Computational Logistics for Container Terminal Handling Systems with Deep Learning

Li, Bin; He, Yuqing

doi:10.1155/2021/5529914

Cited by 9 publications

(1 citation statement)

References 35 publications

(44 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In view of this, state-of-the-art technology such as DL has the potentials to improve all the major segments in CSSC, i.e., vessel/freight/container logistics. For the application of DL in container logistics, Li and He [24] has combined the DL with computational logistics to a so-called container terminal-oriented neural-physical fusion computation (CTO-NPFC), which is used to analyze the performance of the container terminal handling system (CTHS) at ports. In addition, Zhang et al [25] introduced a highly accurate approach to localize and recognize the codes.…”

Section: Introductionmentioning

confidence: 99%

Digital transformation for shipping container terminals using automated container code recognition

2023

View full text Add to dashboard Cite

Due to the sweeping waves of global industry development, the number of containers passing through terminal ports increases every day. Therefore, it is essential to automate the identification process for the container codes to replace the manual identification for more efficient logistics and safer workplace. This paper aims to design and evaluate the performance of such a system. Specifically, automated container codes recognition (ACCR) has been implemented. This is a novel container tracking model based on image processing algorithms and machine learning (ML) algorithms to be applied in ports. There are three steps in this system: character detection, character isolation, and character recognition. The first step is to identify an area with 10 digits and 26 capitals. After detecting the text area, the second step is to separate the characters. Each character is recognized in the last step by the classification method. In particular, features are extracted with the histogram of oriented gradients (HOG) algorithm and support vector machines (SVMs) for training and prediction. The trained ML model is then used to classify characters and digits according to what it has learned. In general, the digital technologies in logistics and container management in ports will benefit from the proposed algorithms.

show abstract

Section: Introductionmentioning

confidence: 99%

Digital transformation for shipping container terminals using automated container code recognition

2023

View full text Add to dashboard Cite

show abstract

Coordinated scheduling problems for sustainable production of container terminals: a literature review

Yu,

Zhang,

Yao

et al. 2023

Ann Oper Res

View full text Add to dashboard Cite

Robust berth scheduling using machine learning for vessel arrival time prediction

et al. 2022

View full text Add to dashboard Cite

In this work, the potentials of data-driven optimization for the well-known berth allocation problem are studied. The aim of robust berth scheduling is to derive conflict-free vessel assignments at the quay of a terminal, taking into account uncertainty regarding the actual vessel arrival times which may result from external influences as, e.g., cross wind and sea current. In order to achieve robustness, four different Machine Learning methods-from linear regression to an artificial neural network-are employed for vessel arrival time prediction in this work. The different Machine Learning methods are analysed and evaluated with respect to their forecast quality. The calculation and use of so-called dynamic time buffers (DTBs), which are derived from the different AIS-based forecasts and whose length depends on the estimated forecast reliability, in the berth scheduling model enhance the robustness of the resulting schedules considerably, as is shown in an extensive numerical study. Furthermore, the results show that also rather simple Machine Learning approaches are able to reach high forecast accuracy. The optimization model does not only lead to more robust solutions, but also to less actual waiting times for the vessels and hence to an enhanced service quality, as can be shown by studying the resulting schedules for real vessel data. Moreover, it turns out that the accuracy of the resulting berthing schedules, measured as the deviation of planned and actually realisable schedules, exceeds the accuracy of all forecasts which underlines the usefulness of the DTB approach.

show abstract

Computational Logistics for Container Terminal Handling Systems with Deep Learning

Cited by 9 publications

References 35 publications

Digital transformation for shipping container terminals using automated container code recognition

Digital transformation for shipping container terminals using automated container code recognition

Coordinated scheduling problems for sustainable production of container terminals: a literature review

Robust berth scheduling using machine learning for vessel arrival time prediction

Contact Info

Product

Resources

About