A novel technique for speaker independent automated speech recognition is proposed. We take a segment model approach to Automated Speech Recognition (ASR), considering the trajectory of an utterance in vector space, then classify using a modified Probabilistic Neural Network (PNN) and maximum likelihood rule. The system performs favourably with established techniques. Our system achieves in exc...

This paper address the problem of dust storm detection based on multispectral image analysis from a probabilistic point of view. Two classifiers are designed, one based on classic probability theory and other based on a probabilistic computational intelligence approach. The first classifier is designed under the Maximum Likelihood Estimation (MLE) model, and the second with a Probabilistic Neur...

Automated classification of brain MRI is important for the analysis of tumor. In this paper magnetic resonance imaging (MRI) is considered to solve the problem of automatic classification of brain images. It presents the classification system with three stages. It consists of discrete wavelet decomposition of the image, texture feature extraction from the LH and HL sub bands and final classific...

In this paper, a novel and simple iris feature extraction technique is proposed for iris recognition of high performance. We use one dimensional circular ring to represent iris features. The reduced and significant features afterward are extracted by Sobel operator and 1D wavelet transform. So as to improve the accuracy, this paper combines Probabilistic Neural Network (PNN) and Particle Swarm ...

in this study, a model for estimating the nfs thermal conductivity by using a gmdh-pnn has been investigated. nfs thermal conductivity was modeled as a function of the nanoparticle size, temperature, nanoparticle volume fraction and the thermal conductivity of the base fluid and nanoparticles. for this purpose, the developed network contains 8 layers with 2 inputs in each layer and also trainin...

Automation of power system fault identification using information conveyed by the wavelet analysis of power system transients is proposed. Probabilistic Neural Network (PNN) for detecting the type of fault is used. The work presented in this paper is focused on identification of simple power system faults. Wavelet Transform (WT) of the transient disturbance caused as a result of occurrence of f...

Soft computing methods and various sentiment indicators are employed to conduct out-of-sample predictions of the future sign of the stock market returns. In particular, we assess the performance of the probabilistic neural network (PNN) against the back-propagation neural network (BPNN) in predicting technology stocks and NYSE up and down moves. Genetic algorithms (GA) are employed to optimize ...

Several methods to identify plants have been proposed by several researchers. Commonly, the methods did not capture color information, because color was not recognized as an important aspect to the identification. In this research, shape and vein, color, and texture features were incorporated to classify a leaf. In this case, a neural network called Probabilistic Neural network (PNN) was used a...

In this paper, we propose a scheme to integrate independent component analysis (ICA) and neural networks for electrocardiogram (ECG) beat classification. The ICA is used to decompose ECG signals into weighted sum of basic components that are statistically mutual independent. The projections on these components, together with the RR interval, then constitute a feature vector for the following cl...