Sharif Digital Repository

Clustering has become an increasingly important task in modern application domains. Targeting useful and relevant information on the World Wide Web is a topical and highly complicated research area. Clustering techniques have been applied to categorize documents on web and extracting knowledge from the web. In this paper we propose novel clustering algorithms based on Harmony Search (HS) optimization method that deals with web document clustering. By modeling clustering as an optimization problem, first, we propose a pure HS based clustering algorithm that finds near global optimal clusters within a reasonable time. Then we hybridize K-means and harmony clustering to achieve better... 

In this paper we introduce a preprocessing method to reduce noise effects in noise prone environments. Prototype based clustering algorithms are sensitive to noise because the effect of noisy data are as same as effect of true data and this affects on calculation of clusters center and then reduces accuracy. Therefore, these algorithms can not be applied in noise-prone environments and if this is applied there, we can not trust to the results. To overcome such problems we reduce and in some cases eliminate the noisy data. Also a part of our method is applied on the source of generated data in a network. Then noisy data that the number of them is high in noisy environments are eliminated and... 

Recently, several algorithms have been introduced for enhancing clustering quality by using supervision in the form of constraints. These algorithms typically utilize the pair wise constraints to either modify the clustering objective function or to learn the clustering distance measure. Very few of these algorithms show the ability of discovering clusters of different shapes along with satisfying the provided constraints. In this paper, a novel semi-supervised clustering algorithm is introduced that uses the side information and finds clusters of arbitrary shapes. This algorithm uses a two-stage clustering approach satisfying the pair wise constraints. In the first stage, the data points... 

Clustering is the problem of partitioning a (large) set of data using unsupervised techniques. Today, there exist many clustering techniques. The most important characteristic of a clustering technique is the shape of the cluster it can find. In this paper, we propose a method that is capable to find arbitrary shaped clusters and uses simple geometric constructs, Circlusters. Circlusters are different radius sectored circles. Circlusters can be used to create many hybrid approaches in mixture with density based or partitioning based methods. We also proposed two new clustering methods that are capable to find complex clusters in O(n), where n is the size of the data set. Both of the methods... 

A set of small battery-operated sensors with low-power transceivers that can automatically form a network and collect some desired physical characteristics of the environment is called a wireless sensor network. The communications must be designed to conserve the limited energy resources of the sensors [14].By clustering sensors we can save energy. In this paper, we introduce a new concept called "Center of Energy Mass" which is a combination of both energy level and location of the nodes which is used to form the new factor of "distance of the nodes to the CEM ".Distance of the nodes to the CEM is used together with Probability Density Function of the normal distribution in optimizing... 

Clustering is currently one of the most crucial techniques for dealing with massive amount of heterogeneous information on the web, which is beyond human being's capacity to digest. Recent studies have shown that the most commonly used partitioning-based clustering algorithm, the K-means algorithm, is more suitable for large datasets. However, the K-means algorithm can generate a local optimal solution. In this paper we present novel harmony search clustering algorithms that deal with documents clustering based on harmony search optimization method. By modeling clustering as an optimization problem, first, we propose a pure harmony search based clustering algorithm that finds near global... 

The rapid increase of information on the web makes it necessary to improve information management techniques. One of the most important techniques is clustering web data. In this paper, we propose a new 3-phase clustering method that finds dense units in a data set using density-based algorithms. The distances in the dense units are stored in order in structures such as a min heap. In the extraction stage, these distances are extracted one by one, and their effects on the clustering process are examined. Finally, in the combination stage, clustering is completed using improved versions of well-known single and average linkage methods. All steps of the methods are performed in O(n log n) time... 

One of the most famous approaches for the segmentation of color images is finding clusters in the color space. Shapes of these clusters are often complex and the time complexity of the existing algorithms for finding clusters of different shapes is usually high. In this paper, a novel clustering algorithm is proposed and used for the image segmentation purpose. This algorithm distinguishes clusters of different shapes using a two-stage clustering approach in a reasonable time. In the first stage, the mean-shift clustering algorithm is used and the data points are grouped into some sub-clusters. In the second stage, connections between sub-clusters are established according to a dissimilarity... 

Using word base n-gram language models in continuous speech recognition systems is so prevalent. For using this type of language models, we should extract them from large corpora. Since Persian corpora are not rich, therefore the extracted language models are not credible. For this reason, most researchers extract class n-grams instead of finding word n-grams. In this research a new idea for fuzzy word clustering is represented that each word can be assigned to more that one class. The Fuzzy c-mean algorithm is used for our clustering method and we have examined its various parameters of it. Finally, this algorithm was applied on 20000 most frequent Persian words extracted from "Persian Text... 

Electromyogram (EMG) signal is an electrical manifestation of muscle contractions. EMG signal collected from surface of the skin, a non-invasive bioelectric signal, can be used in different rehabilitation applications and artificial extremities control. This study has proposed to utilize the surface EMG (SEMG) signal to recognize patterns of hand prosthesis movements. It suggests using an adaptive neuro-fuzzy inference system (ANFIS) to identify motion commands for the control of a prosthetic hand. In this work a hybrid method for training fuzzy system, consisting of back-propagation (BP) and least mean square (LMS) is utilized. Also in order to optimize the number of fuzzy rules, a... 

Background: Electromyography (EMG) is the study of muscle function through the inquiry of electrical signals that the muscles emanate. EMG signals collected from the surface of the skin (Surface Electromyogram: sEMG) can be used in different applications such as recognizing musculoskeletal neural based patterns intercepted for hand prosthesis movements. Current systems designed for controlling the prosthetic hands either have limited functions or can only be used to perform simple movements or use excessive amount of electrodes in order to achieve acceptable results. In an attempt to overcome these problems we have proposed an intelligent system to recognize hand movements and have provided... 

Single Nucleotide Polymorphisms (SNPs), a single DNA base varying from one individual to another, are believed to be the most frequent form responsible for genetic differences. Genotype is the conflated information of a pair of haplotypes on homologous chromosomes. Although haplotypes have more information for disease associating than individual SNPs and genotype, it is substantially more difficult to determine haplotypes through experiments. Hence, computational methods which can reduce the cost of determining haplotypes become attractive alternatives. MEC, as a standard model for haplotype reconstruction, is fed by fragments as input to infer the best pair of haplotypes with minimum error... 

In this paper we propose a new method for estimating the mixing matrix, A, in the linear model X = AS, for the problem of underdetermined Sparse Component Analysis (SCA). Contrary to most existing algorithms, in the proposed algorithm there may be more than one active source at each instant (i.e. in each column of the source matrix S), and the number of sources is not required to be known in advance. Since in the cases where more than one source is active at each instant, data samples concentrate around multidimensional subspaces, the idea of our method is to first estimate these subspaces and then estimate the mixing matrix from these estimated subspaces. ©2007 IEEE  

This paper presents an energy-efficient communication protocol which distributes a uniform energy load to the sensors in a wireless microsensor network. This protocol, called Distance-Based Segmentation (DBS), is a clusterbased protocol that divides the entire network into equalarea segments and applies different clustering policies to each segment to reduce total energy dissipation and hence prolong the lifetime of the network. To evaluate the DBS protocol, a simulator was implemented using the MATLAB software. Simulation results show that the DBS can achieve as much as 16% reduction in total dissipated energy as compared with conventional protocols. In addition this protocol is able to... 

In this paper we propose a content-based text and image retrieval architecture using Fuzzy Adaptive Resonance Theory neural network. This method is equipped with an unsupervised mechanism for dynamic data clustering to deal with incremental information without metadata such as in web environment. Results show noticeable average precision and recall over search results. © 2006 IEEE  

In this paper, it is shown that independent component analysis (ICA) of sparse signals (sparse ICA) can be seen as a cluster-wise principal component analysis (PCA). Consequently, Sparse ICA may be done by a combination of a clustering algorithm and PCA. For the clustering part, we use, in this paper, an algorithm inspired from K-means. The final algorithm is easy to implement for any number of sources. Experimental results points out the good performance of the method, whose the main restriction is to request an exponential growing of the sample number as the number of sources increases. © 2006 Elsevier B.V. All rights reserved