In this paper, we propose a novel feature for recognizing handwritten Odia numerals. By using polygonal approximation, each numeral is segmented into seg ments of equal pixel counts where the centroid of the character is kept as the or igin. Three primitive contour features namely, distance (l), angle (θ), and arc-to-ch ord ratio (r), are extracted from these segments. These features are used i...

In this paper, a wavelet-based neural network classifier for recognizing power quality disturbances is implemented and tested under various transient events. The discrete wavelet transform (DWT) technique is integrated with the probabilistic neural network (PNN) model to construct the classifier. First, the multi-resolution analysis (MRA) technique of DWT and the Parseval’s theorem are employed...

Breast cancer is one of the most common tumors related to death in women in many countries. In this paper, a novel neural network classification model is developed. The proposed model uses floating centroids method and particle swarm optimization algorithm with inertia weight as optimizer to improve the performance of neural network classifier. Wisconsin breast cancer datasets in UCI Machine Le...

The continuous complex wavelet transform offers a convenient framework for neural spike sorting. Results show that wavelet-based neural spike detection outperforms simple threshold detection, especially with signals with low signal to noise ratio. Classification of action potentials using their signatures in wavelet space performed as well as a classifier based upon principal components analysi...

Building on previous work in Chinese character recognition, we describe an advanced system of classification using probabilistic neural networks. Training of the classifier starts with the use of distortion modeled characters from four fonts. Statistical measures are taken on a set of features computed from the distorted character. Based on these measures, the space of feature vectors is transf...

We propose a generative classifier which models the hidden factors that underpin the neural representation of objects with a multivariate multiple linear regression model. Our results indicate that object features derived from a feature norming study or word cooccurrences in web corpus can capture some of these hidden factors and explain a significant portion of the systematic variance in the n...

Speaker Recognition is a challenging task and is widely used in many speech aided applications. This study proposes a new Neural Network (NN) model for identifying the speaker, based on the acoustic features of a given speech sample extracted by applying wavelet transform on raw signals. Wrapper based feature selection applies dimensionality reduction by kernel PCA and ranking by Info gain. Onl...

In this paper, several neural network and statistical learning approaches are proposed that learn to make human like decisions for the job assignment problem of the US Navy. Comparison study of Feedforward Neural Networks (FFNN), Adaptive Neuro-Fuzzy Inference System (ANFIS), Support Vector Machine (SVM) and Adaptive Bayes (AB) classifier with Generalized Estimation Equation (GEE) is provided. ...