New M.E. Thesis Submitted from ECE Student

DESIGN OF DIGITAL FIR FILTER USING RADIAL BASIS FUNCTION NEURAL NETWORK By Harpreet Kaur,Electronics

Abstract
In signal processing, there are many instances in which an input signal to a system contains extra unnecessary content or additional noise which can degrade the quality of the desired portion. In such cases we may remove or filter out the useless samples. For the design of Low pass FIR filters complex calculations are required. Mathematically, by substituting the values of ∆F, δr, δs, Fs and N in any of the methods from window method, frequency sampling method or optimal method we can get the values of filter coefficients h(n). Here, Kaiser Window method has been chosen preferably because of the presence of ripple factor (β). Considering Low pass Filter design, the range of values for the parameters required are calculated. A data sheet through programming is performed on the platform of Matlab. For 30 different range of parameters, the values of h(n) i.e. coefficients of FIR filter, named desired result have been calculated .Artificial Neural Network is a highly simplified model of the structure of the biological neural network. It consists of interconnected processing units. In this thesis, ANN model has been designed which is used to design the low pass FIR in the specified range of parameter. Basically, ANN are of many types like Feed forward neural network, Feedback neural network. But in this is thesis the feed forward neural network has been chosen to design the filter. Here radial basis function in neural networks is used for the training of the neural network. Radial basis function has been chosen. The error is difference between the desired output (i.e. mentioned in data sheet using Matlab) and the actual output obtained at the output layer of the network due to application of the input patterns from the given input-output pattern pair. Firstly, we have calculated the output using the current setting of weights in all the layers. But optimum result has been achieved by adjusting the weights of the network by using the features of radial basis function. The Artificial Neural Network has been trained using datasheet which we have made with the help of programming in the Matlab. Using the radial basis function (newrbe) neural network the goal has been achieved by substituting the values of input parameters:- ∆F , δR , δS, FS and N and filter coefficients (h(n)) as target output. When we simulate this network in the Matlab the values of filter coefficients h(n) which are the required results for the filter design. Secondly, there are three types of graphs which are obtained; first graph is performance graph which has come by training the network means after meeting the goal. Second graphs are error graphs means the error between actual (results from ANN) and desired results (Kaiser window results). Third graph is showing the average error between the Kaiser window response and ANN response. The error graphs show the error between actual and desired results are very less. At the end average error graph is plotted which shows that average error is very small and hence ANN design is validated.

Leisure Readings :