IMPROVED BAYESIAN FEATURE SELECTION AND CLASSIFICATION METHODS USING BOOTSTRAP PRIOR TECHNIQUES
| dc.contributor.author | Oyebayo Ridwan Olaniran | |
| dc.contributor.author | Saidat Fehintola Olaniran | |
| dc.contributor.author | Yahya, Waheed Babatunde | |
| dc.contributor.author | Banjoko, Alabi | |
| dc.contributor.author | Garba, Mohammed Kabir | |
| dc.contributor.author | Amusa, Lateef | |
| dc.contributor.author | Gatta F.N | |
| dc.date.accessioned | 2023-07-27T08:25:42Z | |
| dc.date.available | 2023-07-27T08:25:42Z | |
| dc.date.issued | 2016 | |
| dc.description.abstract | In this paper, the behavior of feature selection algorithms using the traditional t-test, Bayesian t-test using MCMC and Bayesian two sample test using proposed bootstrap prior technique were determined. In addition, we considered some frequentist classification methods like k- Nearest Neighbor (k-NN), Logistic Discriminant (LD), Linear discriminant analysis (LDA), Quadratic discriminant analysis (QDA) and Naïve Bayes when conditional independence assumption is violated. Two new Bayesian classifiers (B-LDA and B-QDA) were developed within the frame work of LDA and QDA using the bootstrap prior technique. The model parameters were estimated using Bayesian approach via the posterior distribution that involves normalizing the prior for the attributes and the likelihood from the sample in a Monte Carlo experiment. The bootstrap prior technique was incorporated into the Normal-Inverse-Wishart natural conjugate prior for the parameters of the multivariate normal distribution where the scale and location parameters were required. All the classifiers were implemented on the simulated data at 90:10 training-test data ratio. The efficiencies of these classifiers were assessed using the misclassification error rate, sensitivity, specificity, positive predictive value, negative predictive value and area under the ROC curve. Results from various analyses established the supremacy of the proposed Bayes classifiers (B-LDA and B-QDA) over the existing frequentists and Naïve Bayes classification methods considered. All these methods including the proposed one were implemented on a published binary response microarray data set to validate the results from the simulation study. | |
| dc.identifier.citation | Olaniran, O.R., & Olaniran, S. F., & Yahya, Waheed Babatunde & Banjoko, Alabi & Garba, Mohammed Kabir & Amusa, Lateef & Gatta F.N. (2016). Improved Bayesian Feature Selection and Classification methods using Bootstrap prior technique. Anale Seria Informatica. 14. 46 - 52. Tibiscus University of Timisoara, Romania | |
| dc.identifier.uri | https://scholar.google.com/scholar?oi=bibs&cluster=1077937408211574578&btnI=1&hl=en | |
| dc.identifier.uri | http://www.anale-informatica.tibiscus.ro/download/lucrari/14-2-07-Olaniran.pdf | |
| dc.identifier.uri | https://kwasuspace.kwasu.edu.ng/handle/123456789/732 | |
| dc.language.iso | en | |
| dc.publisher | Faculty of Computer and Applied Computer Science, Tibiscus University of Timisoara, Romania | |
| dc.relation.ispartofseries | Anale Seria Informatica. 14. 46 - 52; 46 - 52 | |
| dc.title | IMPROVED BAYESIAN FEATURE SELECTION AND CLASSIFICATION METHODS USING BOOTSTRAP PRIOR TECHNIQUES | |
| dc.type | Article |