Bayesian classifiers based on kernel density estimation: Flexible classifiers

Pérez, Aritz; Larraòaga, Pedro; Inza, Iòaki

doi:10.1016/j.ijar.2008.08.008

Cited by 130 publications

(53 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This information loss can be avoided without losing most of the advantages of a discretized NB replacing it by a FNB, where the recruitment is discrete and predictors continuous. A 'flexible naive Bayes' classifier consists of the 'multinomial naive Bayes' classifier, supported by the 'kernel-based Bayesian network' paradigm proposed in Pérez et al (2009), which are based upon a nonparametric density estimation technique, 'kernel density estimation' (Silverman, 1986). This means that the classifier is built by aggregating a mixture of kernel avoiding any assumption such as normality.…”

Section: Supervised Classification Based Methodologymentioning

confidence: 99%

“…40.9 ± 4.9 42.9 ± 7.8 44.7 ± 11.2 Albacore 58.1 ± 5.8 61.4 ± 6.9 34.6 ± 5.1 Blue whiting 51.3 ± 7.6 52.5 ± 7.8 43.9 ± 8.1 Table 4 Brier score comparison between the pipeline without 'missing imputation' as well as with a 'multinomial naive Bayes' classifier, with 'missing imputation' as well as with a 'multinomial naive Bayes' classifier and with 'missing imputation' as well as replacing the 'multinomial naive Bayes' by a 'flexible naive Bayes'. Pérez et al (2009) and their implementation is available on request from this author.…”

Section: Performance Estimationmentioning

confidence: 99%

See 1 more Smart Citation

Evaluating machine-learning techniques for recruitment forecasting of seven North East Atlantic fish species

Fernandes

Irigoien

Lozano

et al. 2015

Ecological Informatics

Self Cite

View full text Add to dashboard Cite

Section: Supervised Classification Based Methodologymentioning

confidence: 99%

Section: Performance Estimationmentioning

confidence: 99%

Evaluating machine-learning techniques for recruitment forecasting of seven North East Atlantic fish species

Fernandes

Irigoien

Lozano

et al. 2015

Ecological Informatics

Self Cite

View full text Add to dashboard Cite

“…Classifier Training Flexible naïve Bayes was used in this section (Perez, Larranaga, and Inza, 2009). The classifier training consisted of estimating the probability density function for each object and background color feature.…”

Section: B Calculation Of Color Featurementioning

confidence: 99%

Color feature extraction of HER2 Score 2+ overexpression on breast cancer using Image Processing

Muhimmah

Heksaputra

2018

MATEC Web Conf.

View full text Add to dashboard Cite

Abstract. One of the major challenges in the development of early diagnosis to assess HER2 status is recognized in the form of Gold Standard. The accuracy, validity and refraction of the Gold Standard HER2 methods are widely used in laboratory (Perez, et al., 2014). Method determining the status of HER2 (human epidermal growth factor receptor 2) is affected by reproductive problems and not reliable in predicting the benefit from anti-HER2 therapy (Nuciforo, et al., 2016). We extracted color features by methods adopting Statistics-based segmentation using a continuous-scale naïve Bayes approach. In this study, there were three parts of the main groups, namely image acquisition, image segmentation, and image testing. The stages of image acquisition consisted of image data collection and color deconvolution. The stages of image segmentation consisted of color features, classifier training, classifier prediction, and skeletonization. The stages of image testing were image testing, expert validation, and expert validation results. Area segmentation of the membrane is false positive and false negative. False positive and false negative from area are called the area of system failure. The failure of the system can be validated by experts that the results of segmentation region is not membrane HER2 (noise) and the segmentation of the cytoplasm region. The average from 40 data of HER2 score 2+ membrane images show that 75.13% of the area is successfully recognized by the system.

show abstract

“…Pérez et al [50] have recently proposed a new approach for Flexible Bayesian classifiers based on kernel density estimation that extends the FNBC proposed by [42] in order to handle dependent attributes and abandons the independence assumption. In this work, three classifiers: tree-augmented naive Bays, a kdependence Bayesian classifier and a complete graph are adapted to the support kernel Bayesian network paradigm.…”

Section: Appendix: Naive Bayesian Classifiersmentioning

confidence: 99%

Naive possibilistic classifiers for imprecise or uncertain numerical data

Bounhas

Hamed

Prade

et al. 2014

Fuzzy Sets and Systems

View full text Add to dashboard Cite

In real-world problems, input data may be pervaded with uncertainty. In this paper, we investigate the behavior of naive possibilistic classifiers, as a counterpart to naive Bayesian ones, for dealing with classification tasks in presence of uncertainty. For this purpose, we extend possibilistic classifiers, which have been recently adapted to numerical data, in order to cope with uncertainty in data representation. Here the possibility distributions that are used are supposed to encode the family of Gaussian probabilistic distributions that are compatible with the considered data set. We consider two types of uncertainty: i) the uncertainty associated with the class in the training set, which is modeled by a possibility distribution over class labels, and ii) the imprecision pervading attribute values in the testing set represented under the form of intervals for continuous data. Moreover, the approach takes into account the uncertainty about the estimation of the Gaussian distribution parameters due to the limited amount of data available. We first adapt the possibilistic classification model, previously proposed for the certain case, in order to accommodate the uncertainty about class labels. Then, we propose an algorithm based on the extension principle to deal with imprecise attribute values. The experiments reported show the interest of possibilistic classifiers for handling uncertainty in data. In particular, the probability-to-possibility transform-based classifier shows a robust behavior when dealing with imperfect data.

show abstract

Bayesian classifiers based on kernel density estimation: Flexible classifiers

Cited by 130 publications

References 32 publications

Evaluating machine-learning techniques for recruitment forecasting of seven North East Atlantic fish species

Evaluating machine-learning techniques for recruitment forecasting of seven North East Atlantic fish species

Color feature extraction of HER2 Score 2+ overexpression on breast cancer using Image Processing

Naive possibilistic classifiers for imprecise or uncertain numerical data

Contact Info

Product

Resources

About