Data-Driven Analysis for Safe Ship Operation in Ports Using Quantile Regression Based on Generalized Additive Models and Deep Neural Network

Marine accidents in ports can cause loss of human life and property and have negative material and environmental impacts. In South Korea, due to a pier collision accident of a large container ship in Busan New Port of South Korea, the need for safe ship operation guidelines in ports emerged. Therefore, to support quantitative safe ship operation guidelines, ship trajectory data based on automatic information system information have been used. However, because this trajectory information is variable and uncertain due to various situations arising during a ship’s navigation, there is a limit to deriving results through traditional regression analysis. Considering the characteristics of these data, we analyzed ship trajectories through quantile regression using two models based on generalized additive models and neural networks corresponding to deep learning. Among the automatic information system information, the speed over ground, course over ground, and ship’s position were analyzed, and the model was evaluated based on quantile loss. Based on this study, it is possible to suggest safe operation guidelines for the position, speed, and course of the ship. In addition, the results of this work can be further developed as a manual for the in-port-autonomous operation of ships in the future.

75 anniversary of the university Library of the Agricultural University – Plovdiv

The article presents the history and the development of the University Library of the Agricultural University – Plovdiv for a period of 75 years from its establishment until the present day. It is one of the oldest specialized agricultural libraries in Bulgaria. The University Library was opened in 1945, together with the opening of the University of Plovdiv. The Library of the Agricultural University – Plovdiv is the first university library in Bulgaria that has begun introducing ICT in its activities. Since 1978 the Library has used an Automatic information system for Bibliographical references. In 1986 the automation of the library processes began. In 2020 the Agricultural University – Plovdiv celebrated its 75th anniversary and its Library gradually established itself as one of the richest specialized agricultural libraries in Bulgaria.

Using big data to estimate whale watching effort

ABSTRACTThe growing concerns about the negative effects caused by whale watching on wild The growing concerns about the negative effects caused by whale watching on wild cetacean populations are evincing the need to measure whale watching effort more precisely. The current alternatives do not provide sufficient information or imply time-consuming and staff intensive tasks that limit their effectiveness to establish the maximum carrying capacity for this touristic activity. A methodology based on big data analysis, using Automatic Information System (AIS) messages, can provide valuable vessel activity information, which is necessary to estimate whale watching effort on cetacean populations. We used AIS data to automatically detect whale watching operations and quantify whale watching effort with high spatial and temporal resolution in the Canary Islands. The results obtained in this study are very encouraging, proving that the methodology is able to estimate seasonal and annual trends in the whale watching effort. The methodology has also proved to be effective in providing detailed spatial information about the whale watching effort, which makes an interesting tool to manage spatial regulations and enforce exclusion zones. The widespread use of AIS devices in maritime navigation provides an enormous potential to easily extend this methodology to other regions worldwide. Any public strategy aimed at the sustainable use of the marine resources should enhance the use of this kind of information technologies, collecting and archiving detailed information on the activity of all the vessels, especially in marine protected areas.

Analysis of Ship RCS Detected by Multifrequency HFGWR

One of the important applications of high frequency-ground wave radar (HFGWR) is to detect offshore ships. A proper method should be used to obtain the ship radar cross section (RCS), which is a key parameter of the ship. This paper proposes a method based on an automatic information system (AIS). The relationship of the ship RCS versus bearing for different frequencies is analyzed by processing multifrequency HFGWR data. With this new method, bearing information is taken into consideration, which is not the case in traditional empirical formulas. The results provide prior knowledge for ship detection and tracking; therefore, the probability of detection is significantly improved.