{"title":"基于多元线性回归模型的菜花重量估计","authors":"Xia-Xia Guo, Gui-hong Zhou, Hong Cheng","doi":"10.1145/3232651.3232656","DOIUrl":null,"url":null,"abstract":"In view of the problem that the traditional electronic scale can't predict the prenatal yield of the cauliflower, which having the characteristics of irregular shape and uneven density distribution. In this paper a method is proposed to predict the weight of the cauliflower based on multiple linear regression models. Using Kinect scanning equipment to obtain 3D model of cauliflower, the length, width, height, max_area and volume of the cauliflower 3D model were selected as features. The optimal parameters of the two regularized models, ridge regression and LASSO were selected by cross-validation. In this paper, the K-fold cross-validation (K = 5) was used to divide and select the test set and the train set for small sample. Ridge Regression and LASSO models, as well as optimized models, were evaluated using decision coefficients and relative errors. The experimental results were compared and analyzed. The results show that the optimized LASSO model has the best prediction accuracy for the weight of cauliflower.","PeriodicalId":365064,"journal":{"name":"Proceedings of the 1st International Conference on Control and Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2018-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Estimation of Cauliflower Weight Based on Multiple Linear Regression Modelling\",\"authors\":\"Xia-Xia Guo, Gui-hong Zhou, Hong Cheng\",\"doi\":\"10.1145/3232651.3232656\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In view of the problem that the traditional electronic scale can't predict the prenatal yield of the cauliflower, which having the characteristics of irregular shape and uneven density distribution. In this paper a method is proposed to predict the weight of the cauliflower based on multiple linear regression models. Using Kinect scanning equipment to obtain 3D model of cauliflower, the length, width, height, max_area and volume of the cauliflower 3D model were selected as features. The optimal parameters of the two regularized models, ridge regression and LASSO were selected by cross-validation. In this paper, the K-fold cross-validation (K = 5) was used to divide and select the test set and the train set for small sample. Ridge Regression and LASSO models, as well as optimized models, were evaluated using decision coefficients and relative errors. The experimental results were compared and analyzed. The results show that the optimized LASSO model has the best prediction accuracy for the weight of cauliflower.\",\"PeriodicalId\":365064,\"journal\":{\"name\":\"Proceedings of the 1st International Conference on Control and Computer Vision\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-06-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 1st International Conference on Control and Computer Vision\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3232651.3232656\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 1st International Conference on Control and Computer Vision","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3232651.3232656","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Estimation of Cauliflower Weight Based on Multiple Linear Regression Modelling
In view of the problem that the traditional electronic scale can't predict the prenatal yield of the cauliflower, which having the characteristics of irregular shape and uneven density distribution. In this paper a method is proposed to predict the weight of the cauliflower based on multiple linear regression models. Using Kinect scanning equipment to obtain 3D model of cauliflower, the length, width, height, max_area and volume of the cauliflower 3D model were selected as features. The optimal parameters of the two regularized models, ridge regression and LASSO were selected by cross-validation. In this paper, the K-fold cross-validation (K = 5) was used to divide and select the test set and the train set for small sample. Ridge Regression and LASSO models, as well as optimized models, were evaluated using decision coefficients and relative errors. The experimental results were compared and analyzed. The results show that the optimized LASSO model has the best prediction accuracy for the weight of cauliflower.