Exploration of a hybrid feature selection algorithm

Osei-Bryson, Kweku-Muata; Giles, Kendall; Kositanurit, Boontaree

doi:10.1057/palgrave.jors.2601565

Cited by 13 publications

(14 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, several authors proposed hybrid approaches taking advantages of both filter and wrapper methods. Examples of hybrid algorithms include t-statistics and a GA [20], a correlation based feature selection algorithm and a genetic algorithm [21], principal component analysis and an ACO algorithm [22], chi-square approach and a multi-objective optimization algorithm [23], mutual information and a GA [24,25]. The idea behind the hybrid method is that filter methods are first applied to select a feature pool and then the wrapper method is applied to find the optimal subset of features from the selected feature pool.…”

Section: Related Workmentioning

confidence: 99%

Bi-level dimensionality reduction methods using feature selection and feature extraction

Veerabhadrappa¹,

Rangarajan²

2010

IJCA

View full text Add to dashboard Cite

Variety of feature selection methods have been developed in the literature, which can be classified into three main categories: filter, wrapper and hybrid approaches. Filter methods apply an independent test without involving any learning algorithm, while wrapper methods require a predetermined learning algorithm for feature subset evaluation. Filter and wrapper methods have their drawbacks and are complementary to each other. The filter approaches have low computational cost with insufficient reliability in classification while wrapper methods tend to have superior classification accuracy but require great computational effort. The methods proposed in this paper are bi-level dimensionality reduction methods that integrate filter method and feature extraction method with the aim to improve the classification performance of the features selected. In the two approaches proposed, in level 1 of dimensionality reduction, feature are selected based on mutual correlation and in level 2 selected features are used to extract features using PCA or LPP. To evaluate the performance of the proposed methods several experiments are conducted on standard datasets and the results obtained show superiority of the proposed methods over single level dimensionality reduction techniques (feature selection based on Mutual correlation, PCA and LPP).

show abstract

Section: Related Workmentioning

confidence: 99%

Bi-level dimensionality reduction methods using feature selection and feature extraction

Veerabhadrappa¹,

Rangarajan²

2010

IJCA

View full text Add to dashboard Cite

show abstract

“…Examples of hybrid 87 algorithms include t-statistics and a GA [24], a correlation-based feature selection algorithm and a genetic algorithm [25], principal com-89 ponent analysis and an ACO algorithm [26], chi-square approach and a multi-objective optimization algorithm [27], mutual information 91 and a GA [28,29]. The idea behind the hybrid method is that filter methods are first applied to select a feature pool and then the wrap-93 per method is applied to find the optimal subset of features from the selected feature pool.…”

Section: Review Of Existing Techniques 19mentioning

confidence: 99%

“…We also compare our algorithm against a hybrid of filter and wrap-79 per approaches-filter-wrapper (FW). Many hybrid algorithms have been proposed for feature subset selection with encouraging re-81 sults [24][25][26][27][28][29]. It was not possible to implement all the methods and empirically assess them.…”

Section: Comparative Performance Analysis 71mentioning

confidence: 99%

“…Since mean 27 vectors and covariance matrices of no two datasets are the same, the joint distribution of features is different in each dataset. 29 Step 2: Generate 10,000 combinations of feature values for each dataset from its unique mean vector and covariance matrix.…”

Section: Synthetic Datasets 11mentioning

confidence: 99%

“…In particular, the prediction performance of any learning algorithm de-25 pends on how efficiently the algorithm learns patterns in the data. Irrelevant and redundant features increase the search space size, 27 making patterns more difficult to detect and making it more difficult 29…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Feature subset selection in large dimensionality domains

Gheyas

Smith

2010

Pattern Recognition

519

231

View full text Add to dashboard Cite

Searching for an optimal feature subset from a high dimensional feature space is known to be an NPcomplete problem. We present a hybrid algorithm, SAGA, for this task. SAGA combines the ability to avoid being trapped in a local minimum of simulated annealing with the very high rate of convergence of the crossover operator of genetic algorithms, the strong local search ability of greedy algorithms and the high computational efficiency of generalized regression neural networks. We compare the performance over time of SAGA and well-known algorithms on synthetic and real datasets. The results show that SAGA outperforms existing algorithms.

show abstract