Ultra-Lightweight Waveform Classification Framework for 6G IoT

A research paper proposes TFZ-Tree, an ultra-lightweight waveform classification framework for resource-constrained devices in 6G IoT. The framework addresses the lack of research on physical-layer waveform type identification (e.g., OFDM, OTFS, LoRa), which is necessary before demodulation and resource scheduling. Existing methods rely on deep neural networks and complex transforms, making deployment difficult. TFZ-Tree uses time-frequency multidimensional features and a cooperative Z-test tree (ZTree) with low-complexity time-domain feature extraction.