MODULATION CLASSIFICATION BASED ON METHOD OF NEURAL NETWORKS
<p align="justify">We use communication signals with different types and different frequencies fall in a very wide band. Usually, it is required to identify and classify these signals for many applications. Some of these applications are in civilian purposes such as signal confirmati...
Saved in:
| Main Author: | |
|---|---|
| Format: | Final Project |
| Language: | Indonesia |
| Online Access: | https://digilib.itb.ac.id/gdl/view/10434 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Institut Teknologi Bandung |
| Language: | Indonesia |
| Summary: | <p align="justify">We use communication signals with different types and different frequencies fall in a very wide band. Usually, it is required to identify and classify these signals for many applications. Some of these applications are in civilian purposes such as signal confirmation, interference identification, and spectrum management.<p align="justify"><p>On this final project research, Neural Networks and statistic methods are used to classify analogue and digital signals. The signal classification being developed consists of two subsystems: (1) key features extraction (2) modulation classification. The choice of maximum value of spectral power density of the normalized-centred amplitude, standard deviation of the absolute value of the centred non-linear component of the instantaneous phase, standard deviation of the absolute value of the normalized-centred instantaneous amplitude, standard deviation of the absolute value of the normalized-centred instantaneous frequency, the kurtosis of the normalized instantaneous amplitude, dan the kurtosis of the normalized instantaneous frequency measure as key features for the modulation classification based on neural networks. The modulation classification uses two Networks with each two hidden layers and one hidden layer. The results are summarized for AM, DSB-AM, LSB-AM, USB-AM, FM, BPSK, QPSK, BFSK, and QFSK signals.<p align="justify"><p>Results of this project are the success rate of modulation classification and the function of key features in modulation classification. <br />
|
|---|