A genetic algorithm for irregularly shaped spatial scan statistics

A new approach is presented for the detection and inference of irregularly shaped spatial clusters, using a genetic algorithm. Given a map divided into regions with corresponding populations at risk and cases, the graph-related operations are minimized by means of a fast offspring generation and efficient evaluation of Kuldorff's spatial scan statistic. A penalty function based on the geometric non-compactness concept is employed to avoid excessive irregularity of cluster geometric shape. The algorithm is an order of magnitude faster and exhibits less variance compared to the simulated annealing scan, and is more flexible than the elliptic scan. It has about the same power of detection as the simulated annealing scan for mildly irregular clusters and is superior for the very irregular ones. An application to breast cancer clusters in Brazil is discussed.     

Random Walks to Identify Anomalous Free-Form Spatial Scan Windows

Often, it is required to identify anomalous windows reflecting unusual rate of occurrence of a specific event of interest. Spatial scan statistic approach moves scan window over the region and computes the statistic of a parameter(s) of interest, and identifies anomalous windows. While this approach has been successfully employed, earlier proposals suffer from two limitations: (i) In general, the scan window is regular shaped (e.g., circle, rectangle) identifying anomalous windows of fixed shapes only. However, the region of anomaly is not necessarily regular shaped. Recent proposals to identify windows of irregular shapes identify windows larger than the true anomalies, or penalize large windows. (ii) These techniques account for autocorrelation among spatial data, but not spatial heterogeneity often resulting in inaccurate anomalous windows. We propose a random walk based Free-Form Spatial Scan Statistic (FS3). We construct a Weighted Delaunay Nearest Neighbor graph (WDNN) to capture spatial autocorrelation and heterogeneity. Using random walks we identify natural free-form scan windows, not restricted to a predefined shape and prove that they are not random. FS3 on real datasets has shown that it identifies more refined anomalous windows with better likelihood ratio of it being an anomaly as compared to earlier spatial scan statistic approaches.     

Arbitrarily shaped multiple spatial cluster detection for case event data

An original method is proposed for spatial cluster detection of case event data. A selection order and the distance from the nearest neighbour are attributed to each point, once pre-selected points have been taken into account. This distance is weighted by the expected distance under the uniform distribution hypothesis. Potential clusters are located by modelling the multiple structural change of the distances on the selection order and the best model (containing one or several potential clusters) is selected using the double maximum test. Finally a p-value is obtained for each potential cluster. With this method multiple clusters of any shape can be detected.     

Spatial scan statistics in loglinear models

The likelihood ratio spatial scan statistic has been widely used in spatial disease surveillance and spatial cluster detection applications. In order to better understand cluster mechanisms, an equivalent model-based approach is proposed to the spatial scan statistic that unifies currently loosely coupled methods for including ecological covariates in the spatial scan test. In addition, the utility of the model-based approach with a Wald-based scan statistic is demonstrated to account for overdispersion and heterogeneity in background rates. Simulation and case studies show that both the likelihood ratio-based and Wald-based scan statistics are comparable with the original spatial scan statistic.     

A flexible spatial scan test for case event data

A new method is proposed for identifying clusters in spatial point processes. It relies on a specific ordering of events and the definition of area spacings which have the same distribution as one-dimensional spacings. Then the spatial clusters are detected using a scan statistic adapted to the analysis of one-dimensional point processes. This flexible spatial scan test seems to be very powerful against any arbitrarily-shaped cluster alternative. These results have applications in epidemiological studies of rare diseases.     

Permutation-test-based clustering method for detection of dynamic patterns in Spatio-temporal datasets

Massive spatio-temporal data have been collected from the earth observation systems for monitoring the changes of natural resources and environment. To find the interesting dynamic patterns embedded in spatio-temporal data, there is an urgent need for detecting spatio-temporal clusters formed by objects with similar attribute values occurring together across space and time. Among different clustering methods, the density-based methods are widely used to detect such spatio-temporal clusters because they are effective for finding arbitrarily shaped clusters and rely on less priori knowledge (e.g. the cluster number). However, a series of user-specified parameters is required to identify high-density objects and to determine cluster significance. In practice, it is difficult for users to determine the optimal clustering parameters; therefore, existing density-based clustering methods typically exhibit unstable performance. To overcome these limitations, a novel density-based spatio-temporal clustering method based on permutation tests is developed in this paper. High-density objects and cluster significance are determined based on statistical information on the dataset. First, the density of each object is defined based on the local variance and a fast permutation test is conducted to identify high-density objects. Then, a proposed two-stage grouping strategy is implemented to group high-density objects and their neighbors; hence, spatio-temporal clusters are formed by minimizing the inhomogeneity increase. Finally, another newly developed permutation test is conducted to evaluate the cluster significance based on the cluster member permutation. Experiments on both simulated and meteorological datasets show that the proposed method exhibits superior performance to two state-of-the-art clustering methods, i.e., ST-DBSCAN and ST-OPTICS. The proposed method can not only identify inherent cluster patterns in spatio-temporal datasets, but also greatly alleviates the difficulty in selecting appropriate clustering parameters.     

A Bayesian mixture model to quantify parameters of spatial clustering

A new Bayesian approach for quantifying spatial clustering is proposed that employs a mixture of gamma distributions to model the squared distance of points to their second nearest neighbors. The method is designed to answer questions arising in biophysical research on nanoclusters of Ras proteins. It takes into account the presence of disturbing metacluster structures as well as non-clustering objects, both common among Ras clusters. Its focus lies on estimating the proportion of points lying in clusters, the mean cluster size and the mean cluster radius without depending on prior knowledge of the parameters. The performance of the model compared to other cluster methods is demonstrated in a comprehensive simulation study, employing a specific new class of spatial point processes, the double Matérn cluster process. Further results and arguments as well as data and code are available as supplementary material.     

基于服务簇的空间信息服务自动发现

现有Web服务自动发现方法中存在服务匹配程度区分不明显、服务发现精度不高等问题。为此,提出一种基于服务簇的空间信息服务自动发现算法。对发布的空间信息服务进行聚类分析,计算服务请求与各服务簇中心的相似度,由此确定最优匹配簇,根据服务请求与最优匹配簇中服务的语义相似度,得出服务请求的最优匹配服务。实验结果表明,该算法在实现对Web服务匹配程度定量表示的同时,能有效提高匹配程度的区分度和服务发现的查全率和效率。     

视频数据库的聚类索引方法

理想的视频库组织方法应该把语义相关并且特征相似的视频的特征向量相邻存储.针对大规模视频库的特点,在语义监督下基于低层视觉特征对视频库进行层次聚类划分,当一个聚类中只包含一个语义类别的视频时,为这个聚类建立索引项,每个聚类所包含的原始特征数据在磁盘上连续存储.统计低层特征和高层特征的概率联系,构造Bayes分类器.查询时对用户的查询范例,首先确定最可能的候选聚类,然后在候选聚类范围内查询相似视频片段.实验结果表明,文中的方法不仅提高了检索速度而且提高了检索的语义敏感度.     

Determination of the appropriate parameters for K‐means clustering using selection of region clusters based on density DBSCAN (SRCD‐DBSCAN)

K‐means clustering can be highly accurate when the number of clusters and the initial cluster centre are appropriate. An inappropriate determination of the number of clusters or the initial cluster centre decreases the accuracy of K‐means clustering. However, determining these values is problematic. To solve these problems, we used density‐based spatial clustering of application with noise (DBSCAN) because it does not require a predetermined number of clusters; however, it has some significant drawbacks. Using DBSCAN with high‐dimensional data and data with potentially different densities decreases the accuracy to some degree. Therefore, the objective of this research is to improve the efficiency of DBSCAN through a selection of region clusters based on density DBSCAN to automatically find the appropriate number of clusters and initial cluster centres for K‐means clustering. In the proposed method, DBSCAN is used to perform clustering and to select the appropriate clusters by considering the density of each cluster. Subsequently, the appropriate region data are chosen from the selected clusters. The experimental results yield the appropriate number of clusters and the appropriate initial cluster centres for K‐means clustering. In addition, the results of the selection of region clusters based on density DBSCAN method are more accurate than those obtained by traditional methods, including DBSCAN and K‐means and related methods such as Partitioning‐based DBSCAN (PDBSCAN) and PDBSCAN by applying the Ant Clustering Algorithm DBSCAN (PACA‐DBSCAN).