基于代价敏感学习的卷烟感官质量评估方法.pdfVIP

2016-1037 5 Chinese Tobacco Science 75 1 2 2 1* 1 1 1. 110819 2. 650231 3 + TS41 1 1007-5119201605-0075-07 DOI 10.13496/j.issn.1007-5119.2016.05.014 A Method for Cigarette Sensory Quality Evaluation Based on Cost-sensitive Learning 1 2 2 1* 1 1 ZHANG Zhongliang , TANG Jianguo , QIAO Danna , LUO Xinggang , ZHAO Liang , TANG Jiafu (1. College of Information Science and Engineering, Northeastern University, Shenyang 110819, China; 2. Technology Center, China Tobacco Yunnan Industrial Co., Ltd., Kunming 650231, China) Abstract: Arming at the cost-sensitive problems in cigarette sensory evaluation, Cost-Sensitive Back-Propagation Neural Networks (CSBPNN) was employed in this paper to deal with the problems derived from cigarette sensory evaluation. In order to verify the effectiveness of our methodology, the cost matrix was obtained based on production practice and the comparative experimental study was carried out by using dataset from a tobacco company. The experimental results indicated that our methods have a significant advantage on total misclassification cost, high cost label recognition rate and average classification accuracy when compared with the cost-insensitive methods. Keywords: classification algorithm; cost-sensitive; sensory evaluation; neural network; cigarette [1] [2] [3] [4] Stone [5]