Optimisasi Metode K-NN (K-Nearest Neighbour) Menggunakan Fuzzy Logic pada Klasifikasi Data

Abstract

Classifications data can be undertaken by using a method of K-Nearest Neighbour through proximity the distance data training with the data that are being tested. A problem was often the case in the process of data processing using a method of K Nearest Neighbour is the result the value of being ambiguous and it is not clear if the distance between data is too near. A new method is required in solving the problem. Fuzzy logic was used in the study in the methods of k-nearest neighbour to group its output target. The data used in this research was classifications a disease of the teeth to determine illnesses that fit on the teeth and classifications the type of leaves to determination of the types of what is fitting and becoming leaves on the leaves. A method of testing shows K-Nearest Neighbour and data obtained the level of accuracy of a disease of the teeth by 86 % and methods K Nearest Neighbour with the data leaves obtained the level of accuracy of as much as 73.3 %. A method of testing shows K-Nearest Neighbour Fuzzy and data obtained the level of accuracy of a disease of the teeth of 93 % and methods K Nearest Neighbour Fuzzy with the data leaves obtained the level of accuracy of 93 %. K-Nearest Neighbour Fuzzy prove even more reliable methods used in data processing to classification.