Soft computing techniques are becoming popular in designing real world applications. Researchers are trying to integrate different soft computing paradigms such as fuzzy logic, artificial neural network, genetic algorithms, decision trees etc. to develop hybrid intelligent autonomous classification systems that provide more flexibility by exploiting tolerance and uncertainty of real life situat...

Validating or accessing the accuracy of soft classification maps has rapidly developed over the past few years. This assessment employs a soft error matrix as generalized from the traditional, hard classification error matrix. However, the impact of positional error on the soft classification is uncertain and whether the well-accepted half-pixel registration accuracy is suitable for the soft cl...

Subspace methods of pattern recognition form an interesting and popular classiication paradigm. The earliest sub-space method of classiication was the CLass Featuring Information Compression (CLAFIC) which associated with each class a corresponding linear subspace. Local subspace classiication methodologies which have enhanced classii-cation power by associating more than one linear subspace wi...

A classifier is called consistent with respect to a given set of classlabeled points if it correctly classifies the set. We consider classifiers defined by unions of local separators and propose algorithms for consistent classifier reduction. The expected complexities of the proposed algorithms are derived along with the expected classifier sizes. In particular, the proposed approach yields a c...

Hard and soft classifiers are two important groups of techniques for classification problems. Logistic regression and Support Vector Machines are typical examples of soft and hard classifiers respectively. The essential difference between these two groups is whether one needs to estimate the class conditional probability for the classification task or not. In particular, soft classifiers predic...

In clinical applications, neural networks must focus on and highlight the most important parts of an input image. Soft-Attention mechanism enables a network to achieve this goal. This paper investigates effectiveness in deep architectures. The central aim is boost value features suppress noise-inducing features. We compare performance VGG, ResNet, Inception ResNet v2 DenseNet architectures with...

This work introduces an iterative soft cluster refinement method that extensively uses soft cluster evaluation to determine which clusters would discriminate between classes in a classification scheme. This iterative refinement is part of the continuous iterative guided spectral class rejection (CIGSCR) classification method for remotely sensed images. Results indicate that CIGSCR produces good...