Wyniki wyszukiwania:

This book presents the real time speaker identification system using artificial neural network. This system takes the speech signal as its input. The input signal is then filtered to remove noise. After preprocessing, frame blocking and windowing the features are obtained using signal processing techniques. The extracted feature is then fed to the multilayer back propagation neural network as input. Thus the network is trained and creates a knowledge base for identification. The same procedures are applied for identification but the only difference is that the neural network uses the...

The Traveling Salesman Problem (TSP) has already been solved in the semi-optimal manners using the numbers of different methods. Among them, genetic algorithms (GA) are pre-dominating. This paper presents a new approach to solve this problem using the Simplified Bi-directional Associative Memory (sBAM), a type of Artificial Neural Network. To get a comparative idea of its performance, the same problem has been solved using a genetic algorithm. In this paper, performance has been analyzed of a TSP by Genetic Algorithm (GA) and sBAM. Finally we proved that sBAM provide real time highly faster...

This paper proposes intersection model and strategy for road extraction from high resolution satellite images. Satellite images are rich in information. For Geographic Information System (GIS), many features require fast and reliable extraction of roads and intersections. They are also complex to analyze. Satellite image provides useful data that is extracted from satellite image of the urban area. Automatic extraction of the road intersections from the urban areas has been a challenging topic because the high resolution satellite images contain multiple layers that represent roads,...