Feasibility study on identification of green, black and Oolong teas using near-infrared reflectance spectroscopy based on support vector machine (SVM)

Chen, Quansheng; Zhao, Jiewen; Fang, Chao; Wang, Dongmei

doi:10.1016/j.saa.2006.03.038

Cited by 251 publications

(142 citation statements)

References 18 publications

Supporting

Mentioning

138

Contrasting

Unclassified

Order By: Relevance

“…RBF kernel function was selected as the kernel function of SVM because it has been applied widely and its theoristical system is also more mature than other kernel functions (Zhao et al 2006). The performance of the SVM model is particularly vulnerable to the parameter g of RBF kernel function and the regularisation constant c which determines the tradeoff between minimising the training error and minimising the model complexity (Chen et al 2007). The leave-one-out cross-validation (LOO-CV) (Dong & Wang 2011) was applied for parameters optimisation of c and g Number of PLS components Number of PLS components subjects to maximise the identification rate.…”

Section: Resultsmentioning

confidence: 99%

A nondestructive method for fish freshness determination with electronic tongue combined with linear and non-linear multivariate algorithms

et al. 2014

View full text Add to dashboard Cite

Han F., Huang X., Teye E., Gu H., Dai H., Yao L. (2014): A nondestructive method for fish freshness determination with electronic tongue combined with linear and non-linear multivariate algorithms. Czech J. Food Sci., 32: 532-537.Electronic tongue coupled with linear and non-linear multivariate algorithms was attempted to address the drawbacks of fish freshness detection. Parabramis pekinensis fish samples stored at 4°C were used. Total volatile basic nitrogen (TVB-N) and total viable count (TVC) of the samples were measured. Fisher liner discriminant analysis (Fisher LDA) and support vector machine (SVM) were applied comparatively to classify the samples stored at different days. The results revealed that SVM model was better than Fisher LDA model with a higher identification rate of 97.22% in the prediction set. Partial least square (PLS) and support vector regression (SVR) were applied comparatively to predict the TVB-N and TVC values. The quantitative models were evaluated by the root mean square error of prediction (RMSEP) and the correlation coefficient in the prediction set (R pre ). The results revealed that SVR model was superior to PLS model with RMSEP = 5.65 mg/100 g, R pre = 0.9491 for TVB-N prediction and RMSEP = 0.73 log CFU/g, R pre = 0.904 for TVC prediction. This study demonstrated that the electronic tongue together with SVM and SVR has a great potential for a convenient and nondestructive detection of fish freshness.

show abstract

Section: Resultsmentioning

confidence: 99%

A nondestructive method for fish freshness determination with electronic tongue combined with linear and non-linear multivariate algorithms

et al. 2014

View full text Add to dashboard Cite

show abstract

“…The smallest number of LVs at the minimum value of the corresponding error rate of venetian blinds cross-validation was chosen. With regards to the RBF-SVM method, the RBF was used as the kernel function of SVM and optimal separation of groups was achieved based on statistical learning [42]. In this study, the parameters of c and g for the RBF-SVM method were chosen in an automatic optimization process.…”

Section: Reference Measurements Statistics and Spectral Data Processingmentioning

confidence: 99%

Visible and Near-Infrared Hyperspectral Imaging for Cooking Loss Classification of Fresh Broiler Breast Fillets

et al. 2018

View full text Add to dashboard Cite

Cooking loss (CL) is a critical quality attribute directly relating to meat juiciness. The potential of the hyperspectral imaging (HSI) technique was investigated for non-invasively classifying and visualizing the CL of fresh broiler breast meat. Hyperspectral images of total 75 fresh broiler breast fillets were acquired by the system operating in the visible and near-infrared (VNIR, 400-1000 nm) range. Mean spectra were extracted from regions of interest (ROIs) determined by pure muscle tissue pixels. CL was firstly measured by calculating the weight loss in cooking, and then fillets were grouped into high-CL and low-CL according to the threshold of 20%. The classification methods partial least square-discriminant analysis (PLS-DA) and radial basis function-support vector machine (RBF-SVM) were applied, respectively, to determine the optimal spectral calibration strategy. Results showed that the PLS-DA model developed using the data, that is, first-order derivative (Der1) of VNIR full spectra, performed best with correct classification rates (CCRs) of 0.90 and 0.79 for the calibration and prediction sets, respectively. Furthermore, to simplify the optimal PLS-DA model and make it practical, effective wavelengths were individually selected using uninformative variable elimination (UVE) and competitive adaptive reweighted sampling (CARS). Through performance comparison, the CARS-PLS-DA combination was identified as the optimal method and the PLS-DA model built with 18 informative wavelengths selected by CARS resulted in good CCRs of 0.86 and 0.79. Finally, classification maps were created by predicting CL categories of each pixel in the VNIR hyperspectral images using the CARS-PLS-DA model, and the general CL categories of fillets were readily discernible. The overall results were encouraging and showed the promising potential of the VNIR HSI technique for classifying fresh broiler breast fillets into different CL categories.

show abstract

“…Comparing with other feasible kernel functions, RBF could handle the linear and nonlinear relationships between the spectra and target attributes. Besides, RBF is able to reduce the computational complexity of the training procedure and give a good performance under general smoothness assumptions (Chen et al 2007). Thus, RBF was recommended as the kernel function of SVM in this work.…”

Section: Support Vector Machinesmentioning

confidence: 99%

Eggshell crack detection based on acoustic impulse response and supervised pattern recognition

Hao¹,

Zhao²,

Chen³

et al. 2009

Czech J. Food Sci.

View full text Add to dashboard Cite

Lin H., Zhao J., Chen Q., Cai J., Zhou P. (2009): Eggshell crack detection based on acoustic impulse response and supervised pattern recognition. Czech J. Food Sci., 27: 393-402.A system based on acoustic resonance was developed for eggshell crack detection. It was achieved by the analysis of the measured frequency response of eggshell excited with a light mechanism. The response signal was processed by recursive least squares adaptive filter, which resulted in the signal-to-noise ratio of the acoustic impulse response reing remarkably enhanced. Five features variables were exacted from the response frequency signals. To develop a robust discrimination model, three pattern recognition algorithms (i.e. K-nearest neighbours, artificial neural network, and support vector machine) were examined comparatively in this work. Some parameters of the model were optimised by cross-validation in the building model. The experimental results showed that the performance of the support vector machine model is the best in comparison to k-nearest neighbours and artificial neural network models. The optimal support vector machine model was obtained with the identification rates of 95.1% in the calibration set, and 97.1% in the prediction set, respectively. Based on the results, it was concluded that the acoustic resonance system combined with the supervised pattern recognition has a significant potential for the cracked eggs detection.

show abstract

Feasibility study on identification of green, black and Oolong teas using near-infrared reflectance spectroscopy based on support vector machine (SVM)

Cited by 251 publications

References 18 publications

A nondestructive method for fish freshness determination with electronic tongue combined with linear and non-linear multivariate algorithms

A nondestructive method for fish freshness determination with electronic tongue combined with linear and non-linear multivariate algorithms

Visible and Near-Infrared Hyperspectral Imaging for Cooking Loss Classification of Fresh Broiler Breast Fillets

Eggshell crack detection based on acoustic impulse response and supervised pattern recognition

Contact Info

Product

Resources

About