PSO and Computationally Inexpensive Sequential Forward Floating Selection in acquiring significant features for handwritten authorship

Pratama, Satrya Fajri; Muda, Azah Kamilah; Choo, Yun-Huoy; Muda, Noor Azilah

doi:10.1109/his.2011.6122132

Cited by 11 publications

(10 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Bu sayede, özellik seçiminin herhangi bir adımında mevcut sınıflama başarısı daha yüksek bir değere ulaşıncaya kadar aynı yönde hareket edilir. Ardışık ileri yönde kayan seçim yöntemine ilişkin algoritma kısaca aşağıdaki gibidir [21,25]. …”

Section: Ardışık Ileri Yönde Kayan Seçimunclassified

Özellik Seçim Yöntemleri ve Yeni Bir Yaklaşım

Budak

2018

SDÜ Fen Bil Enst Der

View full text Add to dashboard Cite

Anahtar KelimelerVeri madenciliği, Özellik seçimi, Özellik seçim algoritmaları, Sınıflandırma Özet: Veri madenciliği sürecinin önemli aşamalarından biri veri boyutunun azaltılması işlemidir. Veri boyutunun azaltılması kısaca, büyük veri kümelerinin depolanması ve analiz edilmesinde karşılaşılan sorunları aşmak için veri kümesinden ilgisiz veya gereksiz değişkenlerin çıkartılması olarak tanımlanmaktadır. Veri boyutunun azaltılması için kullanılan yöntemlerin başında özellik seçimi gelmektedir. Özellik seçimi, orijinal veri setini temsil edebilecek en iyi altkümenin seçimi olarak tanımlanmaktadır. Bu işlem, ilgilenilen problem için en faydalı ve en önemli özellikleri seçerek veri kümesindeki özellik sayısını azaltmayı yani veri boyutunu düşürmeyi amaçlamaktadır. Bu çalışmada, özellik seçim yöntemleri incelenmiş ve alternatif bir yöntem önerilmiştir. Feature Selection Methods and a New Approach Keywords Data mining, Feature selection, Feature selection algorithms, ClassificationAbstract: One of important stages of data mining procedure is the process of dimension reduction. The dimension reduction is the process of removing irrelevant or redundant variables from the data set in order to resolve problems encountered in storing big data sets and analyzing them. Feature selection is one of the most popular method among the methods of dimension reduction. Feature selection, is described as the selection of the best subset which can represent the original data set. This process aims to reduce the number of features in the data set by selecting the most useful and important features for the discussed problem. In this study, feature selection methods have been analyzed and an alternative method has been proposed.

show abstract

Section: Ardışık Ileri Yönde Kayan Seçimunclassified

Özellik Seçim Yöntemleri ve Yeni Bir Yaklaşım

Budak

2018

SDÜ Fen Bil Enst Der

View full text Add to dashboard Cite

show abstract

“…Study conducted by [3,4] has shown significantly improved classification accuracy. Therefore, this study is conducted to explore existing feature selection frameworks, adopt the technique proposed by [4] into novel feature selection framework for handwritten authorship, and then compare the proposed framework against various feature selection techniques.…”

Section: Handwritten Authorshipmentioning

confidence: 99%

“…Swarm Optimized and Computationally Inexpensive Floating Selection (SOCIFS) was proposed by [4]. SO-CIFS is the hybrid between two techniques, which are Particle Swarm Optimization (PSO) [27,28] and Computationally Inexpensive Floating Selection (CIFS) [3].…”

Section: Feature Selection Techniquementioning

confidence: 99%

“…Therefore, identifying the significant features is very important in order to identify the writer, moreover to improve the classification accuracy. Previous studies have been conducted by [3,4] in order to use feature selection in acquiring the significant features of handwriting in WI domain.…”

Section: Introductionmentioning

confidence: 99%

“…Consequences to that, this paper focuses on proposing a novel feature selection framework in acquiring significant features of word shape for handwritten au-thorship by using SOCIFS, proposed by [4], and compares the performance of proposed framework to existing feature selection techniques. The remainder of the paper is structured as follows.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

SOCIFS feature selection framework for handwritten authorship

Pratama

Muda

Choo

et al. 2013

HIS

Self Cite

View full text Add to dashboard Cite

The uniqueness of shape and style of handwriting can be used to identify the significant features in confirming the author of writing. This paper is meant to propose a novel feature selection framework for Swarm Optimized and Computationally Inexpensive Floating Selection (SOCIFS), by exploring existing feature selection frameworks, and compare the performance of proposed feature selection framework against various feature selection methods in Writer Identification in order to find the most significant features. The promising applicability of the proposed framework has been demonstrated in the result and worth to receive further exploration in identifying the handwritten authorship.

show abstract