Hierarchical digital modulation classification using cumulants

2000/03/01 by Ananthram Swami, A. Swami, B.M. Sadler +1 · 1,087 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Engineering · Mathematics · #Algorithm #Artificial intelligence #Bandwidth (computing) #Baseband #Blind Source Separation Techniques #Classifier (UML) #Computer science #Cumulant #Digital signal processing #Electronic engineering #Engineering #Fractal and DNA sequence analysis #Higher-order statistics #Mathematics #Modulation (music) #Pattern recognition (psychology) #Signal processing #Statistics #Telecommunications #Wireless Signal Modulation Classification

paper · doi:10.1109/26.837045

published in IEEE Transactions on Communications 48(3), 416-429 (IEEE Communications Society)

openalex publication_date 2000/03/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01

Abstract

A simple method, based on elementary fourth-order cumulants, is proposed for the classification of digital modulation schemes. These statistics are natural in this setting as they characterize the shape of the distribution of the noisy baseband I and Q samples. It is shown that cumulant-based classification is particularly effective when used in a hierarchical scheme, enabling separation into subclasses at low signal-to-noise ratio with small sample size. Thus, the method can be used as a preliminary classifier if desired. Computational complexity is order N, where N is the number of complex baseband data samples. This method is robust in the presence of carrier phase and frequency offsets and can be implemented recursively. Theoretical arguments are verified via extensive simulations and comparisons with existing approaches.

Cited by

• AI Empowered Communication and Radar Modulation Recognition: A Survey
• Deep Modulation Recognition with Multiple Receive Antennas: An End-to-end Feature Learning Approach
• Signal Classification Recovery Across Domains Using Unsupervised Domain Adaptation
• LinksIQ: Robust and Efficient Modulation Recognition with Imperfect Spectrum Scans
• Visualizing Deep Learning-based Radio Modulation Classifier
• Integrated Radio Sensing Capabilities for 6G Networks: AI/ML Perspective
• Accumulated Polar Feature-based Deep Learning for Efficient and Lightweight Automatic Modulation Classification with Channel Compensation Mechanism
• Intelligent Receivers for Electronic Warfare Applications
• Attention-based Adversarial Robust Distillation in Radio Signal Classifications for Low-Power IoT Devices
• Identifying modulation formats using integrated clustering algorithm
• Asynchronous Linear Modulation Classification with Multiple Sensors via Generalized EM Algorithm
• Fast Deep Learning for Automatic Modulation Classification
• Survey of automatic modulation classification techniques: classical approaches and new trends
• Computationally Efficient Modulation Level Classification Based on Probability Distribution Distance Functions
• Channel Access Method Classification for Cognitive Radio Applications
• SigChord: Sniffing Wide Non-sparse Multiband Signals for Terrestrial and Non-terrestrial Wireless Networks

Related

• Multiuser Modulation Classification Based on Cumulants in AWGN Channel
• Channel-robust Automatic Modulation Classification Using Spectral Quotient Cumulants
• Automatic modulation classification technique for radio monitoring
• Revisiting R: Statistical Envelope Analysis for Lightweight RF Modulation Classification
• Database Assisted Automatic Modulation Classification Using Sequential Minimal Optimization