基于SVM核机器学习的三文鱼新鲜度检测系统  

Detection System of Salmon Freshness Based on SVM Kernel-based Machine Learning

作　　者：李鑫星[1] 董保平 杨铭松 张国祥[1] 张小栓[1] 成建红[3] LI Xinxing;DONG Baoping;YANG Mingsong;ZHANG Guoxiang;ZHANG Xiaoshuan;CHENG Jianhong(Beijing Laboratory of Food Quality and Safety,China Agricultural University,Beijing 100083,China;Station for the Forest Resources Monitoring and Management in Yantai,Yantai 264000,China;Yantai Institute,China Agricultural University,Yantai 264670,China)

机构地区：[1]中国农业大学食品质量与安全北京实验室,北京100083 [2]山东省烟台市森林资源监测管理站,烟台264000 [3]中国农业大学烟台研究院,烟台264670

出　　处：《农业机械学报》2019年第5期376-384,共9页Transactions of the Chinese Society for Agricultural Machinery

基　　金：北京市重点研发计划项目(Z181100001018033);中央高校基本科研业务费专项资金项目(2019TC044)

摘　　要：为了实现对不同冷藏温度下三文鱼新鲜度的检测与识别,设计了一种用于三文鱼气味指纹采集与新鲜度辨识的电子鼻系统。电子鼻系统由密闭检测气室、半导体气体传感器阵列、数据采集模块、模式识别模块和显示界面等组成。电子鼻模式识别方法采用核机器学习方法,以支持向量机(SVM)作为学习机。采集0、4、6℃温度下冷藏三文鱼样本的气味数据,对不同核函数及参数的核机器学习模型进行训练与测试,最终确定了适于此电子鼻系统识别三文鱼新鲜度的最佳核机器学习模型:核函数选用多项式核函数,核参数q取3,γ取15,c取0。此模型对不同温度冷藏三文鱼样本的冷藏时间具有一定的辨识能力,对于测试集,0℃允许偏差1 d预测正确率为92. 86%,4℃无偏差预测正确率为88. 89%、允许偏差1 d预测正确率100%,6℃无偏差预测正确率为75. 00%、允许偏差1 d预测正确率100%。将辨识结果与主成分分析结果(PCA)进行对比,此模型具有明显的优势。In order to detect the odor of salmon refrigerated at different refrigerating temperatures and identify its freshness more accurately, an electronic nose based on kernel-based machine learning model was designed. It consisted of five parts, which were the detection air chamber, the array of six gas sensors, the data acquisition module, the pattern recognition module and the display interface. Kernel-based machine learning model was selected as the pattern recognition method of the electronic nose, and support vector machine (SVM) was selected as the learning machine of kernel-based machine learning model. The odor fingerprint data of salmon samples respectively refrigerated at 0℃, 4℃ and 6℃ was collected to train and test the kernel-based machine learning models with different kernel functions and kernel parameters. Finally, a kernel-based machine learning model that had the best salmon freshness identification effect was determined. And it was determined that the polynomial function was taken in the kernel function, and the kernel parameters of q ,γ and c were taken as 3, 15 and 0, respectively. Analysis of identification result of test set salmon samples was conducted, which showed that no days deviation correct rate was 57.14% and allowable deviation of 1 day correct rate was 92.86% at 0℃, no days deviation correct rate was 88.89% and allowable deviation of 1 day correct rate was 100% at 4℃, no days deviation correct rate was 75.00% and allowable deviation of 1 day correct rate was 100% at 6℃. It proved that the model had certain ability to identify the freshness of salmons refrigerated at different temperatures. Compared with the result of principal component analysis (PCA), the kernel-based machine learning model had a better ability.

关 键 词：三文鱼 新鲜度 电子鼻 核机器学习 

分 类 号：S983[农业科学—捕捞与储运]