Treffer: MMM-DADCL-Net: An Integrated Multi-Model Deep Attention Network based on Machine Learning and Recommendation System.

The Gulf of Guinea has been in the center of attention since 2010, when the International Maritime Organization labeled it one of the most dangerous areas due to the persistence of piracy and armed robbery against ships. This study presented a novel way to identifying attacks in the GoG. Initially, the dataset is pre-processed using standard methodologies, and features are retrieved using statistical methods. The retrieved characteristics are used to choose features using a self-adaptive bacterial foraging optimization algorithm. Finally, classification is performed using a novel MMM-DADCL Net approach that classifies ship type, ship state, protection level, and attacks in four phases using the self-attention mechanism and CNN models such as Alex-Net, Google-Net, LeNet, VGG-19, LSTM, and Densely connected FCN. The proposed model achieved an Accuracy of 97.09% when implemented on a Python platform. The results demonstrate the proposed model's superior efficiency on comparisons with the current techniques. [ABSTRACT FROM AUTHOR]

Copyright of Metallurgical & Materials Engineering is the property of Netherlands Press and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)