A leukocyte image fast scanning method based on max min distance clustering is proposed.Because of the lower proportion and uneven distribution of leukocytes in human peripheral blood,there will not be any leukocyte i...A leukocyte image fast scanning method based on max min distance clustering is proposed.Because of the lower proportion and uneven distribution of leukocytes in human peripheral blood,there will not be any leukocyte in lager quantity of the captured images if we directly scan the blood smear along an ordinary zigzag scanning routine with high power(100^(x))objective.Due to the larger field of view of low power(10^(x))objective,the captured low power blood smear images can be used to locate leukocytes.All of the located positions make up a specific routine,if we scan the blood smear along this routine with high power objective,there will be definitely leukocytes in almost all of the captured images.Considering the number of captured images is still large and some leukocytes may be redundantly captured twice or more,a leukocyte clustering method based on max-min distance clustering is developed to reduce the total number of captured images as well as the number of redundantly captured leukocytes.This method can improve the scanning eficiency obviously.The experimental results show that the proposed method can shorten scanning time from 8.0-14.0min to 2.54.0 min while extracting 110 nonredundant individual high power leukocyte images.展开更多
K-means聚类算法随机确定初始聚类数目,而且原始数据集中含有大量的冗余特征会导致聚类时精度降低,而布谷鸟搜索(CS)算法存在收敛速度慢和局部搜索能力弱等问题,为此提出一种基于自适应布谷鸟优化特征选择的K-means聚类算法(DCFSK)。首...K-means聚类算法随机确定初始聚类数目,而且原始数据集中含有大量的冗余特征会导致聚类时精度降低,而布谷鸟搜索(CS)算法存在收敛速度慢和局部搜索能力弱等问题,为此提出一种基于自适应布谷鸟优化特征选择的K-means聚类算法(DCFSK)。首先,为提升CS算法的搜索速度和精度,在莱维飞行阶段,设计了自适应步长因子;为调节CS算法全局搜索和局部搜索之间的平衡、加快CS算法的收敛,动态调整发现概率,进而提出改进的动态CS算法(IDCS),在IDCS的基础上构建了结合动态CS的特征选择算法(DCFS)。其次,为提升传统欧氏距离的计算精确度,设计同时考虑样本和特征对距离计算贡献程度的加权欧氏距离;为了确定最佳聚类数目的选取方法,依据改进的加权欧氏距离构造了加权簇内距离和簇间距离。最后,为克服传统K-means聚类目标函数仅考虑簇内的距离而未考虑簇间距离的缺陷,提出基于中位数的轮廓系数的目标函数,进而设计了DCFSK。实验结果表明,在10个基准测试函数上,IDCS的各项指标取得了较优的结果;相较于K-means、DBSCAN(Density-Based Spatial Clustering of Applications with Noise)等算法,在6个合成数据集与6个UCI数据集上,DCFSK的聚类效果最佳。展开更多
The clustering on categorical variables has received intensive attention. In dataset with categorical features, some features show the superior performance on clustering procedure. In this paper, we propose a simple m...The clustering on categorical variables has received intensive attention. In dataset with categorical features, some features show the superior performance on clustering procedure. In this paper, we propose a simple method to find such distinctive features by comparing pooled within-cluster mean relative difference and then partition the data upon such features and give subspace of the subgroups. The applications on zoo data and soybean data illustrate the performance of the proposed method.展开更多
把向量作为空间中的物体展开相似度的评估,分析了向量间各维差值与形状差异的间的近似关系,提出了基于形状相似距离的K-means算法。在三个UCI(University of California,Irvine)标准数据集上的聚类结果表明,对于有关形状信息的数据,基...把向量作为空间中的物体展开相似度的评估,分析了向量间各维差值与形状差异的间的近似关系,提出了基于形状相似距离的K-means算法。在三个UCI(University of California,Irvine)标准数据集上的聚类结果表明,对于有关形状信息的数据,基于形状相似距离的K-means算法比采用传统距离的K-means算法,聚类准确度显著提高。展开更多
基金supported by the 863 National Plan Foundation of China under Grant No.2007AA01Z333 and Special Grand National Project of China under Grant No.2009ZX02204-008.
文摘A leukocyte image fast scanning method based on max min distance clustering is proposed.Because of the lower proportion and uneven distribution of leukocytes in human peripheral blood,there will not be any leukocyte in lager quantity of the captured images if we directly scan the blood smear along an ordinary zigzag scanning routine with high power(100^(x))objective.Due to the larger field of view of low power(10^(x))objective,the captured low power blood smear images can be used to locate leukocytes.All of the located positions make up a specific routine,if we scan the blood smear along this routine with high power objective,there will be definitely leukocytes in almost all of the captured images.Considering the number of captured images is still large and some leukocytes may be redundantly captured twice or more,a leukocyte clustering method based on max-min distance clustering is developed to reduce the total number of captured images as well as the number of redundantly captured leukocytes.This method can improve the scanning eficiency obviously.The experimental results show that the proposed method can shorten scanning time from 8.0-14.0min to 2.54.0 min while extracting 110 nonredundant individual high power leukocyte images.
文摘K-means聚类算法随机确定初始聚类数目,而且原始数据集中含有大量的冗余特征会导致聚类时精度降低,而布谷鸟搜索(CS)算法存在收敛速度慢和局部搜索能力弱等问题,为此提出一种基于自适应布谷鸟优化特征选择的K-means聚类算法(DCFSK)。首先,为提升CS算法的搜索速度和精度,在莱维飞行阶段,设计了自适应步长因子;为调节CS算法全局搜索和局部搜索之间的平衡、加快CS算法的收敛,动态调整发现概率,进而提出改进的动态CS算法(IDCS),在IDCS的基础上构建了结合动态CS的特征选择算法(DCFS)。其次,为提升传统欧氏距离的计算精确度,设计同时考虑样本和特征对距离计算贡献程度的加权欧氏距离;为了确定最佳聚类数目的选取方法,依据改进的加权欧氏距离构造了加权簇内距离和簇间距离。最后,为克服传统K-means聚类目标函数仅考虑簇内的距离而未考虑簇间距离的缺陷,提出基于中位数的轮廓系数的目标函数,进而设计了DCFSK。实验结果表明,在10个基准测试函数上,IDCS的各项指标取得了较优的结果;相较于K-means、DBSCAN(Density-Based Spatial Clustering of Applications with Noise)等算法,在6个合成数据集与6个UCI数据集上,DCFSK的聚类效果最佳。
文摘The clustering on categorical variables has received intensive attention. In dataset with categorical features, some features show the superior performance on clustering procedure. In this paper, we propose a simple method to find such distinctive features by comparing pooled within-cluster mean relative difference and then partition the data upon such features and give subspace of the subgroups. The applications on zoo data and soybean data illustrate the performance of the proposed method.
文摘把向量作为空间中的物体展开相似度的评估,分析了向量间各维差值与形状差异的间的近似关系,提出了基于形状相似距离的K-means算法。在三个UCI(University of California,Irvine)标准数据集上的聚类结果表明,对于有关形状信息的数据,基于形状相似距离的K-means算法比采用传统距离的K-means算法,聚类准确度显著提高。
