Fuzzy similarity measures, which are used to judge the closeness of two fuzzy sets, are presented to evaluate the water quality of the Haihe River. Based on the membership functions and coefficient of variation as the...Fuzzy similarity measures, which are used to judge the closeness of two fuzzy sets, are presented to evaluate the water quality of the Haihe River. Based on the membership functions and coefficient of variation as the weights, four fuzzy similarity measures （including Lattice similarity measure, Hamming similarity measure, Euclidean similarity measure and the max-min similarity measure） are used to classify the 299 samples into the proper water quality standard ranks. The results are compared with the traditional distance discriminant methods. The calculation of two traditional distance discriminant methods （both Euclidean distance and absolute value distance） is also based on the use of coefficients of variation as the weights. Without the Lattice similarity measure, for this method loses some information, the correct assignment of samples classified into the same water quality ranks is 75.92% with the other three similarity measures and two distance discriminant methods. This result shows the reliability of the five methods. Only considering the three similarity measures, there were only 1.01% of the samples that did not classify to the same ranks, while the corresponding ratio of the two distance discriminant methods was 5.69%. The results of leave-one-out cross validation show that more than 88% of the samples are classified to the proper ranks, which demonstrates that the similarity measures are suitable to evaluate the water quality of the Haihe River.展开更多
循环谱对雷达调制信号具有良好的可分性,文中提取雷达信号的循环谱对信号的调制类型进行分类识别。为了减小循环谱作为分类特征的计算量,采用距离判别的方法寻找最利于分类的一行循环谱信号作为样本信号的分类特征,并结合支持向量机对...循环谱对雷达调制信号具有良好的可分性,文中提取雷达信号的循环谱对信号的调制类型进行分类识别。为了减小循环谱作为分类特征的计算量,采用距离判别的方法寻找最利于分类的一行循环谱信号作为样本信号的分类特征,并结合支持向量机对雷达信号的调制类型做了分类识别的计算机仿真。仿真结果表明,在0 d B时该方法对多种单个雷达信号的识别率高达92.7%,对混合雷达信号的识别率为89.7%,说明该方法在较低信噪比下对于常见的5种雷达调制信号及其相应混合而成的信号具有较高的识别率。展开更多
基金supported by the National Natural Science Foundation of China (No.51178018,71031001)
文摘Fuzzy similarity measures, which are used to judge the closeness of two fuzzy sets, are presented to evaluate the water quality of the Haihe River. Based on the membership functions and coefficient of variation as the weights, four fuzzy similarity measures （including Lattice similarity measure, Hamming similarity measure, Euclidean similarity measure and the max-min similarity measure） are used to classify the 299 samples into the proper water quality standard ranks. The results are compared with the traditional distance discriminant methods. The calculation of two traditional distance discriminant methods （both Euclidean distance and absolute value distance） is also based on the use of coefficients of variation as the weights. Without the Lattice similarity measure, for this method loses some information, the correct assignment of samples classified into the same water quality ranks is 75.92% with the other three similarity measures and two distance discriminant methods. This result shows the reliability of the five methods. Only considering the three similarity measures, there were only 1.01% of the samples that did not classify to the same ranks, while the corresponding ratio of the two distance discriminant methods was 5.69%. The results of leave-one-out cross validation show that more than 88% of the samples are classified to the proper ranks, which demonstrates that the similarity measures are suitable to evaluate the water quality of the Haihe River.
文摘循环谱对雷达调制信号具有良好的可分性,文中提取雷达信号的循环谱对信号的调制类型进行分类识别。为了减小循环谱作为分类特征的计算量,采用距离判别的方法寻找最利于分类的一行循环谱信号作为样本信号的分类特征,并结合支持向量机对雷达信号的调制类型做了分类识别的计算机仿真。仿真结果表明,在0 d B时该方法对多种单个雷达信号的识别率高达92.7%,对混合雷达信号的识别率为89.7%,说明该方法在较低信噪比下对于常见的5种雷达调制信号及其相应混合而成的信号具有较高的识别率。
