Grand Challenge: Real-time Destination and ETA Prediction for Maritime Traffic

被引：28

作者：

Bodunov, Oleh ^{[1
]}

Schmidt, Florian ^{[1
]}

Martin, Andre ^{[1
]}

Brito, Andrey ^{[2
]}

Fetzer, Christof ^{[1
]}

机构：

[1] Tech Univ Dresden, Dresden, Germany

[2] Univ Fed Campina Grande, Campina Grande, Brazil

来源：

DEBS'18: PROCEEDINGS OF THE 12TH ACM INTERNATIONAL CONFERENCE ON DISTRIBUTED AND EVENT-BASED SYSTEMS | 2018年

基金：

欧盟地平线“2020”;

关键词：

Event Stream Processing; ESP; Machine Learning; ETA Prediction; Destination Prediction; Geo-spatial Analysis;

D O I：

10.1145/3210284.3220502

中图分类号：

TP31 [计算机软件];

学科分类号：

081202 ; 0835 ;

摘要：

In this paper, we present our approach for solving the DEBS Grand Challenge 2018. The challenge asks to provide a prediction for (i) a destination and the (ii) arrival time of ships in a streaming-fashion using Geo-spatial data in the maritime context. Novel aspects of our approach include the use of ensemble learning based on Random Forest, Gradient Boosting Decision Trees (GBDT), XGBoost Trees and Extremely Randomized Trees (ERT) in order to provide a prediction for a destination while for the arrival time, we propose the use of Feed-forward Neural Networks. In our evaluation, we were able to achieve an accuracy of 97% for the port destination classification problem and 90% (in minutes) for the ETA prediction.

引用

页码：198 / 201

页数：4

共 9 条

[1]

[Anonymous], 2015, Deep Residual Learning for Image Recognition

[2]

[Anonymous], 2015, P 2015TH INT C ECML

[3] A bayesian dynamic linear model approach for real-time short-term freeway travel time prediction [J].