The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Automated collaborative filtering has become a popular technique for reducing information overload. We have developed a new method for recommending items using multiple agents. The agents were established by employing the fuzzy C-means clustering technique. We employ these agents collaborating each other to get recommendation for users. The results were evaluated by using MovieLens movie's rating...
The Kohonen self organizing map (SOM) is an excellent tool in exploratory phase of data mining. The SOM is a popular tool that maps a high-dimensional space onto a small number of dimensions by placing similar elements close together, forming clusters. When the number of SOM units is large, to facilitate quantitative analysis of the map and the data, similar units needs to be grouped i.e., clustered...
To identify a person using his/her handwriting; it is necessary to analyze a set of handwritings. Because of special styles of Persian handwritten; identifying Persian handwriting needs different approaches in compare with to other languages. This paper introduces a writer identification method to identify the writer of a Persian handwritten text. In the proposed method, the fuzzy approach is applied...
Wireless spoofing attacks are easy to launch and can significantly impact the performance of networks. Although the identity of a node can be verified through cryptographic authentication, conventional security approaches are not always desirable because of their overhead requirements. In this paper, we propose to use location information, a physical property associated with each node, hard to falsify,...
The paper gives a validity analysis on an automatic dynamic electrocardiogram (Holter) waveform selection strategy. The strategy was based on machine learning techniques. And the data used in analysis are from clinic. The analysis showed that 93% can be reached in clustering phase, and 92% in classification phase. Although the result was not very satisfied, it was a good trying in this study area...
Clustering is one of the most important analysis tasks in spatial databases. However, in many real applications, it is more meaningful constrained clustering objects on a spatial network (e.g. road network including traffic information). The existing methods don't refer to the constrained condition. It is therefore difficult to apply them to a real road network. This paper proposes the model of clustering...
This paper examines the recovery of user context in indoor environmnents with existing wireless infrastructures to enable assistive systems. We present a novel approach to the extraction of user context, casting the problem of context recovery as an unsupervised, clustering problem. A well known density-based clustering technique, DBSCAN, is adapted to recover user context that includes user motion...
Localization of sensor nodes is one of the key issues in wireless sensor networks. Next to the ability, to assign a phenomenon to a position, localization is a precondition for sensor network algorithms like geographic clustering and routing. A simple approach for coarse grained localization is centroid localization (CL), which was firstly presented by Bulusu et al. and assumes regularly arranged...
Random rotation is one of the common perturbation approaches for privacy preserving data classification, in which the data matrix is multiplied by a random rotation matrix before publishing in order to preserve data privacy. One distinct advantage of this approach is that it can maintain the geometric properties of the data matrix, so several categories of classifiers that are based on the geometric...
RF-based transceiver-free object tracking, originally proposed by the authors, allows real-time tracking of a moving object, where the object does not have to be equipped with an RF transceiver. Our previous algorithm, the best cover algorithm, suffers from a drawback, i.e., it does not work well when there are multiple objects in the tracking area. In this paper, we propose a localization model of...
The clustering agglomerative hierarchical algorithm for date grouping is considered. To reduce algorithmic complexity without accuracy losses an approach with the speed and accuracy coefficient is proposed. Some results with quality characteristics of clustered data are presented.
The basic K-means is sensitive to the initial centre and easy to get stuck at local optimal value. To solve such problems, a new clustering algorithm is proposed based on simulated annealing. The algorithm views the clustering as optimization problem, the bisecting K-means splits the dataset into k clusters at first, and then run simulated annealing algorithm using the sum of distances between each...
In this paper, we describe a new clustering-based classification technique (eVQ-Class), which is able to adapt old clusters and to evolve new ones on-line with new incoming data samples. It extends the conventional learning vector quantization approach, which is a kind of supervised version of original vector quantization, in mainly three points: 1.) it is able toevolve new clusters on demand by comparing...
The principle advantage and shortcoming of quantum clustering algorithm (QC) is analyzed. Based on its shortcomings, an improved algorithm - exponent distance-based quantum clustering algorithm (EQDC) is produced. It improved the iterative procedure of QC algorithm and used exponent distance formula to measure the distance between data points and the cluster centers. Experimental results demonstrate...
In this paper, the clustering analysis method is used in the optimization of observed gravity data during the computation of local geoid, while the two slopes of terrain data can be utilized as criteria. Further, a numerical experiment is carried out in hill area. Compared with the result from non-deleted observed gravity data, the deleted data can still work out acceptable result of similar precision...
Threshold selection is an important topic and also a critical preprocessing step, which directly affects the accuracy of the clustering in a road network. This paper analyzes the necessity of multiple thresholds selection in a road network, extracts the similar nature of the objects, proposes firstly the scheme of multiple thresholds based on support vector regression (SVR) and improves on the existing...
Clustering is an important approach to the analysis of DNA microarray data. In this paper, we develop a new algorithm that can cluster DNA microarray data with a graph cut based algorithm. The algorithm can generate a list of clustering results with statistically significant likelihood. It can thus resolve the issue where a gene product may participate in different subsets of co-expressed genes. Our...
Data clustering is an important technique for exploratory data analysis, and has been studied for many years. The existing clustering methods are all designed in attribute-value setting or first-order logic setting. However, attribute-value language can not describe complex structured data. First-order logic can represent certain complex structured data, but both scalability and efficiency of clustering...
In order to set the weights of weighted support vector machine, the method that based the clustering vector was proposed in this paper. The clustering vector was brought in and the weights were set by calculating the distances between the data of every class and their clustering vector. In SVM, the data were mapped into a higher dimensional feature space and the distribution of data was changed, so...
In this paper we present the recommender systems that use the k-means clustering method in order to solve the problems associated with neighbor selection. The first method is to solve the problem in which customers belong to different clusters due to the distance-based characteristics despite the fact that they are similar customers, by properly converting data before performing clustering. The second...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.