K-means Clustering Based on Evolution Strategy

On the Improvement of K-means Clustering Algorithm

一种改进的K-均值聚类算法的研究

Improve k-means algorithms of cluster method by GA

用遗传算法改进聚类分析中的K-平均算法

Furthermore, Bezdek's fuzzy K means algorithms are computationally expensive so that they are impractical in codebook design. So, people have been researching those algorithms which can achieve good performance in the convergent speed of algorithms and the quality of the reconstructed image.

而Bezdek的模糊K-均值算法由于计算量很大，也很少用于矢量量化的设计码书，因此，人们一直在寻找收敛速度和收敛效果两者性能都较好的算法。

In this method, a feature vector is assembled, and an edge preserving filter is used for getting rid of the estimating error, feature space is firstly classified based on K means clustering, the final segmentation is accomplished by using probabilistic relaxation techniques.

在特征划分上，再运用边缘保持的图像滤波对得到的分形维数特征空间进行滤波，滤波结果用K均值簇分类法作特征空间的初分类；

The inter spectral redundancy and intra spectral redundancy can be eliminated mostly by multilevel clustering algorithm with quickly convergent K means classification and the method clearing redundancy at step through enhancing the intra class pixel redundancy.

多层次聚类无损压缩就是利用改进的K-means聚类算法具有快速收敛的特点，和利用分层次去冗余的方法来聚类，因此可最大限度消除残差冗余。

The algorithm uses the result of K means clustering to guide the initiation of fuzzy clustering so that the iteration number of fuzzy clustering can be reduced obviously, thus the speed of fuzzy clustering can be accelerated greatly.

该算法利用K均值聚类结果指导模糊聚类的初始化，使模糊聚类的迭代次数明显减少，从而极大地提高模糊聚类的速度。

In the scheme, the structure of the network is determined by using the optimal K means cluster method posed in this paper, the premise parameters and the weight values are identified by the hybrid algorithms given in this paper.

在该方案中，采用文中提出的优选K均值聚类法辨识该网络的结构，用所给出的混合算法辨识该网络的前件参数和权值。

The evaluations report that compared with K means method, a genetic algorithm based RBF network has the ability of global optimization with a 10% decrease in the spectral distance between the transformed speech and the target speech.

实验结果还说明，与K-均值法相比，用遗传算法训练神经网络可以增强网络的全局寻优能力，使转换语音与目标语音的平均频谱失真距离减小约10%。

In the filtered image feature, application of K means algorithm to cluster features index, then using the Euclidean distance to limit excessive intensive feature points, which are descriptive of the image feature vector.

在得到的过滤后的图像特征中，应用K均值算法对特征进行聚类索引，然后利用欧氏距离来限制过度密集的特征点，从而得到描述图像特征的特征向量。

K means algorithm applied in vector quantization strongly depends on the selection of the initial codebook, and if not given a good initial codebook it can easily be trapped in local minima.

由于传统的K-均值算法在用于矢量量化时强烈依赖初始码书的选取，如果初始码书选取不好，则很容易陷入局部最小点；

The method models the region with the joint histogram of local binary pattern and the labels of K means algorithm, and G-statistic is used to measure the difference of two histograms.

算法采用区域的局部二值模式特征和K均值聚类算法获得的影像标记构建联合直方图，对区域进行建模，采用G统计量度量直方图相似性。

In this paper, an improved K means clustering algorithm is presented to accelerate clustering process with more and more classes becoming stable by judging with neighbor centers nearest to the pixel.

改进后的K-means聚类算法使类内像素只通过和相邻的聚类中心进行距离计算来聚类，由于随着算法的迭代进行，大量类的状态基本固定，因此使得聚类速度不断加快。

Using K Means which can automatically cluster trajectories, a new algorithm based on trajectory space similarity distance is presented, and it is applied to classify trajectory.

应用K均值自动聚类算法，提出了一种新的基于轨迹空间相似距离的轨迹分类算法，对以上获得的有效轨迹进行分类。

In this paper, we use direct classification and K means algorithm to distinguish the high cloud, meddle cloud, low cloud and earth ′ s surface.

应用模式识别中区域聚类法即最近邻简单试探法和K-均值聚类算法来完成高云、中云、低云和地表的区分。

The results illustrate that the best centroids initialization in K means clustering is to select vectors characterized the structure of the dataset.

结果表明：若对基因表达数据进行K-均值聚类分析，最好采用能反映数据结构特征的向量对质心进行初始化。

Experimental results show that this new classifier can realize high quality unsupervised image classification, which outperforms the traditional K means classifier.

实验结果表明，该种分类器能很好地实现对纹理粗糙程度模式的无监督分类，其分类性能要明显好于传统的K均值分类器。

Results Fuzzy K means clustering algorithm can segment white matter, gray matter and CSF better from the MR head images.

结果模糊K－均值聚类算法能很好地分割出磁共振颅脑图像中的灰质、白质和脑脊液。

A data matrix based on the signal gain of cellular networks and some criterion functions are designed for K means clustering.

在聚类分解中，以测试点信号增益矩阵构造聚类分解数据，并给出了收敛判定函数和相似度计算方法。

Fuzzy K means Clustering Algorithm and It's Application Study in Segmentation of MR Head Images

模糊K-均值聚类算法及其在磁共振颅脑图像分割中的应用研究

It also resolves the initial parameter problem of K means algorithm.

而且解决了K-means聚类的参数选择问题。