Narendra Kumar Mishra

Ships are an integral part of maritime traffic where they play both militaries as well as non-combatant roles. This vast maritime traffic needs to be managed and monitored by identifying and recognising vessels to ensure the maritime safety and security. As an approach to find an automated and efficient solution, a deep learning model exploiting convolutional neural network (CNN) as a basic building block, has been proposed in this paper. CNN has been predominantly used in image recognition due to its automatic high-level features extraction capabilities and exceptional performance. We have used transfer learning approach using pre-trained CNNs based on VGG16 architecture to develop an algorithm that performs the different ship types classification. This paper adopts data augmentation and fine-tuning to further improve and optimize the baseline VGG16 model. The proposed model attains an average classification accuracy of 97.08% compared to the average classification accuracy of 88.54% obtained from the baseline model.

With the emergence of artificial intelligence in the field of computer science the utilization of electronic machines are displaced from calculation to executing intellect. The advancement in technology triggered the experts to adhere the psychology and biology with electronics. With the practice of artificial intelligence the machine attempt to classify data into already categorized classes which are analyzed according to the experience acquisitioned in the training session.In this paper a hybrid model i.e. `GA-LDA-NPR' is used for optimization and classification of datasets. The datasets used for experiment are cancer, iris and wine. The optimization take place using GA-LDA and the optimized data set proceed to NPR tool for further training and classification.After observing the classification results a final conclusion is made that during optimization as the number of selected features increases the classification accuracy will increase up to a limit and if we continuously increases the number of selected features the classification rate starts to degrade. The outcome of this analysis is that if the number of parameters increases continuously the problem of over fitting arises which reduces the performance of classifier.