Treffer: Development of KNN method for predicting tidal flood.

Every dataset has a different character, where it is necessary to find an appropriate method to process the dataset. Apart from the data set, each algorithm also has different characteristics and parameters, where these parameters need to be adjusted and the optimal value is found. K-Nearest Neighbor (KNN) is the most widely used algorithm among the ten other algorithms for data mining research and The KNN algorithm can provide competitive and significant results for solving classification problems. In this study, we used tidal flood dataset with two dua feature data (Sea Level & Wave Height) with a total of 52 data. The tools used in this study are jupyter lab with the Python programming. The testing data in the running program in this study is 25% and dataset processing will be carried out to obtain good accuracy through data scaling and the development of the KNN algorithm. We do three test cases to get a good accuracy value. the first case, using the original dataset and the KNN algorithm without parameter development. The second case, using a dataset with data scaling and KNN algorithm without parameter development. third case, using a dataset with data scaling and the KNN algorithm with parameter development of K values and distance metrics. The results of the study show that the first case has an accuracy value of 62%, the second case has an accuracy value of 77% and the third case has a value of 85%. The best accuracy is obtained with the condition where the dataset gets scaling and the KNN algorithm gets parameter development. [ABSTRACT FROM AUTHOR]

Copyright of AIP Conference Proceedings is the property of American Institute of Physics and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)