Scholarlink

This research paper explores the intersection of Global Navigation Satellite Systems (GNSS), neural networks, and Explainable Artificial Intelligence (XAI) models. Through rigorous experimentation, various neural network architectures—such as CNNs, RNNs, and DNNs—are trained on GNSS data, followed by the application of XAI models like LIME, SHAP, and DALEX for interpretation. Our analysis reveals insights into the efficacy of different XAI models across diverse GNSS applications, shedding light on interpretability nuances influenced by neural network complexity and GNSS data characteristics. Furthermore, we identify limitations and challenges within existing XAI techniques for GNSS parameter interpretation, advocating for ongoing advancements to meet evolving application needs.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Prediction and Analysis of GNSS Broadcast Parameter Using Explainable AI

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Ishaan Mehta,
  • Santosh Bharti

摘要

This research paper explores the intersection of Global Navigation Satellite Systems (GNSS), neural networks, and Explainable Artificial Intelligence (XAI) models. Through rigorous experimentation, various neural network architectures—such as CNNs, RNNs, and DNNs—are trained on GNSS data, followed by the application of XAI models like LIME, SHAP, and DALEX for interpretation. Our analysis reveals insights into the efficacy of different XAI models across diverse GNSS applications, shedding light on interpretability nuances influenced by neural network complexity and GNSS data characteristics. Furthermore, we identify limitations and challenges within existing XAI techniques for GNSS parameter interpretation, advocating for ongoing advancements to meet evolving application needs.