SpectraBayes: Exploring Traffic Series Reconstruction in Frequency Domain for Anomaly Detection

Timely detection of anomalies in traffic systems is crucial for mitigating risks and economic losses. Current time series anomaly detection methods often use reconstruction errors to identify anomalies, and their accuracy depends on how well they can reconstruct normal patterns from the original series. However, traffic data typically exhibit high noise, spatiotemporal heterogeneity, and uncertain inter-series correlations, complicating the learning of normal patterns. To address these challenges, we introduce SpectraBayes, which explores the reconstruction of density and volume series in the frequency domain for anomaly detection. First, we transform the series into the frequency domain and apply a low-pass filter to remove noise. Then, we embed periodic information into the frequency-domain representation through phase shifts to enhance the temporal awareness. Additionally, we model the inter-series correlations between density and volume resiliently using cross-spectrum probabilistic modeling. Optimized by maximizing the Evidence Lower Bound (ELBO), SpectraBayes ensures robust reconstruction while avoiding overfitting against the uncertain data. SpectraBayes outperforms 21 existing anomaly detection models on traffic series anomaly detection tasks, achieving mean improvements of 2.71% across three metrics over the second-best model. Furthermore, it is lightweight and maintains robust performance under varying noise levels.