No abstract

Abstract:This paper presents a data-driven model for time series prediction of ship motion. Prediction based on past time series of data is a powerful function in modern ship support systems. For a large amount of ship sensor data, neural network (NN) is considered as a proper tool in modeling the prediction system. Efforts are made to compact the NN structure through sensitive analysis, in which the importance of each input to the output is quantized and lower ranked inputs are eliminated. Further analysis about the impact of three different learning strategies, i.e., offline, online and hybrid learning on the NN is conducted. The hybrid learning combining the advantages of both the offline learning and the online learning exhibits superior prediction performance. According to the long term prediction ability of recurrent NN, multi-stepahead prediction under the hybrid learning strategy is realized in a multi-stage prediction form. Experiments are carried out using collected ship sensor data on a vessel. The results show the feasibility of generating a data-driven model through modeling and analysis of the NN for ship motion prediction.Additional Information: Question ResponseIs your article an invited contribution for a special issue? If yes, please select the title of the special issue from the list below.Please select an option ONLY if you have received an invitation to submit. ABSTRACT This paper presents a data-driven model for time series prediction of ship motion. Prediction based on past time series of data is a powerful function in modern ship support systems. For a large amount of ship sensor data, neural network (NN) is considered as a proper tool in modeling the prediction system. Efforts are made to compact the NN structure through sensitive analysis, in which the importance of each input to the output is quantized and lower ranked inputs are eliminated. Further analysis about the impact of three different learning strategies, i.e., offline, online and hybrid learning on the NN is conducted. The hybrid learning combining the advantages of both the offline learning and the online learning exhibits superior prediction performance. According to the long term prediction ability of recurrent NN, multi-step-ahead prediction under the hybrid learning strategy is realized in a multi-stage prediction form. Experiments are carried out using collected ship sensor data on a vessel. The results show the feasibility of generating a data-driven model through modeling and analysis of the NN for ship motion prediction. Powered by Editorial Manager® and ProduXion Manager® from Aries Systems Corporation

This paper presents a flexible system structure to analyze and model for the potential use of huge ship sensor data to generate efficient ship motion prediction model. The noisy raw data is cleaned using noise reduction, resampling and data continuity techniques. For modeling, a flexible Support Vector Regression (SVR) is proposed to solve regression problem. In the data set, sensitivity analysis is performed to find the strength of input attributes for prediction target. The highly significant attributes are considered for input feature which are mapped into higher dimensional feature using non-linear function, thus SVR model for ship motion prediction is achieved. The prediction results for trajectory and pitch show that the proposed system structure is efficient for the prediction of different ship motion attributes.

This paper presents the potential use of the 3D virtual world of fish population for training and educational purposes, especially for who are new to fish farming industry. Virtual Reality is the proven technology which is emerging everyday with new methods and implementation. We simulate the fish swimming behavior based on the social rules that are derived from flocking behavior of birds. The simple relation we proposed to represent fish birth and death resembles the biological ecosystem of fish in the sea. The experiment results from different case studies we carried out shows the realistic fish population dynamics. The system user interface gives the users the ability to change the system parameters for different cases to see the real-time effect. Through different case studies carried, our framework can be used to simulate different environments.