Wyniki wyszukiwania - Biblioteka Nauki

Nowa wersja platformy, zawierająca wyłącznie zasoby pełnotekstowe, jest już dostępna.
Przejdź na https://bibliotekanauki.pl

Ograniczanie wyników

2 TransNav : International Journal on Marine Navigation and Safety of Sea Transportation

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Developing generative adversarial nets to extend training sets and optimize diiscrete actions

100%

Zhang R. L. , Furusho M.

tom Vol. 13. no. 4

875--880

This study proposes the use of generative adversarial networks (GANs) to solve two crucial problems in the unmanned ship navigation: insufficient training data for neural networks and convergence of optimal actions under discrete conditions. To achieve smart collision avoidance of unmanned ships in various sea environments, first, this study proposes a collision avoidance decision model based on a deep reinforcement learning method. Then, it utilizes GANs to generate enough realistic image training sets to train the decision model. According to generative network learning, the conditional probability distribution of ship maneuvers is learnt (action units). Subsequently, the decision system can select a reasonable action to avoid the obstacles due to the discrete responses of the generated model to different actions and achieve the effect of intelligent collision avoidance. The experimental results showed that the generated target ship image set can be used as the training set of decision neural networks. Further, a theoretical reference to optimize the optimal convergence of discrete actions is provided.

The Development of Marine Accidents Human Reliability Assessment Approach: HEART Methodology and MOP model

80%

Bowo L. P. , Mutmainnah W. , Furusho M.

TransNav : International Journal on Marine Navigation and Safety of Sea Transportation

2017

tom Vol. 11, no. 2

249--254

Humans are one of the important factors in the assessment of accidents, particularly marine accidents. Hence, studies are conducted to assess the contribution of human factors in accidents. There are two generations of Human Reliability Assessment (HRA) that have been developed. Those methodologies are classified by the differences of viewpoints of problem-solving, as the first generation and second generation. The accident analysis can be determined using three techniques of analysis; sequential techniques, epidemiological techniques and systemic techniques, where the marine accidents are included in the epidemiological technique. This study compares the Human Error Assessment and Reduction Technique (HEART) methodology and the 4M Overturned Pyramid (MOP) model, which are applied to assess marine accidents. Furthermore, the MOP model can effectively describe the relationships of other factors which affect the accidents; whereas, the HEART methodology is only focused on human factors.