A Survey On Parallelization Of Data Mining Techniques

1999

Similar scenarios will occur in other areas: we will see large numbers of radiological images generated in hospitals and immense product and customer databases as the Internet and e-commerce continue to expand. 1 Exploring useful information from such data will require efficient parallel algorithms running on high-performance computing systems with powerful parallel I/O capabilities. Without such systems and techniques, invaluable data and information will remain undiscovered.

Lecture Notes in Computer Science, 2002

When data mining first appeared, several disciplines related to data analysis, like statistics or artificial intelligence were combined toward a new topic: extracting significant patterns from data. The original data sources were small datasets and, therefore, traditional machine learning techniques were the most common tools for this tasks. As the volume of data grows these traditional methods were reviewed and extended with the knowledge from experts working on the field of data management and databases. Today problems are even bigger than before and, once again, a new discipline allows the researchers to scale up to these data. This new discipline is distributed and parallel processing. In order to use parallel processing techniques, specific factors about the mining algorithms and the data should be considered. Nowadays, there are several new parallel algorithms, that in most of the cases are extensions of a traditional centralized algorithm. Many of these algorithms have common core parts and only differ on distribution schema, parallel coordination or load/task balancing methods. We call these groups algorithm families. On this paper we introduce a methodology to implement algorithm families. This methodology is founded on the MOIRAE distributed control architecture. In this work we will show how this architecture allows researchers to design parallel processing components that can change, dynamically, their behavior according to some control policies.

2000

This paper presents our approach to data mining that allows the coupling of parallel applications with a scripting language resulting in an efficient and flexible toolbox. Parallel algorithms which are scalable both in data size and number of processors are a key issue to be able to solve the ever increasing problems in data mining. On the other hand, data mining applications should be flexible to allow interactive data exploration. By using a toolbox written in a scripting language we are able to steer parallel applications in a flexible way, thus fulfilling the needs of a data miner for fast interactive data analysis. The chosen approach is discussed and first results are presented.

2006 Proceeding of the Thirty Eighth Southeastern Symposium on System Theory, 2006

This paper discusses parallel Data Mining architecture for large volume of data which eventually scanning billions of rows of data per record. Here we compare the different parallel algorithms for Association Rule Mining and discuss the advantages and disadvantages of each method. We also compare the computational time of serial and parallel algorithms for Association Rule Mining.

Personal Computer/Workstation clusters have been studied intensively in the field of parallel and distributed computing. In the viewpoint of applications, data intensive applications such as data mining and ad-hoc query processing in databases are considered very important for high performance computing, as well as conventional scientific calculations. We have built and evaluated PC cluster pilot systems, especially SAN-connected PC cluster, and implemented parallel data mining on them. Several optimization, including dynamic data allocation, is discussed for the execution of this application.

Proceedings 15th International Parallel and Distributed Processing Symposium. IPDPS 2001, 2001

This paper presents research projects tackling two aspects in data mining. First, a toolbox is discussed that allows flexible and interactive data exploration, analysis and presentation using the scripting language Python. The advantages of this toolbox are that it provides the functionality to process multiple SQL queries in parallel, and enables fast data retrieval using a supervised caching mechanism for commonly used queries. These two facets of the toolbox allow for fast, efficient data access reducing the time spent on data exploration, preparation and analysis.

2003

ABSTRACT In this paper, we focus on using a cluster of SMPs for scalable data mining. We have developed distributed memory and shared memory parallelization techniques that are applicable to a number of common data mining algorithms. These techniques are incorporated in a middleware called FREERIDE (FRamework for Rapid Implementations of Datamining Engines). We present experimental evaluation of our techniques and framework using apriori association mining, k-means clustering, and a decision tree algorithm.

2001

Abstract Data mining is an interdisciplinary field, having applications in diverse areas like bioinformatics, medical informatics, scientific data analysis, financial analysis, consumer profiling, etc. In each of these application domains, the amount of data available for analysis has exploded in recent years, making the scalability of data

Data mining has become one of the most essential tools in diverse fields. The increases in data sizes and algorithmic complexities require the computational power of chip to increase even further. In this paper, we present detailed characteristics from the hardware and software perspectives for a set of representative data mining programs. We first design MineBench, a benchmarking suite containing representative data mining applications from multiple categories including two classification, two association rule mining, and four clustering applications. We evaluate the MineBench applications on an 8-way Shared Memory Parallel (SMP) machine and analyze their important performance characteristics. During the evaluation, the input datasets and the number of processors used are varied to measure the scalability of the applications in our benchmark suite. We present the results based on characteristics such as scalability, I/O complexity, fraction of time spent in the OS mode, and communication/synchronization overheads. This information can aid designers of future systems as well as programmers of new data mining algorithms to achieve better system and algorithmic performance.