Computationally Efficient Modulation Level Classification Based on Probability Distribution Distance Functions

TL;DR

This paper introduces a new modulation level classification method utilizing probability distribution distance functions, specifically modified Kuiper and Kolmogorov-Smirnov distances, achieving high accuracy with low computational complexity.

Contribution

It proposes a novel, computationally efficient MLC approach based on distribution distance functions, outperforming existing cumulant and goodness-of-fit based methods.

Findings

Achieves superior classification accuracy under AWGN with SNR mismatch and phase jitter.

Demonstrates low computational complexity compared to state-of-the-art methods.

Theoretically derives performance metrics and verifies them via simulations.

Abstract

We present a novel modulation level classification (MLC) method based on probability distribution distance functions. The proposed method uses modified Kuiper and Kolmogorov-Smirnov distances to achieve low computational complexity and outperforms the state of the art methods based on cumulants and goodness-of-fit tests. We derive the theoretical performance of the proposed MLC method and verify it via simulations. The best classification accuracy, under AWGN with SNR mismatch and phase jitter, is achieved with the proposed MLC method using Kuiper distances.