With the coming era of astronomic data with mass, high dimensionality and nonlinearity, clustering astronomic data becomes more and more important. This paper proposed a new clustering algorithm, which reduces the spa...
详细信息
ISBN:
(纸本)9781509048403
With the coming era of astronomic data with mass, high dimensionality and nonlinearity, clustering astronomic data becomes more and more important. This paper proposed a new clustering algorithm, which reduces the space and time complexity and the sensitivity to the parameters. It is suitable for processing large scale astronomic data sets. The new algorithm consists of three phases: coarsening clustering, representative data clustering and merging. First, we use affinitypropagation (AP) algorithm for coarsening. Specifically, in order to save the space and computational cost, we only compute the similarity between each point and its t nearest neighbors, and get a coarsened similarity matrix (with only t columns, where t << N and N is the number of data points). Second, to further improve the efficiency and effectiveness of the proposed algorithm, the Find of Density Peaks Clustering (FDP) is used to divide the representative points gotten in the first phase. Third, we can get the classes of all data by merging the results of the first two steps. The experimental results show the proposed algorithm can realize the clusters quickly and precisely for the classification of stars/ galaxies using Sloan Digital Sky Survey (SDSS), and is more efficient than the compared algorithms AP, and FDP.
Current approaches to single-cell transcriptomic analysis are computationally intensive and require assay-specific modeling, which limits their scope and generality. We propose a novel method that compares and cluster...
详细信息
Current approaches to single-cell transcriptomic analysis are computationally intensive and require assay-specific modeling, which limits their scope and generality. We propose a novel method that compares and clusters cells based on their transcript-compatibility read counts rather than on the transcript or gene quantifications used in standard analysis pipelines. In the reanalysis of two landmark yet disparate single-cell RNA-seq datasets, we show that our method is up to two orders of magnitude faster than previous approaches, provides accurate and in some cases improved results, and is directly applicable to data from a wide variety of assays.
A discriminative reference-based method for scene image categorization is presented in this letter. Reference-based image classification approach combined with K-SVD is approved to be a simple, efficient, and effectiv...
详细信息
A discriminative reference-based method for scene image categorization is presented in this letter. Reference-based image classification approach combined with K-SVD is approved to be a simple, efficient, and effective method for scene image categorization. It learns a subspace as a means of randomly selecting a reference-set and uses it to represent images. A good reference-set should be both representative and discriminative. More specifically, the reference-set subspace should well span the data space while maintaining low redundancy. To automatically select reference images, we adapt affinity propagation algorithm based on data similarity to gather a reference-set that is both representative and discriminative. We apply the discriminative reference-based method to the task of scene categorization on some benchmark datasets. Extensive experiment results demonstrate that the proposed scene categorization method with selected reference set achieves better performance and higher efficiency compared to the state-of-the-art methods.
Track association of multi-target has been recognized as one of the key technologies in distributed multiple-sensor data fusion system,and its accuracy directly impacts on the performance of the whole tracking system....
详细信息
Track association of multi-target has been recognized as one of the key technologies in distributed multiple-sensor data fusion system,and its accuracy directly impacts on the performance of the whole tracking system.A multi-sensor data association is proposed based on aftinity propagation(AP)*** proposed method needs an initial similarity,a distance between any two points,as a parameter,therefore,the similarity matrix is calculated by track position,velocity and azimuth of track *** approach can automatically obtain the optimal classification of uncertain target based on clustering validity ***,the same kind of data are fused based on the variance of measured data and the fusion result can be taken as a new measured data of the ***,the measured data are classified to a certain target based on the nearest neighbor ideas and its characteristics,then filtering and target tracking are *** experimental results show that the proposed method can effectively achieve multi-sensor and multi-target track association.
With increasing applications of large-scale networks, fully distributed and self-organized clustering algorithms have attracted much attention recently. In this paper, we review the capacitated network decomposition p...
详细信息
ISBN:
(纸本)9781479941452
With increasing applications of large-scale networks, fully distributed and self-organized clustering algorithms have attracted much attention recently. In this paper, we review the capacitated network decomposition problem that aims to minimize the cut weight. As an extension of our previous work [1], we propose a novel belief propagation based distributed clustering algorithm, which allows each node to select one or multiple co-cluster nodes by sending messages between pairs of nodes. Based on the max-product algorithm, we derive the message-passing procedure on the corresponding factor graph. The distributed clustering algorithm is also extended for a hierarchical structure. Simulation results show that our algorithm can efficiently find a capacitated network decomposition solution, and it outperforms the popular affinity propagation algorithm in some applications.
Aim to the weak intelligence and humanity of current electric nursing-bed control modes, the recommended movement control mode is proposed, which is based on the existing manual, timing and speech control pattern. Fir...
详细信息
ISBN:
(纸本)9783037857502
Aim to the weak intelligence and humanity of current electric nursing-bed control modes, the recommended movement control mode is proposed, which is based on the existing manual, timing and speech control pattern. First, on the basis of accumulating some control data, the affinity propagation algorithm (AP algorithm) is employed to cluster in order to acquire the clustering centers, which reflect the prefer movement and corresponding value at special time of the special user. Then, according to the mechanical and electric constraints, some rules are established to adjust the clustering centers. And the nursing-bed movement sequence is obtained, which is logical. Finally, the rationality of the recommended movement sequence is analyzed according to the distribution characteristic of the dataset. The movement sequence that passes the rationality analysis will be recommended to the user and automatically saved as the recommended pattern. The experimental results show that the recommended movement sequence can basically reflect the user's habits, which is more intelligent and human than other control modes.
A wide number of reports and news on crimes, increasingly conducted almost every day, have resulted in making detection of such crimes more difficult if not complex. Therefore, the need for detecting and identifying s...
详细信息
A wide number of reports and news on crimes, increasingly conducted almost every day, have resulted in making detection of such crimes more difficult if not complex. Therefore, the need for detecting and identifying such crimes emerges as a necessary way of detecting and identifying such crime patterns on the news. Document Clustering have been increasingly becoming an important task for obtaining good results with the unsupervised learning methods. It aims to automatically group similar documents in one cluster using different types of extractions and cluster algorithms. There are ongoing works done to improve Document Clustering techniques such as Extractions and Clustering approaches to overcome the difficulty in designing a general purpose document clustering for crime investigation and the ill posed problem of extraction and clustering. This paper discusses two major sequential stages in Document Clustering “Extraction Features and Clustering algorithms” as well as the major challenges and the key issues in designing extraction features and clustering algorithms. In addition, the following approach assists the law enforcement officers and detectives to enhance performance and speed up the process of solving crimes.
When support vector machine (SVM) classifier is applied to image semantic annotation, it usually encounters the problem of excessive training samples. In this paper, we propose a novel method, which is by combining le...
详细信息
When support vector machine (SVM) classifier is applied to image semantic annotation, it usually encounters the problem of excessive training samples. In this paper, we propose a novel method, which is by combining learning vector quantization (LVQ) technique and SVM classifier, to improve annotation accuracy and speed. affinity propagation algorithm-based LVQ technique is used to optimize the training set, and a few number of optimized representative feature vectors are used to train SVM. This approach not only meets the small sample size characteristic of SVM, but also greatly accelerates the training and annotating process. Comparative experimental studies confirm the validity of the proposed method.
Image semantic annotation can be viewed as a multi-class classification problem, which maps image features to semantic class labels, through the procedures of image modeling and image semantic mapping. Bayesian classi...
详细信息
Image semantic annotation can be viewed as a multi-class classification problem, which maps image features to semantic class labels, through the procedures of image modeling and image semantic mapping. Bayesian classifier is usually adopted for image semantic annotation which classifies image features into class labels. In order to improve the accuracy and efficiency of classifier in image annotation, we propose a combined optimization method which incorporates affinity propagation algorithm, optimizing training data algorithm, and modeling prior distribution with Gaussian mixture model to build Bayesian classifier. The experiment results illustrate that the classifier performance is improved for image semantic annotation with proposed method.
DBSCAN is a density based clustering algorithm and its effectiveness for spatial datasets has been demonstrated in the existing literature. However, there are two distinct drawbacks for DBSCAN: (i) the performances of...
详细信息
DBSCAN is a density based clustering algorithm and its effectiveness for spatial datasets has been demonstrated in the existing literature. However, there are two distinct drawbacks for DBSCAN: (i) the performances of clustering depend on two specified parameters. One is the maximum radius of a neighborhood and the other is the minimum number of the data points contained in such neighborhood. In fact these two specified parameters define a single density. Nevertheless, without enough prior knowledge, these two parameters are difficult to be determined;(ii) with these two parameters for a single density, DBSCAN does not perform well to datasets with varying densities. The above two issues bring some difficulties in applications. To address these two problems in a systematic way, in this paper we propose a novel parameter free clustering algorithm named as APSCAN. Firstly, we utilize the affinitypropagation (AP) algorithm to detect local densities for a dataset and generate a normalized density list. Secondly, we combine the first pair of density parameters with any other pair of density parameters in the normalized density list as input parameters for a proposed DDBSCAN (Double-Density-Based SCAN) to produce a set of clustering results. In this way, we can obtain different clustering results with varying density parameters derived from the normalized density list. Thirdly, we develop an updated rule for the results obtained by implementing the DDBSCAN with different input parameters and then synthesize these clustering results into a final result. The proposed APSCAN has two advantages: first it does not need to predefine the two parameters as required in DBSCAN and second, it not only can cluster datasets with varying densities but also preserve the nonlinear data structure for such datasets. Crown Copyright (C) 2011 Published by Elsevier B.V. All rights reserved.
暂无评论