Traditional clustering method is easy to slow convergence speed because of high data dimension and setting random initial clustering center. To improve these problems, a novel method combining subtractive clustering w...Traditional clustering method is easy to slow convergence speed because of high data dimension and setting random initial clustering center. To improve these problems, a novel method combining subtractive clustering with fuzzy C-means( FCM)clustering will be advanced. In the method, the initial cluster number and cluster center can be obtained using subtractive clustering. On this basis,clustering result will be further optimized with FCM. In addition,the data dimension will be reduced through the analytic hierarchy process( AHP) before clustering calculating.In order to verify the effectiveness of fusion algorithm,an example about enterprise credit evaluation will be carried out. The results show that the fusion clustering algorithm is suitable for classifying high-dimension data,and the algorithm also does well in running up processing speed and improving visibility of result. So the method is suitable to promote the use.展开更多
采集了浙江、福建、江苏、湖南、湖北、四川、重庆、黑龙江、河南9个省的稗(Echinochloa crus-galli(L.)P.Beauv.)及其变种的33份种子,分别播种在相同的环境下,获得33个种群,测定了种群的16个形态性状,筛选出重复性好的9条ISSR引物,从3...采集了浙江、福建、江苏、湖南、湖北、四川、重庆、黑龙江、河南9个省的稗(Echinochloa crus-galli(L.)P.Beauv.)及其变种的33份种子,分别播种在相同的环境下,获得33个种群,测定了种群的16个形态性状,筛选出重复性好的9条ISSR引物,从33个种群中扩增出了109个位点。基于这些形态性状和ISSR位点信息,对33个种群先进行主成分分析,在此基础上再进行模糊均值聚类分析,探讨了它们的形态和遗传变化特点,及其与形态—遗传—地理背景三者之间的关系。主要结论如下:(1)33个种群可以鉴别出形态性状相对一致的4组,能够识别出西来稗(E.crus-galli var.zelayensis(Kunth)Farw.)、无芒稗(E.crus-galli var.mitis(Pursh)Peterm.)、细叶旱稗(E.crus-galli var.praticola Ohwi);(2)基于109个位点信息对33个种群进行聚类分析得到了6组,部分组与形态聚类分组有一定的对应性;(3)33个稗草种群的遗传分化受地理背景因素的影响(r=0.684,n=33,P<0.001);形态变异也有较明显的遗传背景因素(r=0.425,n=33,P<0.02)。在相对一致的稻田生境中,可能存在着形态上的趋同适应,使遗传上分化的组间在形态上又往往有交叉过渡,致使稗原变种(E.crus-galli var.crus-galli)、西来稗、无芒稗、短芒稗(E.crus-galli var.breviseta(D9ll)Podp.)在形态上难以区别;(4)基于遗传和形态数据分析,发现细叶旱稗无论在形态上,还是遗传上,均形成了明显的一组,推测与该种长期适应于干旱生境有关,建议将细叶旱稗提升为种的水平,并将其命名为Echinochloa praticola(Ohwi)Guo S L,Lu Y L,Yin L P&Zou M Y。展开更多
基金Innovation Program of Shanghai Municipal Education Commission,China(No.12YZ191)
文摘Traditional clustering method is easy to slow convergence speed because of high data dimension and setting random initial clustering center. To improve these problems, a novel method combining subtractive clustering with fuzzy C-means( FCM)clustering will be advanced. In the method, the initial cluster number and cluster center can be obtained using subtractive clustering. On this basis,clustering result will be further optimized with FCM. In addition,the data dimension will be reduced through the analytic hierarchy process( AHP) before clustering calculating.In order to verify the effectiveness of fusion algorithm,an example about enterprise credit evaluation will be carried out. The results show that the fusion clustering algorithm is suitable for classifying high-dimension data,and the algorithm also does well in running up processing speed and improving visibility of result. So the method is suitable to promote the use.
文摘采集了浙江、福建、江苏、湖南、湖北、四川、重庆、黑龙江、河南9个省的稗(Echinochloa crus-galli(L.)P.Beauv.)及其变种的33份种子,分别播种在相同的环境下,获得33个种群,测定了种群的16个形态性状,筛选出重复性好的9条ISSR引物,从33个种群中扩增出了109个位点。基于这些形态性状和ISSR位点信息,对33个种群先进行主成分分析,在此基础上再进行模糊均值聚类分析,探讨了它们的形态和遗传变化特点,及其与形态—遗传—地理背景三者之间的关系。主要结论如下:(1)33个种群可以鉴别出形态性状相对一致的4组,能够识别出西来稗(E.crus-galli var.zelayensis(Kunth)Farw.)、无芒稗(E.crus-galli var.mitis(Pursh)Peterm.)、细叶旱稗(E.crus-galli var.praticola Ohwi);(2)基于109个位点信息对33个种群进行聚类分析得到了6组,部分组与形态聚类分组有一定的对应性;(3)33个稗草种群的遗传分化受地理背景因素的影响(r=0.684,n=33,P<0.001);形态变异也有较明显的遗传背景因素(r=0.425,n=33,P<0.02)。在相对一致的稻田生境中,可能存在着形态上的趋同适应,使遗传上分化的组间在形态上又往往有交叉过渡,致使稗原变种(E.crus-galli var.crus-galli)、西来稗、无芒稗、短芒稗(E.crus-galli var.breviseta(D9ll)Podp.)在形态上难以区别;(4)基于遗传和形态数据分析,发现细叶旱稗无论在形态上,还是遗传上,均形成了明显的一组,推测与该种长期适应于干旱生境有关,建议将细叶旱稗提升为种的水平,并将其命名为Echinochloa praticola(Ohwi)Guo S L,Lu Y L,Yin L P&Zou M Y。
文摘针对化工生产过程的安全性问题,提出基于混合蛙跳(shuffled frog leaping algorithm,SFLA)的FCM聚类算法。该算法引入寻优能力强的SFLA求得最优解作为FCM算法的初始聚类中心,然后利用FCM算法优化初始聚类中心,最后求得全局最优解,从而有效避免了F C M算法易陷入局部最优和对初始值敏感的缺点。将该算法用于化工生产状态数据的聚类分析,实验结果表明,本文算法与F C M聚类算法相比,提高了算法的寻优能力,聚类效果更好;并且能够快速、客观地对化工生产过程的状态进行判别,为其安全运行提供了保障。
