Autoencoder-Based FM Spectrum Anomaly Detection: A Pipeline-Level Study of Preprocessing, Model Capacity, and...

Automated anomaly detection is increasingly important in radio spectrum monitoring, where large volumes of continuously generated measurements must be analyzed while anomalous events remain relatively rare. This study investigates reconstruction-based anomaly detection for real-world very-high-frequency (VHF) Band II radio-broadcasting spectrum measurements using autoencoders whose gradient-based parameter optimization was performed exclusively on normal observations. Measurements covering 87.5-108 MHz in VHF Band II were represented as time-frequency images and processed through a unified pipeline comprising preprocessing, representation learning, reconstruction, residual-based scoring, and anomaly decision. The effects of input normalization, image resolution, network depth, latent-space dimensionality, encoder-decoder symmetry, spectrum representation, and reconstruction scoring were systematically evaluated across symmetric, asymmetric, stacked, augmented stacked, and pixel-sorted autoencoder configurations, while exploratory CVAE (convolutional variational autoencoder) experiments were additionally used to examine probabilistic latent regularization. Increasing architectural complexity did not necessarily improve detection performance. The best configuration identified during model development achieved an F1-score of 91.4% on the labeled development subset at its F1-optimized operating point. To obtain an independent assessment of generalization, the finalized pipelines were subsequently evaluated on a separate held-out test subset that was excluded from model, checkpoint, scoring-hyperparameter, and threshold selection. The held-out evaluation showed lower absolute performance and a change in configuration ranking, demonstrating that development-set differences should not be interpreted as definitive evidence of architectural superiority. A controlled reconstruction-scoring ablation further showed that anomaly separability depends materially on the formulation of the observation-level reconstruction score.