Changes of Agricultural Materials’ 
 Price and its Impact on Agricultural Production and Farmers’ Income

Hui, Yang; ., Hu Bao-Quan

doi:10.3923/jas.2013.3897.3902

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Detailed demonstrations of these three problems can be found in the literature. 31,32 In terms of the abovementioned problems, an AdaBoost-frame based on the BPANN algorithm, namely, AdaBoost-BPANN, was used to enhance the performance of the BPANN model. It constructs a more powerful prediction system by developing a sequence composed by the original forecasting algorithm.…”

Section: Discussionmentioning

confidence: 99%

Quantifying of total volatile basic nitrogen (TVB-N) content in chicken using a colorimetric sensor array and nonlinear regression tool

Urmila

Chen

et al. 2015

Anal. Methods

View full text Add to dashboard Cite

Total volatile basic nitrogen (TVB-N) content is an important indicator for evaluating meat's freshness. This study attempts to quantify TVB-N content non-destructively in chicken using a colorimetric sensors array with the help of multivariate calibration. First, we fabricated a colorimetric sensor array by printing 12 chemically responsive dyes on a C2 reverse silica-gel flat plate. A color change profile was obtained by differentiating the images of the sensor array before and after exposure to volatile organic compounds (VOCs) released from a chicken sample. In addition, we proposed a novel algorithm for modeling, which is a back propagation artificial neural network (BPANN), and an adaptive boosting (AdaBoost) algorithm, namely, AdaBoost-BPANN, and we compared it with the commonly used algorithms. Experimental results showed that the optimum model was achieved by the AdaBoost-BPANN algorithm with RMSEP ¼ 7.7124 mg/100 g and R ¼ 0.8915 in the prediction set. This study demonstrated that the colorimetric sensors array has a high potential in the non-destructive sensing of chicken's freshness and that the AdaBoost-BPANN algorithm performs well as a solution to a complex data calibration.

show abstract

Section: Discussionmentioning

confidence: 99%