CBRG: A Novel Algorithm for Handling Missing Data Using Bayesian Ridge Regression and Feature Selection Based on Gain Ratio
Existing imputation methods may lead to biased predictions and decrease or increase the statistical influence which leads to improper estimations. Several missing value imputation approaches performance depends on the size of the dataset and the number of missing values within the dataset. In this w...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9277540/ |
_version_ | 1811209728813957120 |
---|---|
author | Samih M. Mostafa Abdelrahman S. Eladimy Safwat Hamad Hirofumi Amano |
author_facet | Samih M. Mostafa Abdelrahman S. Eladimy Safwat Hamad Hirofumi Amano |
author_sort | Samih M. Mostafa |
collection | DOAJ |
description | Existing imputation methods may lead to biased predictions and decrease or increase the statistical influence which leads to improper estimations. Several missing value imputation approaches performance depends on the size of the dataset and the number of missing values within the dataset. In this work, the authors proposed a novel algorithm for manipulating missing data versus some common imputation approaches. The proposed algorithm imputes missing values in cumulative order depending on the gain ratio (GR) feature selection (to select the candidate feature to be manipulated) and the Bayesian Ridge Regression (BRR) technique (to build the predictive model). Each imputed feature will be used to manipulate the missing values in the following selected candidate feature. The proposed algorithm was implemented on eight different datasets after generating different missing values proportions from the missingness mechanisms. The imputation performance was calculated in terms of imputation time, mean absolute error (MAE), coefficient of determination (<inline-formula> <tex-math notation="LaTeX">$R^{2}$ </tex-math></inline-formula>), and root-mean-square error (RMSE). The results show the efficiency of the proposed algorithm when imputing any dataset with any number of missing data from any missingness mechanism. |
first_indexed | 2024-04-12T04:45:32Z |
format | Article |
id | doaj.art-2b1b59e2998b4f69be67d7af9e7ae634 |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-04-12T04:45:32Z |
publishDate | 2020-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-2b1b59e2998b4f69be67d7af9e7ae6342022-12-22T03:47:31ZengIEEEIEEE Access2169-35362020-01-01821696921698510.1109/ACCESS.2020.30421199277540CBRG: A Novel Algorithm for Handling Missing Data Using Bayesian Ridge Regression and Feature Selection Based on Gain RatioSamih M. Mostafa0https://orcid.org/0000-0001-9234-5898Abdelrahman S. Eladimy1https://orcid.org/0000-0003-3254-0872Safwat Hamad2https://orcid.org/0000-0002-1338-8724Hirofumi Amano3https://orcid.org/0000-0002-8187-4337Computer Science-Mathematics Department, Faculty of Science, South Valley University, Qena, EgyptComputer Science-Mathematics Department, Faculty of Science, South Valley University, Qena, EgyptScientific Computing Department, Faculty of Computer and Information Sciences, Ain Shams University, Cairo, EgyptResearch Institute for Information Technology, Kyushu University, Fukuoka, JapanExisting imputation methods may lead to biased predictions and decrease or increase the statistical influence which leads to improper estimations. Several missing value imputation approaches performance depends on the size of the dataset and the number of missing values within the dataset. In this work, the authors proposed a novel algorithm for manipulating missing data versus some common imputation approaches. The proposed algorithm imputes missing values in cumulative order depending on the gain ratio (GR) feature selection (to select the candidate feature to be manipulated) and the Bayesian Ridge Regression (BRR) technique (to build the predictive model). Each imputed feature will be used to manipulate the missing values in the following selected candidate feature. The proposed algorithm was implemented on eight different datasets after generating different missing values proportions from the missingness mechanisms. The imputation performance was calculated in terms of imputation time, mean absolute error (MAE), coefficient of determination (<inline-formula> <tex-math notation="LaTeX">$R^{2}$ </tex-math></inline-formula>), and root-mean-square error (RMSE). The results show the efficiency of the proposed algorithm when imputing any dataset with any number of missing data from any missingness mechanism.https://ieeexplore.ieee.org/document/9277540/Bayesian ridge regressionimputationgain ratiomissingness mechanismsmissing value |
spellingShingle | Samih M. Mostafa Abdelrahman S. Eladimy Safwat Hamad Hirofumi Amano CBRG: A Novel Algorithm for Handling Missing Data Using Bayesian Ridge Regression and Feature Selection Based on Gain Ratio IEEE Access Bayesian ridge regression imputation gain ratio missingness mechanisms missing value |
title | CBRG: A Novel Algorithm for Handling Missing Data Using Bayesian Ridge Regression and Feature Selection Based on Gain Ratio |
title_full | CBRG: A Novel Algorithm for Handling Missing Data Using Bayesian Ridge Regression and Feature Selection Based on Gain Ratio |
title_fullStr | CBRG: A Novel Algorithm for Handling Missing Data Using Bayesian Ridge Regression and Feature Selection Based on Gain Ratio |
title_full_unstemmed | CBRG: A Novel Algorithm for Handling Missing Data Using Bayesian Ridge Regression and Feature Selection Based on Gain Ratio |
title_short | CBRG: A Novel Algorithm for Handling Missing Data Using Bayesian Ridge Regression and Feature Selection Based on Gain Ratio |
title_sort | cbrg a novel algorithm for handling missing data using bayesian ridge regression and feature selection based on gain ratio |
topic | Bayesian ridge regression imputation gain ratio missingness mechanisms missing value |
url | https://ieeexplore.ieee.org/document/9277540/ |
work_keys_str_mv | AT samihmmostafa cbrganovelalgorithmforhandlingmissingdatausingbayesianridgeregressionandfeatureselectionbasedongainratio AT abdelrahmanseladimy cbrganovelalgorithmforhandlingmissingdatausingbayesianridgeregressionandfeatureselectionbasedongainratio AT safwathamad cbrganovelalgorithmforhandlingmissingdatausingbayesianridgeregressionandfeatureselectionbasedongainratio AT hirofumiamano cbrganovelalgorithmforhandlingmissingdatausingbayesianridgeregressionandfeatureselectionbasedongainratio |