Efficient Network Inference via Hardware-Aware Architecture Search, Model Pruning & Quantization
2026-06-22 • Machine Learning
Machine LearningDistributed, Parallel, and Cluster Computing
AI summaryⓘ
The authors study how to make deep learning models small and fast enough to run on limited hardware for detecting interference in GPS signals. They use methods like pruning and quantization to shrink models, and also search for the best network designs that fit hardware constraints without losing accuracy. Testing on real GPS interference data shows their combined approach keeps performance while using less memory and computing power. Their work helps create efficient AI tools that can work in real time on devices like microcontrollers and small computers.
GNSSinterference monitoringdeep neural networksmodel pruningquantizationneural architecture searchMCUNetembedded systemsreal-time inferencemodel compression
Authors
Lucas Heublein, Mark Deutel, Axel Plinge, Felix Ott
Abstract
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).