FREQUENCY ESTIMATION USING AN ARTIFICIAL NEURAL NETWORK AND THE DISCRETE FOURIER TRANSFORM.
Saved in:
| Title: | FREQUENCY ESTIMATION USING AN ARTIFICIAL NEURAL NETWORK AND THE DISCRETE FOURIER TRANSFORM. |
|---|---|
| Authors: | Burtea, Daniela Giorgiana1, Tufisi, Cristian1, Gillich, Gilbert-Rainer1, Constantin, Carla-Silvana1 |
| Source: | Annals of 'Constantin Brancusi' University of Targu-Jiu. Engineering Series / Analele Universităţii Constantin Brâncuşi din Târgu-Jiu. Seria Inginerie. 2022, Issue 4, p20-26. 7p. |
| Subjects: | Discrete Fourier transforms, Spectral lines, Artificial neural networks, Machine learning |
| Abstract: | There are several known methods that can be applied to estimate the Frequency for short signals, but various research shows that imprecise frequency readings can be obtained due to the large distance between the spectral lines. We propose a machine learning approach for estimating the frequency values between spectral lines. The method uses the data obtained by applying the Discrete Fourier Transform for generating a sinusoidal signal with different lengths and known frequency and amplitude values. The peak amplitudes in the spectrum are similar in shape to that of the sinc function. For determining the amplitudes, three points on the main lobe of the signal are chosen, which will represent the input data for training the ANN. The results obtained by applying the normalized training data for training an artificial neural network that will estimate a correction coefficient for the amplitudes or frequencies of a signal, show that the method is more accurate than other current methods, and the errors resulting from the tests are very small. [ABSTRACT FROM AUTHOR] |
| Copyright of Annals of 'Constantin Brancusi' University of Targu-Jiu. Engineering Series / Analele Universităţii Constantin Brâncuşi din Târgu-Jiu. Seria Inginerie is the property of Universitatea Constantin Brancusi din Targu-Jiu and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
Be the first to leave a comment!
