Case Study · PhD Research

DBSCAN-based RF Classifier

A single FPGA architecture that identifies the modulation of an incoming radio signal and estimates its SNR at the same time, in the hardware footprint usually needed for one of those jobs. It matches deep-learning accuracy with zero RAM, using a novel O(n) pipelined DBSCAN, and runs faster and far cooler than the state of the art.

Read the thesis Source on GitHub


The idea

Why build it

Cognitive radio and 5G/6G receivers need to know what they are listening to: which modulation scheme a signal uses, and how clean it is. Deep-learning classifiers do this accurately but are far too heavy for the small, low-power hardware at the edge of a network. The goal of the PhD was to reach that same accuracy in a tiny, RAM-free FPGA design that classifies a live signal stream in real time.

How it works

The approach

DUAL

Two jobs, one core

Automatic modulation classification and non-data-aided SNR estimation share a single unified architecture, delivering both capabilities in the footprint usually spent on one.

METHOD

1D DBSCAN decomposition

The 2D constellation is split into two 1D datasets and clustered with DBSCAN, which separates even same-order schemes like 4QAM and 4PSK that other methods confuse.

SORT

Pipelined O(n) sort

A novel pipelined insertion sort keeps the whole DBSCAN at O(n) on a continuous real-time stream with no latency overhead, a previously unreported capability on FPGA.

HARDWARE

Zero-RAM datapath

A fully pipelined datapath with no buffering bottleneck and no RAM, synthesised in Vivado across four configurations from DBMC-50 up to DBMC-1000.

Results

What it achieved

The design matched state-of-the-art deep-learning classification accuracy while eliminating RAM entirely. Against the next fastest comparable design it cut inference latency by 7.5×, and against existing approaches it ran 71.7% more power-efficiently. It sustains roughly 142,857 classifications per second and reaches 100% accuracy at SNR of 8dB or above on 5G modulation sets.

The work was published in the IEEE Open Journal of the Computer Society (2024) and presented at the SAI Computing Conference in London (2023).

FPGA Verilog MATLAB Vivado DSP Published in IEEE


Read the research

The full method, hardware results, and comparisons are in the thesis, with the Verilog, MATLAB, and Python on GitHub.

Read the thesis Source on GitHub