Vehicles Classification Using the HRBF Neural Network
Journal Title: Computer Science and Mathematical Modelling - Year 2011, Vol 0, Issue 7
Abstract
The paper presents the problem of using a neural network for military vehicle classification on the basis of ground vibration. One of the main elements of the system is a unit called the geophone. This unit allows to measure the amplitude of ground vibration in each direction for a certain period of time. The value of the amplitude is used to fix the characteristic frequencies of each vehicle. If we want to fix the main frequency it is necessary to use the Fourier transform. In this case the fast Fourier transform FFT was used. Since the neural network (Hyper Radial Basis Function network) was used, a learning set has to be prepared.Please find the attached results of using the HRBF neural network, which include: examples of learning, validation and test sets, the structure of the networks and the learning algorithm, learning and testing results.
Authors and Affiliations
Roman Wantoch-Rekowski
Keywords
Related Articles
- EP ID EP63170
- DOI -
- Views 139
- Downloads 0
Property analysis of multi-label classifiers in the example of determining the initial medical diagnosis
Automatic construction of a semantic model of disease symptoms based on text corpus
The research described in article refers the medical data. Descriptions of diagnostic technologies results and descriptions of diseases form the text corpus. The corpus is the basis for building a semantic model of sympt...
Calculating matrix form of an operator describing complex quantum circuit
The article contains a method′s description, which allows to calculate matrix form of quantum operator representing quantum circuit, made of quantum gates (in case, when matrix representations of these gates are known)....
Model procesu ubywania w sytuacji istnienia obiektów pozornych
Do Networks Control the World? From Euler to Barabasi
In the paper problem of multi-applications of graph and networks theory models and methods is considered. The paper is especially focused on specific features of real networks. Analysis methods of these networks, their p...