AI 中文总结
本文提出用于多任务射频信号识别的异构神经网络加速器，结合紧凑注意力增强CNN与LSDec，通过新型硬件架构及调度优化资源。在三个数据集上有高准确率，端到端推理延迟低，对嵌入式和边缘设备的多任务频谱智能应用有效。
AI 中文摘要
本文提出了一种用于多任务射频信号识别的异构神经网络加速器，支持自动调制识别（AMR）、硬件木马隐蔽信道（HT-CC）检测和全球导航卫星系统干扰分类。我们引入了一种紧凑的注意力增强卷积神经网络（CNN），结合LSDec（一种可学习的流抽取器，实现自适应时间下采样和灵活输入长度）。硬件架构集成了新型双流水线、融合卷积池化引擎和基于DMA的流，以最小化内存流量和延迟。加速器上的协同执行调度和SIMD优化的CPU内核减少了硬件资源使用，同时保持高性能和任务级灵活性。在三个数据集上，该系统在RadioML2018数据集上对于AMR在4dB信噪比以上平均准确率≥99%，在HT-CC数据集上为90%，在GNSS干扰数据集上为99.5%。加速器每帧端到端推理延迟为98微秒，证明其对嵌入式和边缘设备上低功耗、延迟关键的多任务频谱智能应用有效。
英文摘要
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.
CommentsAccepted for publication in IEEE Transactions on Very Large Scale Integration (VLSI) Systems (TVLSI). 14 pages, 11 figures
DOI：10.1109/TVLSI.2026.3715734
