针对嵌入式设备优化干扰检测模型，实现高效推理。
Efficient Network Inference via Hardware-Aware Architecture Search, Model Pruning & Quantization
- 结合结构化剪枝与量化压缩模型，降低计算开销。
- 硬件感知架构搜索提升在MCU上的部署效率。
- 适用于实时GNSS干扰监测的轻量级模型设计。
嵌入式全球导航卫星系统（GNSS）干扰监测需要快速、低内存消耗的推理能力，以实时处理大量原始同相与正交（IQ）采样数据。同时，为在多变信号条件下实现鲁棒的干扰分类与表征，日益复杂的深度神经网络（DNN）成为需求。这导致预测性能与资源受限硬件可部署性之间的根本矛盾。本文研究基于迭代结构化剪枝、训练后静态量化及硬件感知零样本神经架构搜索（NAS）的高效网络推理方法。以MCUNet为紧凑基线，分析模型压缩与自动化架构优化对模型大小、计算复杂度和内存使用的影响，同时保持任务性能。在涵盖分类与广义表征的GNSS干扰数据集上实验表明，压缩与硬件感知设计结合显著提升嵌入式部署效果。结果为在iMXRT1062 MCU、Raspberry Pi Zero 2W及Raspberry Pi 5等平台上开发实时GNSS干扰监测的轻量级机器学习模型提供了实用指导。
原文摘要 · Abstract (English)
Embedded global navigation satellite system (GNSS) interference monitoring requires fast and memory-efficient inference to process large volumes of raw in-phase and quadrature (IQ) samples in real time. At the same time, increasingly expressive deep neural networks (DNNs) are needed for robust interference classification and characterization across diverse signal conditions. This creates a fundamental tension between predictive performance and deployability on resource-constrained hardware. In this paper, we investigate efficient network inference for GNSS interference characterization using iterative structured pruning, post-training static quantization, and hardware-aware zero-shot neural architecture search (NAS). Starting from MCUNet as a compact baseline, we analyze how model compression and automated architecture optimization affect model size, computational complexity, and memory usage while maintaining task performance. Experiments on a GNSS interference dataset, covering both classification and generalized characterization, show the benefits of combining compression and hardware-aware design for embedded deployment. Our results provide practical guidance for developing compact machine learning (ML) models for real-time GNSS interference monitoring on embedded platforms (iMXRT1062 MCU, Raspberry Pi Zero 2W, and Raspberry Pi 5).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。