As one of the important daily consumer goods, alcoholic beverage presents high safety risks and potential hazards. Therefore, ensuring its quality and safety to meet consumer demand is urgent. Meanwhile, in response t...
详细信息
As one of the important daily consumer goods, alcoholic beverage presents high safety risks and potential hazards. Therefore, ensuring its quality and safety to meet consumer demand is urgent. Meanwhile, in response to the iterative and optimization issues in ensemble learning, this paper introduces a Genetic algorithm (GA) to enhance the performance of the Stacking ensemble learning model. Based on the inspection data of alcoholic food products published by National Food Safety Sampling Inspection Results Query System in China, this study applies the Synthetic Minority Oversampling Technique and Tomek Links algorithm for comprehensive sampling, to achieve balanced categorization of different samples. It effectively mitigates the impact of non-smooth data and improves the classification results biased towards majority class samples. After cross-validation and hyperparameter optimization, the proposed GA-improved Stacking ensemble learning model has an accuracy of 0.885, a precision of 0.882, a recall of 0.885, and an F1 score of 0.876, comparing with traditional single classifier algorithms such as random search, Bayesian search, and other methods. This study provides an effective risk warning method for regulatory agencies' inspection focus.
暂无评论