Modulation Classifier

J Roopesh; Amrutha DC; Meghana Bhushan S N; Keerti Kulkarni

doi:10.32628/CSEIT2410319

Authors

J Roopesh Electronics and Communication Dept, BNM Institute of Technology, Bengaluru, Karnataka, India Author
Amrutha DC Electronics and Communication Dept, BNM Institute of Technology, Bengaluru, Karnataka, India Author
Meghana Bhushan S N Electronics and Communication Dept, BNM Institute of Technology, Bengaluru, Karnataka, India Author
Keerti Kulkarni Associate Professor, ECE, BNM Institute of Technology, Bengaluru, Karnataka, India Author

DOI:

https://doi.org/10.32628/CSEIT2410319

Keywords:

Amplitude values, Power Spectral Density, Signal to Noise Ratio

Abstract

In the realm of wireless communications, automatic modulation classification (AMC) plays a crucial role in identifying the modulation type of incoming signals, enabling efficient spectrum usage in congested wireless environments and other communication systems applications. We present an AMC that takes into consideration various parameters among them the 3 major parameters are amplitude, power spectral density (PSD), and Signal to noise ratio (SNR), with the help of machine learning that is Support Vector machine in specific, within the MATLAB environment helps us in classifying the different types of signal that is QPSK, BPSK, QAM, 64QAM and PAM4.Therefore our AMC significantly contributes to the wireless communication by significantly boosting the different modulation techniques and thereby improving the spectrum efficiency.

Downloads

Download data is not yet available.

References

Automatic Modulation Classification Based on Deep Learning for Software-Defined Radi Authors:Peng WuvBei Sun Shaojing Su Junyu W

Frequency-based Automated Modulation Sahay,Christopher ,G. Brinton, David J. Love

Classification Authors:Rajeev Machine Learning-Based Automatic Modulation Recognition for Wireless Communications Authors:Bachir Jidid,Iyad Dayoub,Kais Hassan,Wei Hong

A Survey of Automatic Modulation Classification Techniques Authors:Octavia A. ,Ali Abdi2 ,Wei Su3

Machine learning model to classify modulation techniques Authors:Nadakuditi Durga Indira,Matcha Venu Gopala Rao

Modulation Classification Using Compressed Sensing Authors:Xiaojun Guo ,Xiaopeng Tan

A Survey of Modulation Classification Using Deep Learning: Signal Representation and Data Preprocessing - Shengliang Peng ,Shujun Sun, Yu-Dong Yao published in IEEE Transactions on Neural Networks and Learning Systems ( Volume: 33, Issue: 12, December 2022) DOI: https://doi.org/10.1109/TNNLS.2021.3085433

Performance of Feature-Based Techniques for Automatic Digital Modulation Recognition and Classification- Dhamyaa H. Al-Nuaimi ,Ivan A. Hashim ,Intan S. Zainal Abidin ,Laith B. Salman and Nor Ashidi Mat Isa published on 26 November 2019

A Survey of Automatic Modulation Classification Techniques:Classical Approaches and New Trends - Octavia A. Dobre1 , Ali Abdi , Yeheskel Bar-Ness and Wei Su published on 2015

Zhou, S., Yin, Z., Wu, Z. et al. A robust modulation classification method using convolutional neural networks. EURASIP J. Adv. Signal Process. 2019, 21 (2019). https://doi.org/10.1186/s13634-019-0616- DOI: https://doi.org/10.1186/s13634-019-0616-6

Han H, Ren Z, Li L, Zhu Z. Automatic Modulation Classification Based on Deep Feature Fusion for High Noise Level and Large Dynamic Input. Sensors (Basel). 2021 Mar 17;21(6):2117. doi: 10.3390/s21062117. PMID: 33803042; PMCID: PMC8003108. DOI: https://doi.org/10.3390/s21062117