Abstract
The peculiarity of the current moment for modern shipping is that information technologies are intensively used in the fleet and port infrastructure. However, despite the introduction of new technical means of navigation, the problem of taking into account the influence of the human factor remains unsolved. The most promising direction of application of information technologies to solve the above-mentioned problem is the concept of e-Navigation, which is currently a key initiative of the IMO. The concept involves the use of "end-to-end" digital technologies of artificial intelligence and augmented reality in the part of intellectualization of the shipmaster's interface. These technologies are the key to a fundamentally new level of human-operator (master) interaction with navigation data in the digital environment, including for identifying the situation and recognizing situations. According to the results of the conducted research, the conclusion was obtained that the accuracy of the forecast of the ship's motion parameters by a neurocomputer is higher than when using a distributed computing system for this purpose. Thus, in the considered model situations, the neural network showed higher computational reliability compared to the parallel algorithm for solving the differential equation. It should also be noted that the conclusions based on the results of the study of the reliability of the neural network calculation system should be understood in a statistical and not an absolute sense
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call