Adjusting the Outputs of a Classifier to New a Priori Probabilities May Significantly Improve Classification Accuracy: Evidence from a multi-class problem in remote sensing

Published 28 June 2001Open access

Patrice Latinne, Marco Saerens, Christine Decaestecker

Citations37

TL;DR

A simple iterative procedure that allows to correct the outputs of a classifier with respect to the new a priori probabilities of a new data set to be scored, even when these new a Priori probabilities are unknown in advance is introduced.

Abstract

In the present study, we introduce a simple iterative procedure that allows to correct the outputs of a classifier with respect to the new a priori probabilities of a new data set to be scored, even when these new a priori probabilities are unknown in advance. We also show that a significant increase in classification accuracy can be observed when using this procedure properly. More specifically, by applying the correcting procedure on the outputs of a simple logistic regression model, we observed an increase of 5.8% of classification rate on a di#cult real-world multi-class problem -- the automatic labeling of geographical maps based on remote sensing information.

Keywords

Computer ScienceMathematics

Revue économiqueNonparametric Statistics for the Behavioral Sciences

35,492 Citations1958Henri Guitton, Sidney Siegel

C4.5: Programs for Machine Learning

23,665 Citations1992J. R. Quinlan

A complete guide to the C4.5 system as implemented in C for the UNIX environment, which starts from simple core learning methods and shows how they can be elaborated and extended to deal with typical problems such as missing data and over hitting.

Machine LearningBagging Predictors

16,973 Citations1996Leo Breiman

View PDF

Journal of the American Statistical AssociationProbability, Random Variables, and Stochastic Processes.

16,350 Citations1984Julia Abrahams, A. Papoulis

View PDF

IEEE Transactions on Pattern Analysis and Machine IntelligenceThe random subspace method for constructing decision forests

6,737 Citations1998Tin Kam Ho

A method to construct a decision tree based classifier is proposed that maintains highest accuracy on training data and improves on generalization accuracy as it grows in complexity.

TechnometricsThe EM Algorithm and Extensions

5,108 Citations1998Debashis Kushary, Geoffrey J. McLachlan +1 more

Neural ComputationApproximate Statistical Tests for Comparing Supervised Classification Learning Algorithms

3,654 Citations1998Thomas G. Dietterich

This article reviews five approximate statistical tests for determining whether one learning algorithm outperforms another on a particular learning task and measures the power (ability to detect algorithm differences when they do exist) of these tests.

Neural ComputationAdjusting the Outputs of a Classifier to New a<i>Priori</i>Probabilities: A Simple Procedure

333 Citations2002Marco Saerens, Patrice Latinne +1 more

The original method, based on the EM algorithm, is shown to be superior to the standard one for a priori probability estimation and always performs better than the original one in terms of classification accuracy, when the a Priori probability conditions differ from the training set to the real-world data.

View PDF

IEEE Transactions on Neural NetworksBuilding cost functions minimizing to some summary statistics

56 Citations2000Marco Saerens

The calculus of variations is used to derive necessary and sufficient conditions on the cost function ensuring that the output of the trained model approximates the conditional expectation of the desired output given the explanatory variables.