Ensemble Model Based Ship Motion Response Data Analysis and Monitoring Prediction System

The Automatic Identification System (AIS) is data suggested the ship monitoring, helps of maritime regulation and practitioners make reasonable are paid to acquire an accurate ship trajectory. However, there are consider various parameter requires to large information to analysis multiple of representations of input data which lead to increased energy, adding complexity to the model training process. In this paper, proposed ensemble model such as linear Support Vector Machine (LSVM), K-Nearest Neighbour (KNN), Random Forest (RF) is efficiently analysis the ship motion, better filtering out this noise, providing more stable and reliable prediction. The ship motion is highly non-linear due to wind wave and other environment faction by using ensemble models better capture this non-linear dynamic compared to single models. Initially data occur AIF dataset and data normalization using ensures that feature dominates others due to magnitude and transforming data. The proposed ensemble model technique for ship motion detection is achieving better outcomes such as Mean Absolute Error (MAE) of 2.03, Mean Absolute Scaled Error (MASE) of 3.45, R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> score of 2.45 on raw dataset. The existing technique such Multi-Head Attention Mechanism and Bidirectional Gate Recurrent unit (MHA-BiGRU) and Bidirectional Long Short-Term Memory (Bi-LSTM) are evaluated of proposed method.