Genetic algorithms as a tool for feature selection in machine learning

Vafaie, H.; Jong, Kenneth De

doi:10.1109/tai.1992.246402

Cited by 165 publications

(102 citation statements)

References 1 publication

Supporting

Mentioning

102

Contrasting

Order By: Relevance

“…This method reduces the computational complexity and achieves better performing clustering [13]. Haleh Vafaie et al presented a genetic algorithm-based approach to develop the rules for identifying the suitable variable subset for the texture classification tasks and observed that it also can be used in rule induction machine learning systems [14]. W. Siedlecki et al presented the usage of the genetic algorithm for selecting the necessary feature subsets form the large dataset [15].…”

Section: Related Workmentioning

confidence: 99%

Dimensionality Reduction using Genetic Algorithm for Improving Accuracy in Medical Diagnosis

Singh¹,

Leavline²,

Priyanka³

et al. 2016

IJISA

View full text Add to dashboard Cite

Abstract-The technological growth generates the massive data in all the fields. Classifying these highdimensional data is a challenging task among the researchers. The high-dimensionality is reduced by a technique is known as attribute reduction or feature selection. This paper proposes a genetic algorithm (GA)-based features selection to improve the accuracy of medical data classification. The main purpose of the proposed method is to select the significant feature subset which gives the higher classification accuracy with the different classifiers. The proposed genetic algorithmbased feature selection removes the irrelevant features and selects the relevant features from original dataset in order to improve the performance of the classifiers in terms of time to build the model, reduced dimension and increased accuracy. The proposed method is implemented using MATLAB and tested using the medical dataset with various classifiers namely Naï ve Bayes, J48, and k-NN and it is evident that the proposed method outperforms other methods compared.

show abstract

Section: Related Workmentioning

confidence: 99%

Dimensionality Reduction using Genetic Algorithm for Improving Accuracy in Medical Diagnosis

Singh¹,

Leavline²,

Priyanka³

et al. 2016

IJISA

View full text Add to dashboard Cite

show abstract

“…Over the years GA which is considered to be an inductive searching technique demonstrated substantial improvement [14]. The Feature selection using genetic algorithms are considered to be an excellent choice for improving the performance of the classification system [15]. The selection of an appropriate representation and an adequate evaluation function is vital for the successful implementation of any searching problem using GA. For the problem of feature selection the importance of selecting the appropriate representation and evaluation function is described in [16].…”

Section: Genetic Algorithmmentioning

confidence: 99%

Face Recognition based on a Hybrid Meta-heuristic Feature Selection Algorithm

Arivalagan¹,

Venkatachalapathy²

2012

IJCA

View full text Add to dashboard Cite

For the past few years, a number of new face recognition techniques have been proposed. Always it is a big unanswered question among face recognition researchers about which method or technique will have better performance. In this study an approach to recognize known faces based on Eigen vectors and a hybrid Meta-heuristic feature selection algorithm is proposed. The eigenvectors which are covariance matrix of the face images together describes the difference between face images. Face recognition problem is viewed as a two dimensional recognition problem. Initially the face images are projected in to face space and using Principal component analysis the eigenvectors with high Eigenvalues are extracted to reduce the dimension of the feature vector. Further to select the best feature vectors which increase the classification accuracy is selected by using a hybrid metaheuristic algorithm using Genetic algorithm (GA) and Bacteria Foraging Optimization (BFO). In this study the Support vector machine (SVM) and Back propagation neural network (BPNN) are used for classification. The classifiers are trained and tested separately using the frontal face images taken from AT&T database. The SVM and BPNN produces an average classification accuracy of 82.6% and 83.28% respectively.

show abstract

“…When chromosome[i] is 1, the i th feature is selected for classification, and when it is 0, the i th feature is not selected [11,16].…”

Section: B Feature Selection Using Gamentioning

confidence: 99%

“…A mong the many methods proposed for feature selection, evolutionary optimization algorith ms such as genetic algorith m (GA) have gained a lot of attention. Genetic algorith m has been used as an efficient feature selection method in many applications [11,16].…”

Section: Introductionmentioning

confidence: 99%

The Impact of Feature Selection on Web Spam Detection

Karimpour¹,

Noroozi²,

Abadi³

2012

IJISA

View full text Add to dashboard Cite

Abstract-Search engine is one of the most important tools for managing the massive amount of d istributed web content. Web spamming tries to deceive search engines to rank some pages higher than they deserve. Many methods have been proposed to combat web spamming and to detect spam pages. One basic one is using classification, i.e., learn ing a classification model for classifying web pages to spam or non-spam. This work tries to select the best feature set for classification of web spam using imperialist competitive algorithm and genetic algorith m. Imperialist competitive algorith m is a novel optimization algorithm that is inspired by socio-political process of imperialis m in the real world. Experiments are carried out on W EBSPAM-UK2007 data set, which show feature selection improves classification accuracy, and imperialist competitive algorithm outperforms GA.

show abstract

Genetic algorithms as a tool for feature selection in machine learning

Cited by 165 publications

References 1 publication

Dimensionality Reduction using Genetic Algorithm for Improving Accuracy in Medical Diagnosis

Dimensionality Reduction using Genetic Algorithm for Improving Accuracy in Medical Diagnosis

Face Recognition based on a Hybrid Meta-heuristic Feature Selection Algorithm

The Impact of Feature Selection on Web Spam Detection

Contact Info

Product

Resources

About