Distributed Deep Learning Models for Wireless Signal Classification with Low-Cost Spectrum Sensors

TL;DR

This paper introduces an LSTM-based model for automatic modulation classification in wireless spectrum sensing, achieving high accuracy without expert features, and explores its deployment on low-cost, distributed sensors with reduced data communication.

Contribution

A novel LSTM model for modulation classification that learns from raw time domain data, adaptable to variable symbol rates, and suitable for low-power sensor deployment.

Findings

Achieves ~90% accuracy across 0-20dB SNR conditions.

Successfully classifies variable symbol rate signals with 75% accuracy.

Demonstrates feasibility of low-data and quantized models for sensor deployment.

Abstract

This paper looks into the technology classification problem for a distributed wireless spectrum sensing network. First, a new data-driven model for Automatic Modulation Classification (AMC) based on long short term memory (LSTM) is proposed. The model learns from the time domain amplitude and phase information of the modulation schemes present in the training data without requiring expert features like higher order cyclic moments. Analyses show that the proposed model yields an average classification accuracy of close to 90% at varying SNR conditions ranging from 0dB to 20dB. Further, we explore the utility of this LSTM model for a variable symbol rate scenario. We show that a LSTM based model can learn good representations of variable length time domain sequences, which is useful in classifying modulation signals with different symbol rates. The achieved accuracy of 75% on an input sample length of 64 for which it was not trained, substantiates the representation power of the model. To reduce the data communication overhead from distributed sensors, the feasibility of classification using averaged magnitude spectrum data, or online classification on the low cost sensors is studied. Furthermore, quantized realizations of the proposed models are analyzed for deployment on sensors with low processing power.