Towards Data-Driven GRU based ETA Prediction Approach for Vessels on both Inland Natural and Artificial Waterways

Noman, Abdullah Al; Heuermann, Aaron; Wiesner, Stefan; Thoben, Klaus‐Dieter

doi:10.1109/itsc48978.2021.9564883

Cited by 6 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Collectively, these studies hold significance and provide valuable references for the application of data mining in predicting ship arrival times at specific ports. Noman et al [46] investigated the use of Gradient Boosting Decision Trees (GBDT), Multi-Layer Perceptron Neural Networks (MLP), and Gated Recurrent Unit Neural Networks (GRU) for predicting vessel ETA in inland waterways. It used historical AIS data for training and compared the accuracy of these methods.…”

Section: Waterway Applicationmentioning

confidence: 99%

Automatic Identification System-Based Prediction of Tanker and Cargo Estimated Time of Arrival in Narrow Waterways

Arbabkhah,

Sedaghat,

Jafari Kang

et al. 2024

JMSE

View full text Add to dashboard Cite

In maritime logistics, accurately predicting the Estimated Time of Arrival (ETA) of vessels is pivotal for optimizing port operations and the global supply chain. This study proposes a machine learning method for predicting ETA, drawing on historical Automatic Identification System (AIS) data spanning 2018 to 2020. The proposed framework includes a preprocessing module for extracting, transforming, and applying feature engineering to raw AIS data, alongside a modeling module that employs an XGBoost model to accurately estimate vessel travel times. The framework’s efficacy was validated using AIS data from the Port of Houston, and the results indicate that the model can estimate travel times with a Mean Absolute Percentage Error (MAPE) of just 5%. Moreover, the model retains consistent accuracy in a simplified form, pointing towards the potential for reduced complexity and increased generalizability in maritime ETA predictions.

show abstract

Section: Waterway Applicationmentioning

confidence: 99%

Automatic Identification System-Based Prediction of Tanker and Cargo Estimated Time of Arrival in Narrow Waterways

Arbabkhah,

Sedaghat,

Jafari Kang

et al. 2024

JMSE

View full text Add to dashboard Cite

show abstract

“…Wide and deep model does not fit with sequential data study, some researchers provides different types of recurrent neural network as the solution. For example LSTM [1] , which is the widely used RNN model for nature language sequential to sequential translation with forget, input and output gates, the model is described in Figure 8; GRU [10] (Gated Recurrent Unit) is the optimized version of LSTM combined forget and input gate to an update gate (refer to Figure 9 for gate micro structure), this variation is preferred for study of smaller dataset compared with LSTM, and proved to have better performance. RNN has its nature weakness on supporting the parallelism computing capability which modern GPU and accelerator hardware provide, since input of state in RNN hn relies on output of previous states (h1, h2…hn-1).…”

Section: Figure 6 Google Wide and Deep Learning For Recommendation Sy...mentioning

confidence: 99%

WDA: Estimation of Travel Time for Taxi Using Wide and Deep Learning Together with Target Attention

Wang

2023

ACE

View full text Add to dashboard Cite

There is an increasing interest in ways to use data and machine learning methods to optimize the operation of transportation system. In this paper, the author focuses on estimation of time arrival (ETA) for taxi. As taxi is one of the popular transportation vehicles in the urban area, predicting the time of arrival for taxi would help the customer to better estimate time required for the trip, especially in case of urgencies. The author develops a comprehensive neural network with both wide and deep components, and attention component for this predictive job. The author also evaluates the network with huge historic data and compare it with industry existing solutions. This network model is proven to have a better prediction accuracy under extreme traffic and weather condition with reasonable shorter training time.

show abstract

Towards Vessel Arrival Time Prediction Through a Deep Neural Network Cluster

Schindler,

Ohlendorf,

Thoben

2024

Lecture Notes in Logistics

View full text Add to dashboard Cite

Towards Data-Driven GRU based ETA Prediction Approach for Vessels on both Inland Natural and Artificial Waterways

Cited by 6 publications

References 19 publications

Automatic Identification System-Based Prediction of Tanker and Cargo Estimated Time of Arrival in Narrow Waterways

Automatic Identification System-Based Prediction of Tanker and Cargo Estimated Time of Arrival in Narrow Waterways

WDA: Estimation of Travel Time for Taxi Using Wide and Deep Learning Together with Target Attention

Towards Vessel Arrival Time Prediction Through a Deep Neural Network Cluster

Contact Info

Product

Resources

About