With the large volume of electronic portal images acquired and stringent time constraints, it is no longer feasible to follow the convention whereby the radiation oncologist reviews and approves or rejects all portals. For that purpose we have developed a portal image classifier based on the fuzzy k-nearest neighbour (k-NN) algorithm. Each portal image is represented by a feature vector that co...

Our special fuzzy classifier operates on the set of eight features extracted from the 3x3 neighborhood of each pixel. These features are the magnitudes of differences between that pixel and the eight neighboring pixels. They are input into the fuzzy classifier inputs that connect to two fuzzy set membership functions that represent “white background” or “black edge.” The paradigm is simple, com...

We propose the use of a Fuzzy Naive Bayes classifier with a MAP rule as a decision making module for the RoboCup Soccer Simulation 3D domain. The Naive Bayes classifier has proven to be effective in a wide range of applications, in spite of the fact that the conditional independence assumption is not met in most cases. In the Naive Bayes classifier, each variable has a finite number of values, ...

This paper describes a VLSI architecture for classification of multiand hyperspectral imagery using Fuzzy Logic with trapezoidal membership functions. The fuzzy classifier is implemented using a rule-based approach, where each class is defined as a set of sub rules. There is only one sub rule associated to each band within a class. Each sub rule is implemented as a dedicated parallel hardware. ...

This paper presents a comparison between the use of particle swarm optimization and the use of genetic algorithms for tuning the parameters of a novel fuzzy classifier. In the previous work on the classifier, the large amount of time needed by genetic algorithms has been significantly diminished by using an optimized initial population. Even with this improvement, the time spent on tuning the p...

Abstract: This paper presents a neural network classifier for classification of individual wine odors. The data set used for classification was obtained from already reported responses of thick-film tin oxide sensor array exposed to five different alcoholic beverages. The proposed classifier was trained with back-propagation algorithm and fuzzy memberships were used as target vectors in the out...

This paper combines the novel concept of Fuzzy Gaussian Inference(FGI) with Genetic Programming (GP) in order to accurately classify real natural 3d human Motion Capture data. FGI builds Fuzzy Membership Functions that map to hidden Probability Distributions underlying human motions, providing a suitable modelling paradigm for such noisy data. Genetic Programming (GP) is used to make a time dep...

Pattern classification is an important task for many practical systems. Many classifier systems rely on similarity measures to classify unknown patterns. Signal patterns are an interesting class of patterns exhibited in many sensorbased systems. In this paper we present three fuzzy similarity measures that can be used for signal pattern classification. We use the three fuzzy similarity measures...

Supervised classification of data affected by noise or error, with unknown probability distribution, is a challenging task. To this extend, we propose the Fuzzy Regularized Eigenvalue Classifier, based on a recent technique to classify data in two or more classes. We compare the execution time and accuracy of the classifier with other de facto standard methods. With the adoption of a novel memb...

Naive Bayes classifiers are a well-known and powerful type of classifiers that can easily be induced from a dataset of sample cases. However, the strong conditional independence and distribution assumptions underlying them can sometimes lead to poor classification performance. Another prominent type of classifiers are neuro-fuzzy classification systems, which derive (fuzzy) classifiers from dat...