A Modified Naïve Possibilistic Classifier for Numerical Data
نویسندگان
چکیده
In this paper, we propose a modified version of the Näıve Possibilistic Classifier (NPC) which has been already suggested to make decision from numerical data. As the former NPC, the modified classifier makes use of the probability to possibility transformation of Dubois et al. in the continuous case in order to estimate possibilistic beliefs. However, unlike the former NPC which uses the product as a fusion operator, the proposed classifier fuses possibilistic beliefs using the generalized minimum-based algorithm which has been recently proposed as an improvement of the minimum operator for combining possibilistic estimates. Experimental evaluations are conducted on 15 numerical datasets taken from University of California Irvine (UCI) and show that the new version of NPC largely outperforms the former one in terms of accuracy.
منابع مشابه
Naive possibilistic classifiers for imprecise or uncertain numerical data
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 i...
متن کاملPossibilistic classifiers for numerical data
Naive Bayesian Classifiers, which rely on independence hypotheses, together with a normality assumption to estimate densities for numerical data, are known for their simplicity and their effectiveness. However, estimating densities, even under the normality assumption, may be problematic in case of poor data. In such a situation, possibility distributions may provide a more faithful representat...
متن کاملA Naive Bayes Style Possibilistic Classifier
Naive Bayes classifiers can be seen as special probabilistic networks with a star-like structure. They can easily be induced from a dataset of sample cases. However, as most probabilistic approaches, they run into problems, if imprecise (i.e, set-valued) information in the data to learn from has to be taken into account. An approach to handle uncertain as well imprecise information, which recen...
متن کاملCombining Classifier Guided by Semi-Supervision
The article suggests an algorithm for regular classifier ensemble methodology. The proposed methodology is based on possibilistic aggregation to classify samples. The argued method optimizes an objective function that combines environment recognition, multi-criteria aggregation term and a learning term. The optimization aims at learning backgrounds as solid clusters in subspaces of the high...
متن کاملOn solving possibilistic multi- objective De Novo linear programming
Multi-objective De Novo linear programming (MODNLP) is problem for designing optimal system by reshaping the feasible set (Fiala [3] ). This paper deals with MODNLP having possibilistic objective functions coefficients. The problem is considered by inserting possibilistic data in the objective functions coefficients. The solution of the problem is defined and established under the using of effi...
متن کامل