Detecting abnormal cardiac rhythms in ECG signals using unsupervised deep learning — trained exclusively on normal heartbeats, evaluated on a held-out set of normal and abnormal sequences. This ...

This implements an supervised anomaly detection system for detecting network and vehicular intrusions using an LSTM-based autoencoder. The model is trained only on normal traffic and flags anomalies ...

Abstract: This paper proposes a hybrid Transformer-LSTM autoencoder for student final grade prediction, addressing the limitations of existing models that capture either short-term or long-term ...

Abstract: Trajectory prediction is a significant function in many areas, such as autonomous driving, robotic navigation, surveillance, and human-robot interaction. The precise prediction of the future ...