A hybrid feature selection method combining Gini index and support vector machine with recursive feature elimination for gene expression classification

Almutiri, Talal; Saeed, Faisal

doi:10.1504/ijdmmm.2022.122038

Cited by 4 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(1) Threshold segmentation based on the Otsu method In this study, in order to facilitate the detection of maize tips and feature extraction later, the enhanced image needs to be segmented. Due to the non-uniform grey value of the background, only part of the maize seeds can be segmented with one-dimensional or two-dimensional thresholding, most of which will be segmented into the background colour, and if multiple thresholding is used, each threshold needs to be calculated, which is complicated to calculate and also cannot guarantee the correctness of the threshold selection, therefore In this paper, the adaptive thresholding Otsu algorithm is used to segment the image of maize kernels [14][15].…”

Section: Maize Variety Image Processingmentioning

confidence: 99%

Maize Variety Identification Based on Support Vector Machines

2021

View full text Add to dashboard Cite

Seeds are the most basic and critical means of production in agricultural production. Declining purity of seed varieties will significantly reduce crop yield and product quality. The quality of crop seed varieties, especially purity testing, can protect the interests of farmers and promote the development of rural economies. The aim of this paper is to study maize variety identification based on support vector machines. Based on the morphological structure characteristics of maize varieties, a set of characteristic parameters that can accurately reflect the morphological structure of different maize varieties is proposed for variety identification. The parameter set consists of four components: shape, colour, size and sharpness parameters. The experimental results show that the support vector machine algorithm outperforms the BP neural network.

show abstract

Section: Maize Variety Image Processingmentioning

confidence: 99%

Maize Variety Identification Based on Support Vector Machines

2021

View full text Add to dashboard Cite

show abstract

“…Based on various feature selection strategies, three categories of feature selection algorithms can be distinguished: Filter [3][4][5][6][7][8], Wrapper [9][10][11][12][13][14][15], and Embedded [16][17][18][19][20][21][22][23][24][25][26]. The Filter method primarily relies on a vast variety of statistical metrics or informationtheoretic measures to assess the usefulness or duplication of data aspects and thereafter choose the most advantageous variables for modeling.…”

mentioning

confidence: 99%

A More Flexible and Robust Feature Selection Algorithm

Tu,

Su,

Tang

et al. 2023

IEEE Access

View full text Add to dashboard Cite

With the rising number of actual data, the challenges of huge model operations and poor generalization capacity arise, making the selection of the right feature set a significant issue. This study proposes ImprovedRFECV, an enhanced feature selection approach for cross-validated recursive feature elimination (RFECV). The algorithm first increases the robustness of the optimal feature subset by randomly sampling different data, building multiple models, and comparing the scores. Simultaneously, L1 regularization term and L2 regularization term scores are introduced to thoroughly evaluate the value of each feature, reducing the influence on the anti-interference term and further improving the algorithm's accuracy and stability. Additionally, a multi-model ensemble learning framework is utilized to promote generalization ability and effectively prevent overfitting. Finally, a both-end expansion removal strategy is adopted to solve the problem of strong covariance of features while enhancing the flexibility of the algorithm. The experimental results show that, when compared to the RFECV algorithm, the ImprovedRFECV algorithm obtains fewer optimal average features and performs better on the optimal feature subset on five datasets from five different domains, demonstrating the algorithm's high robustness and generalization ability.

show abstract

Construction Cost Index Prediction Based on Machine Learning

2023

2023 International Conference on Applied Intelligence and Sustainable Computing (ICAISC)

View full text Add to dashboard Cite

A hybrid feature selection method combining Gini index and support vector machine with recursive feature elimination for gene expression classification

Cited by 4 publications

References 0 publications

Maize Variety Identification Based on Support Vector Machines

Maize Variety Identification Based on Support Vector Machines

A More Flexible and Robust Feature Selection Algorithm

Construction Cost Index Prediction Based on Machine Learning

Contact Info

Product

Resources

About