Keratoconus Severity Classification Using Features Selection and Machine Learning Algorithms

Algorithm 2

KNN algorithm.

Input data:

   i. Dataset D.

   ii. A distance calculation function.

   iii. A number K

To predict a new observation X, do:

1. Calculate all distances of this observation with the other observations in the dataset D.

2. Retain the K observations from the dataset close to X using the selected distance calculation function.

3. Take the values of retained observations:

   a. if regression: Calculate the average of retained observations values.

   b. if classification: Calculate the mode of retained observations values.

4. Return the value calculated in step 3 as a predicted value by K-NN for the observation X.