Online Resource 2 – Simulated GNSS Time-Series Experiment Dataset for "Hybrid Fourier–LSTM Framework for Adaptive GNSS Anomaly Detection via Multi-Scale and Type-Specific Fusion"

This repository corresponds to Online Resource 2 of the manuscript: Hybrid Fourier–LSTM Framework for Adaptive GNSS Anomaly Detection via Multi-Scale and Type-Specific Fusion It contains the reproducibility package for the simulated GNSS time-series experiments, including Python scripts and configuration files used to generate and evaluate synthetic datasets. Contents: hybrid_gnss_synth.py — main script for anomaly-detection experiments on synthetic GNSS-like time series. outputs/ — subfolders containing experiment results (results.json, benchmark_table.csv, series.npy, labels.npz, etc.). config_summary.json — parameters defining the synthetic data generation setup. README.md — environment setup and execution guide. Environment:Python ≥ 3.9 with dependencies: numpy==1.26.4, torch==2.3.1. Execution:Run all synthetic experiments with: python hybrid_gnss_synth.py Outputs include:results.json, benchmark_table.csv, scores_overall.npz, and summary_mean_std.csv, corresponding to the results discussed in the manuscript.