Supercomputers and Supercomputing

What is a Supercomputer? A Supercomputer is defined as the fastest type of computer used for specialized applications that require a massive number of mathematical calculations. The term “supercomputer” was coined in 1929 by the New York World, referring to tabulators manufactured by IBM. To modern computer users, these tabulators would probably appear awkward, slow, and cumbersome to use, but at the time, they represented the cutting edge of technology. This continues to be true of supercomputers today, which harness immense processing power so that they are incredibly fast, sophisticated, and powerful.

Using an Ontology-Based Framework to Extract External Web Data for the Data Warehouse

Data warehouses have established themselves as necessary components of an effective Information Technology (IT) strategy for large businesses. In addition to utilizing operational databases data warehouses must also integrate increasing amounts of external data to assist in decision support. An important source of such external data is the Web. In an effort to ensure the availability and quality of Web data for the data warehouse we propose an intermediate data-staging layer called the Meta-Data Engine (M-DE). A major challenge, however, is the conversion of data originating in the Web, and brought in by robust search engines, to data in the data warehouse. The authors therefore also propose a framework, the Semantic Web Application (SEMWAP) framework, which facilitates semi-automatic matching of instance data from opaque web databases using ontology terms. Their framework combines Information Retrieval (IR), Information Extraction (IE), Natural Language Processing (NLP), and ontology techniques to produce a matching and thus provide a viable building block for Semantic Web (SW) Applications.

Interactive Visualization Tool for Analysis of Large Image Databases

Navigation and interaction are essential features for an interface that is built as a help tool for analyzing large image databases. A tool for actively searching for information in large image databases is called an Image Retrieval System, or its more advanced version is called an Adaptive Image Retrieval System (AIRS). In an Adaptive Image Retrieval System (AIRS) the user-system interaction is built through an interface that allows the relevance feedback process to take place. In this chapter, the author identifies two types of users for an AIRS: a user who seeks images whom the author refers to as an end-user, and a user who designs and researches the collection and the retrieval systems whom the author refers to as a researcher-user. In this context, she describes a new interactive multiple views interface for an AIRS (Doloc-Mihu, 2007), in which each view illustrates the relationships between the images from the collection by using visual attributes (colors, shapes, proximities). With such views, the interface allows the user (both end-user and researcher-user) a more effective interaction with the system, which, further, helps during the analysis of the image collection. The author‘s qualitative evaluation of these multiple views in AIRS shows that each view has its own limitations and benefits. However, together, the views offer complementary information that helps the user in improving his or her search effectiveness.

From Data to Knowledge

This chapter will discuss a very useful technique to get (or to mine) a hidden information or knowledge which is lie in our data namely, data mining, which is a powerful and automatic (or semi-automatic) technique. Not only about the concept and theory, this chapter will also discuss about the application and implementation of data mining. Firstly, the authors will talk about data, information, and knowledge, whether they are different or not. After understand the term, they will discuss about what data mining is and what the importance of it. Second, they describe the process of gaining the hidden knowledge, how it is done, from the beginning until presenting the result. The authors will go through it step by step. In the next section, they will discuss about the several different tasks of data mining. In addition, to get a better understanding, the authors will compare data mining with other terminology which closely related so called data warehouse, and OLAP. For the last, but not the least, as stated before, this chapter will tell us about the real implementation of data mining in several different areas.

An Optimal Categorization of Feature Selection Methods for Knowledge Discovery

With the continuous availability of massive experimental medical data has given impetus to a large effort in developing mathematical, statistical and computational intelligent techniques to infer models from medical databases. Feature selection has been an active research area in pattern recognition, statistics, and data mining communities. However, there have been relatively few studies on preprocessing data used as input for data mining systems in medical data. In this chapter, the authors focus on several feature selection methods as to their effectiveness in preprocessing input medical data. They evaluate several feature selection algorithms such as Mutual Information Feature Selection (MIFS), Fast Correlation-Based Filter (FCBF) and Stepwise Discriminant Analysis (STEPDISC) with machine learning algorithm naive Bayesian and Linear Discriminant analysis techniques. The experimental analysis of feature selection technique in medical databases has enable the authors to find small number of informative features leading to potential improvement in medical diagnosis by reducing the size of data set, eliminating irrelevant features, and decreasing the processing time.

Towards the Notion of Typical Documents in Large Collections of Documents

This chapter presents a new measure of document similarity – the GNGrank that was inspired by the popular opinion that links between the documents reflect similar content. The idea was to create a rank measure based on the well known PageRank algorithm which exploits the document similarity to insert links between the documents. A comparative study of various link- and content-based similarity measures, and GNGrank is performed in the context of identification of a typical document of a collection. The study suggests that each group of them measures something different, a different aspect of document space, and hence the respective degrees of typicality do not correlate. This may be an indication that for different purposes different documents may be important. A deeper study of this phenomenon is our future research goal.

Mammogram Mining Using Genetic Ant-Miner

Image mining deals with the extraction of implicit knowledge, image data relationship, or other patterns not explicitly stored in the images. It is an extension of data mining to image domain and an interdisciplinary endeavour. This chapter focuses on mammogram classification using genetic Ant-Miner. The key idea is to generate classifier for classifying mammograms as normal or abnormal using the proposed Genetic Ant-Miner algorithm. The Genetic Algorithm has been employed to optimize some of the ant parameters. A comparative analysis is performed in order to achieve the efficiency of the proposed algorithm. Further, the experimental results reveals that the improvement of the proposed Genetic Ant-Miner in the domain of Biomedical image Analysis.

A Robust Biclustering Approach for Effective Web Personalization

Web recommendation or personalization could be viewed as a process that recommends the customized web presentations or predicts the tailored web contents to web users according to their specific need. The first step in intelligent web personalization is segmenting web log data into web user sessions for constructing user model. These segments are later used to recommend relevant URLs to old and new anonymous users of a web site. The knowledge discovery part can be executed offline by periodically mining new contents of the user access log files. The recommendation part is the online component of a usage-based personalization system. In this study, we propose a robust Biclustering algorithm to disclose the correlation that exists between users and pages. This chapter proposes a Robust Biclustering (RB) method based on constant values for integrating user clustering and page clustering techniques which is followed by a recommendation system that can respond to the users’ individual interests. To evaluate the effectiveness and efficiency of the recommendation, experiments are conducted in terms of the recommendation accuracy metric. The experimental results have demonstrated that the proposed Biclustering method is very simple and is able to efficiently extract needed usage knowledge accurately for web page recommendation.

Visual Survey Analysis in Marketing

The authors present a use and visualization of the ordinal evaluation (OrdEval) algorithm as a promising technique to study questionnaire data. The OrdEval algorithm is a general tool to analyze data with ordinal attributes, including surveys. It has many favorable features, including context sensitivity, ability to exploit meaning of ordered features and ordered response, robustness to noise and missing values in the data, and visualization capability. The authors select customer (dis)satisfaction analysis, an important problem from marketing research, as a case study and present visual analysis on two practical applications: business-to-business and costumer-to-business customer satisfaction studies. They demonstrate some interesting advantages offered by the new methodology and visualization and show how to extract and interpret new insights not available with classical analytical toolbox.

Dimensionality Reduction for Interactive Visual Clustering

Visualization techniques could enhance the existing methods for knowledge and data discovery by increasing the user involvement in the interactive process. VISTA, an interactive visual cluster rendering system, is known to be an effective model which allows the user to interactively observe clusters in a series of continuously changing visualizations through visual tuning. Identification of the dominating dimensions for visual tuning and visual distance computation process becomes tedious, when the dimensionality of the dataset increases. One common approach to solve this problem is dimensionality reduction. This chapter compares the performance of three proposed feature selection methods viz., Entropy Weighting Feature Selection, Outlier Score Based Feature Selection and Contribution to the Entropy Based Feature Selection for interactive visual clustering system. The cluster quality of the three feature selection methods is also compared. The experiments are carried out for various datasets of University of California, Irvine (UCI) machine learning data repository.