← Back to all news
arXiv AI By Ammar Bouketta, Smail Niar, Hamza Ouarnoughi, Eva Mutuzo Brindle

Cycle-Aware Autoencoder with Cross-SignalConsistency for Railway Door Anomaly Detection

Read the original on arXiv AI →

The paper introduces the Temporal Cycle-Aware Attention Autoencoder with Cross-Signal Consistency (TCAA‑CS) for detecting anomalies in railway passenger door operations. It treats each full opening‑dwell‑closing cycle as a monitoring unit and trains on nominal cycles using a dual‑stream encoder for physical measurements and logical states, an LSTM with temporal attention, and a hybrid anomaly score that fuses reconstruction error, latent‑space deviation, and phase‑aware cross‑signal consistency. On real industrial data, TCAA‑CS achieves 93.8% recall, 97.3% precision, and a 0.5% false‑alarm rate, outperforming other unsupervised baselines and demonstrating real‑time feasibility on an NVIDIA Jetson AGX Xavier.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
2d ago

Deep Learning for Anomaly Detection in Railway Systems: A Structured Survey

This survey reviews deep learning methods for detecting anomalies in railway systems, organizing them by taxonomy of anomaly location, data representation, sensing modality, and temporal traits. It categorizes approaches—convolutional, recurrent, attention-based, autoencoders, GANs, transformers—into classification, prediction, reconstruction, and hybrid paradigms, and discusses data challenges, evaluation, metrics, and deployment issues such as edge‑cloud architectures and hardware constraints. The paper also offers a decision‑oriented framework linking anomaly characteristics, data properties, and operational constraints to guide the selection and deployment of suitable detection solutions.

By Ammar Bouketta, Smail Niar, Hamza Ouarnoughi
llmssafety
More like this →
arXiv Computer Vision
Sep 7

Training-Free Logical and Structural Anomaly Detection via Calibrated Fusion

The paper introduces a training‑free anomaly detector that simultaneously handles structural and logical defects by calibrating heterogeneous anomaly cues with statistics from normal images. This calibration aligns frozen representations, allowing their fusion without extra training or part‑level supervision. The resulting method achieves state‑of‑the‑art AUROC scores on MVTec‑LOCO and remains competitive on MVTec‑AD.

By Changyi Li, Miao Yu, Kai Dong, Yu Xiao
More like this →