Multimodal-to-Text Prompt Engineering in Large Language Models Using Feature Embeddings for GNSS Interference Characterization

TL;DR

This paper introduces a novel approach using large language models and feature embeddings for GNSS interference characterization, enhancing classification accuracy and interpretability in signal processing tasks.

Contribution

It presents a new multimodal prompt engineering method leveraging feature embeddings and LLaVA for GNSS interference analysis, a novel application of LLMs in this domain.

Findings

Outperforms existing machine learning models in interference classification

Enables visual and logical reasoning in GNSS signal analysis

Demonstrates effective use of feature embeddings and prompt engineering

Abstract

Large language models (LLMs) are advanced AI systems applied across various domains, including NLP, information retrieval, and recommendation systems. Despite their adaptability and efficiency, LLMs have not been extensively explored for signal processing tasks, particularly in the domain of global navigation satellite system (GNSS) interference monitoring. GNSS interference monitoring is essential to ensure the reliability of vehicle localization on roads, a critical requirement for numerous applications. However, GNSS-based positioning is vulnerable to interference from jamming devices, which can compromise its accuracy. The primary objective is to identify, classify, and mitigate these interferences. Interpreting GNSS snapshots and the associated interferences presents significant challenges due to the inherent complexity, including multipath effects, diverse interference types, varying sensor characteristics, and satellite constellations. In this paper, we extract features from a large GNSS dataset and employ LLaVA to retrieve relevant information from an extensive knowledge base. We employ prompt engineering to interpret the interferences and environmental factors, and utilize t-SNE to analyze the feature embeddings. Our findings demonstrate that the proposed method is capable of visual and logical reasoning within the GNSS context. Furthermore, our pipeline outperforms state-of-the-art machine learning models in interference classification tasks.