A Heterogeneous Neural Network Accelerator for End-to-End Multitask RF Signal Recognition
2026-07-27 • Hardware Architecture
Hardware Architecture
AI summaryⓘ
The authors designed a special computer chip that helps recognize different radio signals and detect problems quickly, like jamming or hidden threats. Their method uses a small, smart neural network that can adjust how it processes signal data to work with different input sizes. They combined efficient hardware techniques to speed up processing while using less memory and power. Tests showed their system is very accurate and fast, making it useful for devices that need quick and reliable signal analysis with limited resources.
neural network acceleratorautomatic modulation recognitionhardware Trojancovert channel detectionGNSS jammingconvolutional neural networkattention mechanismtemporal downsamplingDMA streamingSIMD optimization
Authors
Zhifan Song, Haralampos-G. Stratigopoulos, Hassan Aboushady
Abstract
This paper presents a heterogeneous neural network accelerator for multi-task RF signal recognition, supporting automatic modulation recognition (AMR), hardware-Trojan covert channel (HT-CC) detection, and GNSS jamming classification. We introduce a compact attention-enhanced convolutional neural network (CNN) combined with LSDec, a learnable streaming decimator that enables adaptive temporal downsampling and flexible input lengths. The hardware architecture integrates a novel dual-pipeline, fused convolution-pooling engine with DMA-based streaming to minimize memory traffic and latency. Co-execution scheduling on the accelerator and SIMD-optimized CPU kernels reduces hardware resource usage while preserving high performance and task-level flexibility. Across three datasets, the proposed system achieves $\geq$ 99% average accuracy above 4 dB Signal-to-Noise Ratios (SNRs) on the RadioML2018 dataset for AMR, 90% on the HT-CC dataset, and 99.5% on the GNSS-Jamming dataset. The accelerator sustains an end-to-end inference latency of 98 $μ$s per frame, demonstrating its effectiveness for low-power, latency-critical multi-task spectrum-intelligence applications on embedded and edge devices.