Search

In this study, an intelligent predictor is designed for predicting the direction of dinghy booms and coaching dinghy sailing using the designed predictor with information obtained from multiple sensors attached to the dinghy and the sailor. For this purpose, we designed a Takagi-Sugeno-Kang-based linguistic model with interval prediction based on fuzzy granulation, which can be realized by using a context-based fuzzy c-means clustering. The sensors used in this study are cameras, GPS, and an anemometer. The GPS and cameras were attached to the dinghy, and the anemometer was installed on a separate boat near the dinghy. Features are extracted from obtained data to interpret them discretely without sequential data. The boom direction was predicted by collecting information from the dinghy driven by an expert wearing a marked suit to predict the optimal direction. The constructed database was randomly divided into a training set (60%) and a validation set (40%) for a 10-fold cross-validation. The experimental results revealed that in the prediction of the dinghy boom direction, the proposed predictor showed performance improvements of 25.2% and 17.9% on the training and validation sets, respectively, when compared to the previous predictors.