Special food safety supervision by means of intelligent models and methods is of great significance for the health of local people and tourists. Models like BP neural network have the problems of low accuracy and poor robustness in food safety prediction. So, firstly, the principal component analysis was used to extract the key factors that influenced the amount of coliform communities, which was applied to reduce the dimension of this model as the input variable of BP neural network. Secondly, both the particle swarm optimization (PSO) and BP neural network were implemented to optimize initial weights and threshold to obtain the optimal parameter, and a model was constructed to predict the amount of coliform bacteria in Dai Special Snacks, Sa pie, based on PSO-BP neural network model. Finally, the predicted value of the model is verified. The results show that MSE is 0.0097, MAPE is 0.3198 and MAE is 0.0079, respectively. It was clear that PSO-BP model was better accuracy and robustness. That means, this model can effectively predict the amount of coliform. The research has important guiding significance for the quality and the production of Sa pie.
In this paper, the top-down approach (CNAS-GL34: Guidance for Measurement Uncertainty Evaluation Based on Quality Control Data in Environmental Testing, China National Accreditation Service for Conformity Assessment, Beijing, China, 2013) for A type evaluation of empirical model can be applied to qualify the SO2 by using analyzer and primary test method (PTM) (GB/T 27408: Quality Control in Laboratories—Evaluating Validity of Non-Standard Test Method—Practice for a Linear Relationship, Standardization Administration of the People's Republic of China, Beijing, China, 2010), whereupon a large number of real-time data, in multi-sites at different levels, were accumulated under site precision (sR′) in-statistical-control condition (GB/T 27411: Routine Methods for Evaluation and Expression of Measurement Uncertainty in Testing Laboratory, Standardization Administration of the People's Republic of China, Beijing, China, 2012). The data-transformed-system under investigation cannot be considered suspect as none of the Anderson Darling (AD) statistics were failed in acceptance at the 95 % confidence level for the hypothesis of normality and independence. Our survey was originated from the fog-haze over a period of time for SO2 in air, with its boundary of 100 × 10−9∼400 × 10−9. Finally, the top-down approach, based on closeness sum of squares (CSS), gave the reliable and valid evaluation as the expanded uncertainty, U = 8.5 μg/m3, which maximized the combination of the effects on various variances, refrained from the complicated relativity by bottom-up for uncertainty evaluation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.