Signal Modulation Recognition System Based on Different Signal Noise Rate Using Artificial Intelligent Approach

Abstract

Everyone has paid much attention to modulation-type recognition in the past few years. There are many ways to find the modulation type, but only a few good ways to deal with signals with a lot of noise. This study comes up with a way to test how well different machine learning algorithms can handle noise when detecting digital and analogue modulations. This study looks at the four most common digital and analogue modulations: Phase Shift Keying, Quadrature Phase Shift Keying, Amplitude Modulation, and Morse Code. A signal noise rate from -10dB to +25dB is used to find these modulations. We used machine learning algorithms to determine the modulation type like Decision Tree, Random Forest, Support Vectors Machine, and k-nearest neighbours. After the IQ samples had been converted to the amplitude of samples and radio frequency format, the accuracy of each method looked good. Still, in the format of the sample phase, each algorithm's accuracy was less. The results show that the proposed method works to find the signals that have noises. When there is less noise, the random forest algorithm gives better results than SVM, but SVM gives better results when there is more noise.

A Review of Various Machine Learning Techniques and its Application on IoT and Cloud Computing

“…Integration of all these advanced technologies results in a complex networking system while implementing them into a more extensive application [10]. Cloud computing has evolved to include the delivery of infrastructure, platform, software, and, more recently, network 'as a service' encompassing IaaS, PaaS, SaaS, and NaaS [11]. In Saas applications, there is no requirement for installation, maintenance, and storage of any application and users can access SaaS applications using only internet connectivity.…”