TFZ-Tree: An Ultra-Lightweight Waveform Classification Framework for Resource-Constrained Devices

2026-05-15

AI Summary

This work addresses the challenge of efficiently classifying diverse physical-layer waveforms—such as OFDM, OTFS, and LoRa—in 6G Internet of Things (IoT) scenarios under stringent computational constraints. Existing approaches rely on high-overhead time-frequency transformations and complex deep neural networks, rendering them impractical for resource-limited devices. To overcome this, the authors propose an ultra-lightweight waveform classification framework that integrates low-complexity time-domain features with a cooperative Z-test tree (ZTree), a novel decision-tree architecture that leverages Z-statistic hypothesis testing to autonomously govern node splitting. The method achieves real-time identification of ten candidate 6G waveforms with high accuracy: average classification rates reach 99.5% in AWGN channels and 87.4% under TDL-C multipath fading, while maintaining inference latency below 4 ms per sample on x86 platforms.

Abstract

Under the trend of multi-waveform coexistence in 6G IoT, intelligent receivers must first identify physical-layer waveform types before performing correct demodulation and resource scheduling. However, existing signal identification research largely focuses on symbol-level modulation classification. Research directly targeting physical-layer waveform types (e.g., OFDM, OTFS, LoRa) is not only extremely scarce but also heavily reliant on deep neural networks and complex time-frequency transforms, making deployment on resource-constrained terminals difficult. Symbol modulation classification methods themselves cannot circumvent the prerequisite of ``waveform identification first.''To address this dual gap, we propose an ultra-lightweight waveform classification framework based on time-frequency multidimensional features with a cooperative Z-test tree (ZTree). The framework employs low-complexity time-domain feature extraction, and the classification backend adopts a ZTree optimized by Z-statistical testing, which uses hypothesis testing confidence to automatically control decision tree splitting and size, ensuring efficient execution on resource-limited processors. Tested on ten 6G candidate waveforms including OFDM, OTFS, DSSS, LoRa, and NB-IoT, the method achieves 99.5\% average accuracy under AWGN and 87.4\% under TDL-C multipath channels, with main confusion between OTFS and LoRa. Implemented in C on an x86 platform, single inference latency is under 4~ms. To the best of our knowledge, this is the first work achieving real-time recognition of ten IoT waveform types. Future work will target deployment acceleration on embedded MCUs. Code and dataset are open-sourced at: https://github.com/Einstein-sworder/IoT-wave.

Problem

• waveform classification
• resource-constrained devices
• physical-layer waveform
• 6G IoT
• signal identification

Innovation

• waveform classification
• ultra-lightweight framework
• Z-test tree
• 6G IoT
• resource-constrained devices