摘要
D-S证据理论在应用中,如何生成一个合理的基本概率赋值函数,仍然是一个亟需解决的问题。研究提出了一种基于属性权重与方差的基本概率赋值函数生成方法,该方法通过计算样本数据方差与实验数据方差之间的相似度,结合属性权重确立出每个实验数据的基本概率赋值。算例分析表明,新方法能准确的对实验数据建立基本概率赋值函数,验证了新方法的准确性与有效性。
How to generate a reasonable basic probability assignment function in the application of Dempster-Shafer evidence theory still remains a problem which needs an urgent solution. A method to generate the basic probability assignment based on attribute weights and variance is presented, which establishes the basic probability assignment of each experiment data by calculating the similarity between the variance of sample data and the variance of experimental data, and combined with the attribute weights. The example analysis shows that the new method can accurately establish the basic probability assignment function of the experimental data, verifying the accuracy and effectiveness of new methods.
出处
《中国电子科学研究院学报》
2014年第4期415-419,共5页
Journal of China Academy of Electronics and Information Technology
关键词
证据理论
方差
基本概率赋值
属性权重
evidence theory
variance
basic probability assignment
attribute weights
