radioml

Code for "Complex-Valued Depthwise Separable Convolutional Neural Network for Automatic Modulation Classification"

Energy-Modulated Gain (EMG) that the sufficient-statistic-driven conditional normalization layer for automatic modulation recognition, with EMGNet and five baselines on RML2016.10a, RML2018.01a, and HisarMod2019.

IQ-free LLM-controller for online automatic modulation recognition (AMR): the LLM plans deterministic RF tools and never sees raw IQ. Code, results, and figures.

Newton–Puiseux for CVNNs: complete toolkit for uncertainty mining, confidence calibration and local symbolic-numeric analysis on ECG (MIT-BIH) and wireless IQ data (RadioML 2016.10A).

Neural DFT: GPU-accelerated learnable spectral layers for real-time RF modulation classification

Classification of radio signals on a neuromorphic chip in space

Provably sound agentic control for self-healing Open RAN: action repair and predicate-coverage analysis. Manuscript, simulator, and aggregated results.

Exploring constraint-aware neural network design through LUT-based FPGA pruning and RadioML signal classification analysis.

Automatic modulation classification from I/Q signals using signal processing, physical feature engineering and classical machine learning.

AI-assisted SIGINT fusion platform: Kafka ingest, ONNX modulation classifier trained on RadioML, Kalman/Hungarian emitter fusion, hybrid-RAG LangGraph analyst, React operator console