| 摘 要: 本文通过实验对比了逻辑回归、决策树、人工神经网络和支持向量机等方法在分析抽检数据中的表现。 结果表明，支持向量机的预测准确率最高。该方法及相应软件系统能够为未来的抽检计划制定提供决策依据，在有限的 抽检成本和时间花费的条件限制下，能更多地暴露食品安全中的问题，从而提升食品安全和食品质量。 |
| 关键词: 食品安全；抽检数据；支持向量机；数据挖掘 |
|
中图分类号: TP311.5
文献标识码: A
|
| 基金项目: 大学生创新计划(X201810022128)；国家重点研发计划(2018YFC1603302). |
|
| SVM-Based Analysis on Food Safety Sampling and Inspection Data |
|
YOU Qingshun,WANG Jianxin,ZHANG Xiuyu,LUO Xi1,2
|
1.( 1.School of Information, Beijing Forestry University, Beijing 100083, China;2.
2.Guizhou Academy of Testing and Analysis, Guiyang 550000, China)
|
| Abstract: By means of experiments,this paper compares the performances of logistic regression,decision tree,artificial neural network,and support vector machine in the analysis of sampling data.The results show that support vector machine has the highest prediction accuracy.This method and the corresponding software system can provide decision-making basis for the future sampling plan,expose more problems in food safety,and thus promote food safety and quality. |
| Keywords: food safety;sampling and inspection data;support vector machine;data mining |
