BIRCH Algorithm Research Articles

A Comprehensive Review of Privacy Preservation Framework using Birch and K-Means Algorithm

A Comprehensive Review of Privacy Preservation Framework using Birch and K-Means Algorithm

BIRCH algorithm and data management in financial enterprises based on dynamic panel GMM test

A risk management strategy to inspect BIRCH algorithm and data in financial enterprises based on dynamic panel GMM was proposed to increase effectiveness of risk management for financial enterprises. Firstly, description method of dynamic panel GMM was offered to establish primary model of partners. Secondly, design and realization of BIRCH algorithm on parallelization of Spark was researched on focus and Spark transformation operation of much time consumption in the process of parallelization was obtained through analysis of theoretical performance; meanwhile, shuffle and disk accessing frequency can be reduced to achieve performance optimization according to directed acyclic graph DAG of parallelized BIRCH algorithm. Finally, the proposed algorithm was applied to risk management of financial enterprises.

Variations on the Clustering Algorithm BIRCH

Abstract Clustering algorithms are recently regaining attention with the availability of large datasets and the rise of parallelized computing architectures. However, most clustering algorithms suffer from two drawbacks: they do not scale well with increasing dataset sizes and often require proper parametrization which is usually difficult to provide. A very important example is the cluster count, a parameter that in many situations is next to impossible to assess. In this paper we present A-BIRCH, an approach for automatic threshold estimation for the BIRCH clustering algorithm. This approach computes the optimal threshold parameter of BIRCH from the data, such that BIRCH does proper clustering even without the global clustering phase that is usually the final step of BIRCH. This is possible if the data satisfies certain constraints. If those constraints are not satisfied, A-BIRCH will issue a pertinent warning before presenting the results. This approach renders the final global clustering step of BIRCH unnecessary in many situations, which results in two advantages. First, we do not need to know the expected number of clusters beforehand. Second, without the computationally expensive final clustering, the fast BIRCH algorithm will become even faster. For very large data sets, we introduce another variation of BIRCH, which we call MBD-BIRCH, which is of particular advantage in conjunction with A-BIRCH but is independent from it and also of general benefit.

Detection of Malware and Malicious Executables Using E-Birch Algorithm

Malware detection is one of the challenges to the modern computing world. Web mining is the subset of data mining used to provide solutions for complex problems. Web intelligence is the new hope for the field of computer science to bring solution for the malware detection. Web mining is the method of web intelligence to make web as an intelligent tool to combat malware and phishing websites. Generally, malware injected through websites into the user system and modifies the executable file and paralyze the whole activity of the system. Antivirus application utilizes the data mining technique to find the malware in the web. There is a need of heuristic approach to solve the malware problem. Dynamic analysis methods yield better result than the static methods. Data mining is the best option for the dynamic analysis of malware or malicious program. The purpose of the research is to apply the enhanced Birch algorithm to find the malware and modified executables of Windows and Android operating system.

Efficient Analysis of PharmaceuticalCompound Structure Based on EnhancedK-Means Clustering Algorithm

In this paper to focuses on discovery of functional group of the connectivity atom for drug effects of chemical compound structured data with position of each atom. A simple Kmeans algorithm, select an initial centroid distance randomly for analysing the data. In the proposed method an Enhanced K means algorithm, forms a functional group of inter connected atoms based on calculate initial centroid distance instead of random selected. The pharmaceutical compounds specifically represented as atom number, atom name like carbon, hydrogen, nitrogen, oxygen with connected atoms. Here it can be experimented the number of iterations are reduced and performance of time accuracy can improve when compare with chameleon and Birch algorithm.

Sentence-Similarity Based DocumentClustering Using Birch Algorithm

Document clustering is the process of automatically grouping the related documents into clusters. Instead of searching entire documents for relevant information, these clusters will improve the efficiency and avoid overlapping of contents. Relevant document can be efficiently retrieved and accessed by means of document clustering. When compared with hard clustering, birch algorithms allow patterns to belong to all the clusters with differing degrees of membership. Birch algorithm is important in domains such as sentence clustering, since a sentence is related to more than one theme or topic present within a document or set of documents. In our proposed system, birch clustering algorithm operates on cluster Start with initial threshold and inserts points into the tree. Results obtained while applying the algorithm to sentence clustering tasks demonstrate that birch algorithm is capable of identifying overlapping clusters of semantically related sentences and its performance improvement can be proved by comparing with k-means. Performance measures document clustering and its application in document summarization

An efficient method for motif and anomaly detection in time series based on clustering

Motifs and anomalies are two important representative patterns in a time series. Existing approaches usually handle motif discovery and anomaly detection in time series separately. In this paper, we propose a new efficient clustering-based method for discovering motif and detecting anomaly at the same time in large time series data. Our method first extracts motif/anomaly candidates from a time series by using significant extreme points and then clusters the candidates by using BIRCH algorithm. The proposed method computes anomaly scores for all sub-clusters and discovers the top motif based on the sub-cluster with the smallest anomaly score and detects the top anomaly based on the sub-cluster with the largest anomaly score. Experimental results on several benchmark datasets show that our proposed method can discover precise motif and anomaly with high time efficiency on large time series data.

Mapping patterns of well-being and quality of life in extended Europe

In this paper, we have applied a powerful clustering procedure (the two-step cluster analysis or BIRCH algorithm) to a set of non-monetary indicators of well-being and quality of life taken from the first four waves of the European Social Survey. By employing this technique, we have identified nine clusters of people characterized by different forms of well-being and quality of life, while preserving as much as possible the multidimensional information contained in the preselected indicators. We then analyzed the distribution of the clusters among the various European countries, finding significant differences among the groups of Nordic countries, Continental European countries, Mediterranean European countries and Eastern European countries in the chances of belonging to the nine forms of well-being and quality of life previously identified. On average, citizens of the Nordic countries, but also those of Switzerland and Luxembourg, have a higher chance of belonging to cumulative clusters of well-being than countries in Continental Europe and Eastern Europe. In very concise terms, the former appear to be somewhat protected from the risk of incurring the more severe forms of material deprivation, distrust of others and of institutions, poor health and relational isolation. In contrast, Eastern Europeans are characterized by particularly pronounced levels of deprivation across multiple dimensions.

Improved BIRCH clustering algorithm

BIRCH algorithm is a clustering algorithm suitable for very large data sets. In the algorithm, a CF-tree is built whose all entries in each leaf node must satisfy a uniform threshold T, and the CF-tree is rebuilt at each stage by different threshold. But how to set the initial threshold and how to increase the threshold of each stage are not given. In addition, the algorithm can only work with "metric" attribute, which makes its application restrained. This paper made some improvements on BIRCH algorithm: 1) Changed CF structure so that heterogeneous attributes could be manipulated; 2) Gave a heuristic method of getting initial threshold and increasing threshold of second stage of the algorithm; 3) Discussed the algorithm's parameter B and L and found that the algorithm had equal performance when B=L, at last, gave a sound scope for B. Experimental results on public data sets show that the improved algorithm has preferable performance.

Finding approximate solutions to combinatorial problems with very large data sets using BIRCH

Computing estimators with good robustness properties generally requires solving highly complex optimization problems. The current state-of-the-art algorithms to find approximate solutions to these problems need to access the data set a large number to times and become unfeasible when the data do not fit in memory. In this paper the BIRCH algorithm is adapted to calculate approximate solutions to problems in this class. For data sets that fit in memory, this approach is able to find approximate Least Trimmed Squares (LTS) and Minimum Covariance Determinant (MCD) estimators that compare very well with those returned by the fast-LTS and fast-MCD algorithms, and in some cases is able to find a better solution (in terms of value of the objective function) than those returned by the fast- algorithms. This methodology can also be applied to the Linear Grouping Algorithm and its robust variant for very large datasets. Finally, results from a simulation study indicate that this algorithm performs comparably well to fast-LTS in simple situations (large data sets with a small number of covariates and small proportion of outliers) and does much better than fast-LTS in more challenging situations without requiring extra computational time. These findings seem to confirm that this approach provides the first computationally feasible and reliable approximating algorithm in the literature to compute the LTS and MCD estimators for data sets that do not fit in memory.