction and automatic diagnosis of cucumber leaf disease can be achieved.

No abstract