Real-Time Outlier Detection Applied to a Doppler Velocity Log Sensor Based on Hybrid Autoencoder and Recurrent Neural Network

This article presents a real-time outlier detection deep-learning (OD-DL)-based method using a hybridized artificial neural network (ANN) approach. We propose an unsupervised ANN scheme that runs in parallel, a denoising autoencoder (DAE) and a recurrent neural network (RNN). The DAE aims to reconst...

Ausführliche Beschreibung