Barak Chizi

A Survey of Feature Selection Techniques

IGI Global eBooks, 2009

Download

Feature Selection by Combining Multiple Methods

Springer eBooks, Aug 10, 2006

Feature selection is the process of identifying relevant features in the dataset and discarding e... more

A Methodology for Improving the Performance of Non-Ranker Feature Selection Filters

International Journal of Pattern Recognition and Artificial Intelligence, Aug 1, 2007

Feature selection is the process of identifying relevant features in the dataset and discarding e... more Feature selection is the process of identifying relevant features in the dataset and discarding everything else as irrelevant and redundant. Since feature selection reduces the dimensionality of the data, it enables the learning algorithms to operate more effectively and rapidly. In some cases, classification performance can be improved; in other instances, the obtained classifier is more compact and can be easily interpreted. There is much work done on feature selection methods for creating ensemble of classifiers. Thus, these works examine how feature selection can help ensemble of classifiers to gain diversity. This paper examines a different direction, i.e. whether ensemble methodology can be used for improving feature selection performance. In this paper we present a general framework for creating several feature subsets and then combine them into a single subset. Theoretical and empirical results presented in this paper validate the hypothesis that this approach can help finding a better feature subset.

Download

Dimension Reduction and Feature Selection

Springer eBooks, 2009

Data Mining algorithms search for meaningful patterns in raw data sets. The Data Mining process r... more Data Mining algorithms search for meaningful patterns in raw data sets. The Data Mining process requires high computational cost when dealing with large data sets. Reducing dimensionality (the number of attributed or the number of records) can effectively cut this cost. This chapter focuses a pre-processing step which removes dimension from a given data set before it is fed to a data mining algorithm. This work explains how it is often possible to reduce dimensionality with minimum loss of information. Clear dimension reduction taxonomy is described and techniques for dimension reduction are presented theoretically.

Download

Flexible and Scalable Simulations of Mass Participants in Real Time

A Decision Tree Framework for Semi-Automatic Extraction of Product Attributes from the Web

Studies in Computational Intelligence

Semi-Automatic extraction of product attributes from URLs is an important issue for comparison-sh... more

Isolation-based conditional anomaly detection on mixed-attribute data to uncover workers' compensation fraud

Decision Support Systems, 2018

The development of new data analytical methods remains a crucial factor in the combat against ins... more The development of new data analytical methods remains a crucial factor in the combat against insurance fraud. Methods rooted in the research field of anomaly detection are considered as promising candidates for this purpose. Commonly, a fraud data set contains both numeric and nominal attributes, where, due to the ease of expressiveness, the latter often encodes valuable expert knowledge. For this reason, an anomaly detection method should be able to handle a mixture of different data types, returning an anomaly score meaningful in the context of the business application. We propose the iForest CAD approach that computes conditional anomaly scores, useful for fraud detection. More specifically, anomaly detection is performed conditionally on well-defined data partitions that are created on the basis of selected numeric attributes and distinct combinations of values of selected nominal attributes. In this way, the resulting anomaly scores are computed with respect to a reference group of interest, thus representing a meaningful score for domain experts. Given that anomaly detection is performed conditionally, this approach allows detecting anomalies that would otherwise remain undiscovered in unconditional anomaly detection. Moreover, we present a case study in which we demonstrate the usefulness of our proposed approach on realworld workers' compensation claims received from a large European insurance organization. As a result, the iForest CAD approach is greatly accepted by domain experts for its effective detection of fraudulent claims.

Download

A Survey of Feature Selection Techniques

by Barak Chizi and Oded Maimon

... (2004), introduced a new approach called SIMBA (Iterative Search Margin Based Algorithm), whi... more

System for Analyzing Mobile Telephone Users Locations and Classifications, While Maintaining Users Privacy Constraints

A Methodology for Improving the Performance of Non-Ranker Feature Selection Filters

by Oded Maimon, Barak Chizi, and Shimon Lior Rokach

International Journal of Pattern Recognition and Artificial Intelligence, 2007

Feature selection is the process of identifying relevant features in the dataset and discarding e... more Feature selection is the process of identifying relevant features in the dataset and discarding everything else as irrelevant and redundant. Since feature selection reduces the dimensionality of the data, it enables the learning algorithms to operate more effectively and rapidly. In some cases, classification performance can be improved; in other instances, the obtained classifier is more compact and can be easily interpreted. There is much work done on feature selection methods for creating ensemble of classifiers. Thus, these works examine how feature selection can help ensemble of classifiers to gain diversity. This paper examines a different direction, i.e. whether ensemble methodology can be used for improving feature selection performance. In this paper we present a general framework for creating several feature subsets and then combine them into a single subset. Theoretical and empirical results presented in this paper validate the hypothesis that this approach can help finding a better feature subset.

Download

A Survey of Feature Selection Techniques

by Barak Chizi and Shimon Lior Rokach

... (2004), introduced a new approach called SIMBA (Iterative Search Margin Based Algorithm), whi... more

Feature Selection by Combining Multiple Methods

by Barak Chizi and Oded Maimon

Studies in Computational Intelligence, 2006

This paper proposes a feature selection method that combines various feature selection techniques... more This paper proposes a feature selection method that combines various feature selection techniques. Feature selection has been realized as one of the most important processes in various applications, especially pattern classification problems. When too many attributes are involved, training a machine to classify patterns into their respective classes is seemingly impossible. Hence, selecting good features is necessary. Albeit numerous methods to select features have been proposed, there exists no universal solution for this problem unless one searches all possible subsets of all attributes. Some techniques such as forward selection and backward elimination are feasible in terms of speed, but suffer from the effect of local optima problem. Exhaustive search technique guarantees to find the optimal subset, but it takes too long for users to wait for the output; its computational time complexity is exponential. Hence, we propose first to reduce the number of features to the minimum size, so that exhaustive search technique can handle in reasonable time, using forward selection and backward elimination techniques. In this way, the selected feature set is much better than those from forward selection and backward elimination and computed much faster than the exhaustive search technique. The proposed combined feature selection technique is tested on the off-line signature verification data set.

Download

Dimension Reduction and Feature Selection

by Oded Maimon and Barak Chizi

Data Mining and Knowledge Discovery Handbook, 2005

ABSTRACT Data Mining algorithms search for meaningful patterns in raw data sets. The Data Mining ... more ABSTRACT Data Mining algorithms search for meaningful patterns in raw data sets. The Data Mining process requires high computational cost when dealing with large data sets. Reducing dimensionality (the number of attributed or the number of records) can effectively cut this cost. This chapter focuses a pre-processing step which removes dimension from a given data set before it is fed to a data mining algorithm. This work explains how it is often possible to reduce dimensionality with minimum loss of information. Clear dimension reduction taxonomy is described and techniques for dimension reduction are presented theoretically. Key wordsDimension Reduction-Preprocessing

A Decision Tree Framework for Semi-Automatic Extraction of Product Attributes from the Web

by Roni Romano, Oded Maimon, and Barak Chizi

Studies in Computational Intelligence, 2006

Semi-Automatic extraction of product attributes from URLs is an important issue for comparison-sh... more

Uploads

Papers by Barak Chizi

Log In