MtDetector

Abstract

In this paper, we present MtDetector, a high performance marine tra c detector that can predict the destination and the arrival time of travelling vessels. MtDetector accepts streaming data reported by the moving vessels and generates continuous predictions of the arrival port and arrival time for those vessels. To predict the destination for a ship, MtDetector builds a neural network for every port and infers the arrival port for vessels based on their departure port. For the arrival time prediction, we derive informative features from training data and apply Deep Neural Network (DNN) to estimate the traveling time. MtDetector is built on top of DtCraft [1, 2], a high-performance distributed execution engine for stream programming. By utilizing the task-based parallelism in DtCraft, Mt-Detector can process multiple predictions concurrently to achieve high throughput and low latency. CCS CONCEPTS• Theory of computation → Distributed computing models; • Computing methodologies → Neural networks; • Software and its engineering → Cloud computing;

A Deep Learning Streaming Methodology for Trajectory Classification

“…Although many methodologies have been developed for trajectory classification, fewer studies have focused on real-time stream processing of events in the maritime domain [10,31,32]. Lin et al [31] extracted features from AIS messages, which were then fed to a deep neural network for the prediction of the Estimated Time of Arrival (ETA) of vessels.…”

“…Although many methodologies have been developed for trajectory classification, fewer studies have focused on real-time stream processing of events in the maritime domain [10,31,32]. Lin et al [31] extracted features from AIS messages, which were then fed to a deep neural network for the prediction of the Estimated Time of Arrival (ETA) of vessels. Chatzikokolakis et al [32] developed a real-time anomaly detection service, which was focused on identifying a wide range of events of interest in the maritime domain either through the use of machine learning techniques or with rule-based approaches.…”

Prediction of the Estimated Time of Arrival of container ships on short-sea shipping: A pragmatical analysis

“…En [16] se presenta un servicio cognitivo, cuyo elemento prin-cipal es un modelo basado en el algoritmo -Nearest Neighbor (KNN), capaz de predecir la ETA de los buques en el puerto de Valencia (España). En [17] y [18] se desarrollaron dos soluciones al DEBS Grand Challenge 2018 [19] para predecir el destino y la hora de llegada de los buques a puerto. En ambos estudios se emplearon redes neuronales profundas.…”