Enhancing Wind Tunnel Data Classification Through Effective Data Preprocessing for Machine Learning Algorithm Modeling

Wind tunnel experiments provide valuable insights into the aerodynamics behavior of objects, enabling engineers and researchers to optimize designs and enhance performance. In one series of a wind tunnel test can be produced a huge of data. In relation of this number of data, furthermore, a classification have to be built to simplify in recognizing the type of the data resulted from the wind tunnel experiments. In recent years, machine learning techniques have shown great potential in analyzing wind tunnel data and extracting meaningful patterns. However, the preprocessing stage plays a critical role in preparing the data for machine learning modeling, ensuring accurate and reliable classification results. This research focuses on the preprocessing of wind tunnel data for machine learning modeling, specifically targeting classification tasks by doing noise reduction, missing data handling, feature scaling, and outlier detection.