We develop a flexible model-based procedure for clustering functional data. The technique can be applied to all types of curve data but is particularly useful when individuals are observed at a sparse set of time points. In addition to producing final cluster assignments, the procedure generates predictions and confidence intervals for missing portions of curves. Our approach also provides many useful tools for evaluating the resulting models. Clustering can be assessed visually via low dimensional representations of the curves, and the regions of greatest separation between clusters can be determined using a discriminant function. Finally, we extend the model to handle multiple functional and finite dimensional covariates and show how it can be applied to standard finite dimensional clustering problems involving missing data.

The creation of complex virtual worlds has expanded from the domain of designers and animators to that of general users with no background in computer graphics. Example applications are military simulations, urban planning, landscape design, search and rescue simulations, and social media technologies such as “Second Life”. In many cases the user wants to create content containing hundreds or thousands of similar objects. Modelling and placing each individual object is infeasible and new ways must be found to allow users to easily specify the distribution of a large number of objects. In this paper we introduce a sketch-based approach for crowd modelling, which is intuitive and suitable for different input devices such as mice, sketch pads, and touch screens (Windows 7). We derive design requirements by analysing real environments and by testing users ’ abilities to characterise crowds and collections/accumulations of objects. Based on these requirements we formulate a model-by-example approach in which users sketch a sample distribution of objects and our tool computes the complete “population ” of objects over a domain specified with a sketched contour. In order to deal with different distribution patterns we first characterise the input and then use clustering and texture synthesis to replicate the characteristics over the domain. Initial results demonstrate that the tool gives plausible results for random, regular and clustered input and that it can be used in a wide variety of modelling applications. 1

For many clustering algorithms, such as k-means, EM, and CLOPE, there is usually a requirement to set some parameters. Often, these parameters directly or indirectly control the number of clusters to return. In the presence of di#erent data characteristics and analysis contexts, it is often di#cult for the user to estimate the number of clusters in the data set. This is especially true in text collections such as Web documents, images or biological data. The fundamental question this paper addresses is: "How can we e#ectively estimate the natural number of clusters in a given text collection?". We propose to use spectral analysis, which analyzes the eigenvalues (not eigenvectors) of the collection, as the solution to the above. We first present the relationship between a text collection and its underlying spectra. We then show how the answer to this question enhances the clustering process. Finally, we conclude with empirical results and related work.

Abstract. In this paper, we present a new kernel for unordered sets of data of the same type. It works by first fitting a set with a Gaussian mixture, then evaluate an efficient kernel on the two fitted Gaussian mixtures. Furthermore, we show that this kernel can be extended to sets embedded in a feature space implicitly defined by another kernel, where Gaussian mixtures are fitted with the kernelized EM algorithm [6], and the kernel for Gaussian mixtures are modified to use the outputs from the kernelized EM. All computation depends on data only through their inner products as evaluations of the base kernel. The kernel is computable in closed form, and being able to work in a feature space improves its flexibility and applicability. Its performance is evaluated in experiments on both synthesized and real data. 1

Abstract not found

Image segmentation plays a significant role in computer vision. It aims at extracting meaningful objects lying in the image. Generally there is no unique method or approach for image segmentation. Clustering is a powerful technique that has been reached in image segmentation. The cluster analysis is to partition an image data set into a number of disjoint groups or clusters. The clustering methods such as k means, improved k mean, fuzzy c mean (FCM) and improved fuzzy c mean algorithm (IFCM) have been proposed. K means clustering is one of the popular method because of its simplicity and computational efficiency. The number of iterations will be reduced in improved K compare to conventional K means. FCM algorithm has additional flexibility for the pixels to belong to multiple classes with varying degrees of membership. Demerit of conventional FCM is time consuming which is overcome by improved FCM. The experimental results exemplify that the proposed algorithms yields segmented gray scale image of perfect accuracy and the required computer time reasonable and also reveal the improved fuzzy c mean achieve better segmentation compare to others. The quality of segmented image is measured by statistical parameters: rand index (RI), global consistency error (GCE), variations of information (VOI) and boundary displacement error (BDE). Keywords K means, improved k means, fuzzy c means, improved c means, rand index, global consistency error, variations of information 1.

functional images

functional images

Using iterative cluster merging with improved gap statistics to perform online phenotype discovery in the context of high-throughput RNAi screens

Abstract—The machine learning and pervasive sensing technologies found in smart homes offer unprecedented opportunities for providing health monitoring and assistance to individuals experiencing difficulties living independently at home. In order to monitor the functional health of smart home residents, we need to design technologies that recognize and track activities that people normally perform as part of their daily routines. Although approaches do exist for recognizing activities, the approaches are applied to activities that have been pre-selected and for which labeled training data is available. In contrast, we introduce an automated approach to activity tracking that identifies frequent activities that naturally occur in an individual’s routine. With this capability we can then track the occurrence of regular activities to monitor functional health and to detect changes in an individual’s patterns and lifestyle. In this paper we describe our activity mining and tracking approach and validate our algorithms on data collected in physical smart environments.