Track: Research Track |
| Machine Learning Approaches for QAM-16 Demodulation: Evaluating Decision Trees and Random Forests as Hardware Alternatives |
| Quadrature Amplitude Modulation (QAM) is widely used in modern wireless communication systems to transmit data efficiently. Conventional QAM transceivers rely on specialized hardware to quickly and accurately modulate, transmit, and demodulate signals. However, hardware-based transceivers are expensive and slow to adapt to evolving technologies. In this research, we examine the potential of replacing hardware with Machine Learning (ML)-based models in QAM transceivers while maintaining performance standards. Using a QAM-16 gray code constellation, we simulate a QAM transceiver and generate a dataset to train machine learning models for signal decoding. We evaluated and compared the accuracy, operational speed, and functionality of decision trees and random forests models against each other. The results of this study show that decision trees are the best model when bounded by a maximum depth. |
|
| Presentation Video |
| Presentation Notes |
|
Vijay-Machine-Learning-Approaches-for-QAM-16-Demodulation.pdf |
Real Time Communications Conference & Expo at Illinois Tech
IEEE International Conference
Follow Us
Share This
