Sharif Digital Repository

Purpose: The main purpose of this study is to review the knowledge management literature from a content-related perspective using cluster analysis. Design/methodology/approach: A critical analysis of previous review articles in KM provided a conceptual framework with nine dimensions. A survey was then administered to 120 KM authors asking them to review which dimensions they considered in their own research. Findings: Three clusters of KM research were identified as follows: the socialization school, the collaboration school, and the codification school. Research limitations/implications: The study does not consider the dimension of strategic versus operational KM issues nor does it consider... 

This study was a prototype segmentation of Iran's inbound tourism market with a concentration on culture. The focus of this paper was to introduce a step by step description of the methodology used to segment Iran's inbound tourism market. In the first phase, cluster analysis was employed to segment the entire market based on two dimensions of tourists' expenditure and cultural traits. In the second phase, the resulting clusters were divided into further subgroups using a common sense approach. Additional variables were utilised to profile the segments, and finally, the segmentation process was verified through outcome analysis  

Construction of two haplotypes from a set of Single Nucleotide Polymorphism (SNP) fragments is called haplotype reconstruction problem. One of the most popular computational model for this problem is Minimum Error Correction (MEC). Since MEC is an NP-hard problem, here we propose a novel heuristic algorithm based on clustering analysis in data mining for haplotype reconstruction problem. Based on hamming distance and similarity between two fragments, our iterative algorithm produces two clusters of fragments; then, in each iteration, the algorithm assigns a fragment to one of the clusters. Our results suggest that the algorithm has less reconstruction error rate in comparison with other... 

Clustering the web documents is one of the most important approaches for mining and extracting knowledge from the web. Recently, one of the most attractive trends in clustering the high dimensional web pages has been tilt toward the learning and optimization approaches. In this paper, we propose novel hybrid harmony search (HS) based algorithms for clustering the web documents that finds a globally optimal partition of them into a specified number of clusters. By modeling clustering as an optimization problem, first, we propose a pure harmony search-based clustering algorithm that finds near global optimal clusters within a reasonable time. Then, we hybridize K-means and harmony clustering... 

Data gathering is a common but critical operation in many applications of wireless sensor networks. Innovative techniques that improve energy efficiency to prolong the network lifetime are highly required. Clustering is an effective topology control approach in wireless sensor networks, which can increase scalability and lifetime. These networks require robust wireless communication protocols that are energy efficient and provide low latency. In this paper, we develop and analyze an efficient cooperative transmission protocol with robust clustering (RCCT) for sensor networks that considers a fault-tolerant and energy-efficient distributed clustering with minimum overhead. RCCT distributes... 

There is a growing interest in developing high-performance sensors monitoring organophosphate pesticides, primarily due to their broad usage and harmful effects on mammals. In the present study, a colorimetric sensor array consisting of citrate-capped 13 nm gold nanoparticles (AuNPs) has been proposed for the detection and discrimination of several organophosphate pesticides (OPs). The aggregation-induced spectral changes of AuNPs upon OP addition has been analyzed with pattern recognition techniques, including hierarchical cluster analysis (HCA) and linear discriminant analysis (LDA). In addition, the proposed sensor array has the capability to identify individual OPs or mixtures of them in... 

We first propose a quantitative approach to detect high risk outbreaks of independent and coinfective SIR dynamics on three empirical networks: A school, a conference and a hospital contact network. This measurement is based on the k-means clustering method and identifies proper samples for calculating the mean outbreak size and the outbreak probability. Then we systematically study the impact of different temporal correlations on high risk outbreaks over the original and differently shuffled counterparts of each network. We observe that, on the one hand, in the coinfection process, randomization of the sequence of the events increases the mean outbreak size of high-risk cases. On the other... 

Recently query log mining is extensively used by web information systems. In this paper a new hierarchical co-clustering for queries and URLs of a search engine log is introduced. In this method, firstly we construct a bipartite graph for queries and visited URLs, and then to discover noiseless clusters, all queries and related URLs are projected in a reduced dimensional space by applying singular value decomposition. Finally, all queries and URLs are iteratively clustered for constructing hierarchical categorization. The method has been evaluated using a real world data set and shows promising results. © Springer-Verlag Berlin Heidelberg 2007  

In this article the methodology proposed by Li and Wang for mixed qualitative and quantitative modeling and simulation of temporal behavior of processing unit is reexamined and extended to more complex case. The main issue of their approach considers the multivariate statistics of principal component analysis (PCA), along with clustered fuzzy digraphs and reasoning. The PCA and fuzzy clustering provide tools to categorize the quantitative dynamic trends, describing the temporal behavior of joint human-process interactions qualitatively, and through the proposed neuro-fuzzy reasoning the system responses can be obtained when the system is exposed to uncertain disturbances. First, the method... 

This study proposes an approach for improving service reliability in the distribution network based on establishing competition among electric distribution utilities. The idea behind this approach is to categorise the utilities and compare the performance of utilities located in one cluster with the other members of the same cluster. The reward/penalty mechanism (RPM) as a quality regulating instrument is designed for each cluster and used to penalise the utilities with a performance worse than the benchmark and to reward them for providing a performance better than the benchmark. Based on the RPM, utilities located in one cluster compete to make more profit by serving customers in better... 

We propose a graph-based data clustering algorithm which is based on exact clustering of a minimum spanning tree in terms of a minimum isoperimetry criteria. We show that our basic clustering algorithm runs in O(nlogn) and with post-processing in almost O(nlogn) (average case) and O(n2) (worst case) time where n is the size of the data-set. It is also shown that our generalized graph model, which also allows the use of potentials at vertices, can be used to extract an extra piece of information related to anomalous data patterns and outliers. In this regard, we propose an algorithm that extracts outliers in parallel to data clustering. We also provide a comparative performance analysis of... 

Identifying clusters is an important aspect of analyzing large datasets. Clustering algorithms classically require access to the complete dataset. However, as huge amounts of data are increasingly originating from multiple, dispersed sources in distributed systems, alternative solutions are required. Furthermore, data and network dynamicity in a distributed setting demand adaptable clustering solutions that offer accurate clustering models at a reasonable pace. In this paper, we propose GoScan, a fully decentralized density-based clustering algorithm which is capable of clustering dynamic and distributed datasets without requiring central control or message flooding. We identify two major... 

This study proposes an approach for improving service reliability in the distribution network based on establishing competition among electric distribution utilities. The idea behind this approach is to categorise the utilities and compare the performance of utilities located in one cluster with the other members of the same cluster. The reward/penalty mechanism (RPM) as a quality regulating instrument is designed for each cluster and used to penalise the utilities with a performance worse than the benchmark and to reward them for providing a performance better than the benchmark. Based on the RPM, utilities located in one cluster compete to make more profit by serving customers in better... 

Nanoparticles (NPs) are increasingly being used in different branches of science and in industrial applications; however, their rapid detection and characterization at low concentration levels have remained a challenge; more specifically, there is no single technique that can characterize the physicochemical properties of NPs (e.g. composition and size). In this work we have developed a colorimetric sensor array for defining the physicochemical properties of NPs in aqueous solution with ultra-low concentrations (e.g. 10-7g ml-1 for gold NPs). Various NPs were readily identified using a standard chemometric approach (i.e. hierarchical clustering analysis), with no misclassifications over 400... 

One of the important problems in knowledge discovery from data is clustering. Clustering is the problem of partitioning a set of data using unsupervised techniques. An important characteristic of a clustering technique is the shape of the cluster it can find. Clustering methods which are capable to find simple cluster shapes are usually fast but inaccurate for complex data sets. Ones capable to find complex cluster shapes are usually not fast but accurate. In this paper, we propose a simple clustering technique named circlusters. Circlusters are circles partitioned into different radius sectors. Circlusters can be used to create hybrid approaches with density based or partitioning based... 

One of the major problems in underdetermined Sparse Component Analysis (SCA) in the field of (semi) Blind Source Separation (BSS) is the appropriate estimation of the mixing matrix, A, in the linear model X = AS, especially where more than one source is active at each instant of time. Most existing algorithms require the restriction that at each instant (i.e. in each column of the source matrix S), there is at most one single dominant component. Moreover, these algorithms require that the number of sources must be determined in advance. In this paper, we proposed a new algorithm for estimating the matrix A, which does not require the restriction of single dominant source at each instant.... 

Most of clustered models in wireless sensor networks use a double-layered structure. In these structures a node is considered as cluster-head and has the responsibility of gathering information of environment. Static attribute is the main disadvantage of these clustering method. because as traffic rises in environment as time passes, cluster-head nodes energy and its close nodes, is consumed rapidly and so these nodes that has important role in data gathering, are break down. This issue is considered as age decrease in network life time and finally, network death. In this paper, a new three-layered dynamic model is introduced that its main goal is to increase network life time. The dynamic... 

Most positions of the human genome are typically invariant (99%) and only some positions (1%) are commonly variant which are associated with complex genetic diseases. Haplotype reconstruction is to divide aligned SNP fragments, which is the most frequent form of difference to address genetic diseases, into two classes, and thus inferring a pair of haplotypes from them. Minimum error correction (MEC) is an important model for this problem but only effective when the error rate of the fragments is low. MEC/GI as an extension to MEC employs the related genotype information besides the SNP fragments and so results in a more accurate inference. The haplotyping problem, due to its NP-hardness, may...