Non Coherent Receiver

Non-coherent receivers are designed to process signals without requiring precise knowledge of the channel's characteristics, offering advantages in terms of reduced complexity and power consumption. Current research focuses on improving their performance in various applications, including optical fiber communication (using techniques like clustered equalizers and Fourier convolution networks), federated learning (employing multi-resolution model broadcasting and over-the-air computation with balanced number systems), and radio frequency fingerprint identification (through domain adaptation methods). These advancements are significant because they enable more efficient and robust communication systems across diverse contexts, particularly in resource-constrained environments or scenarios with high levels of interference.