pcaPerfViaKnncLoo

PCA analysis using KNNC and LOO

Contents

Syntax

Description

recogRate=pcaPerfViaKnncLoo(DS) return the leave-one-out recognition rate of KNNC on the dataset DS after dimension reduction using PCA (principal component analysis)

Example

PCA over WINE dataset

DS=prData('wine');
recogRate1=pcaPerfViaKnncLoo(DS, [], 1);

		LOO recog. rate of KNNC using 1 dim = 126/178 = 70.7865%
		LOO recog. rate of KNNC using 2 dim = 128/178 = 71.9101%
		LOO recog. rate of KNNC using 3 dim = 130/178 = 73.0337%
		LOO recog. rate of KNNC using 4 dim = 135/178 = 75.8427%
		LOO recog. rate of KNNC using 5 dim = 136/178 = 76.4045%
		LOO recog. rate of KNNC using 6 dim = 137/178 = 76.9663%
		LOO recog. rate of KNNC using 7 dim = 137/178 = 76.9663%
		LOO recog. rate of KNNC using 8 dim = 137/178 = 76.9663%
		LOO recog. rate of KNNC using 9 dim = 137/178 = 76.9663%
		LOO recog. rate of KNNC using 10 dim = 137/178 = 76.9663%
		LOO recog. rate of KNNC using 11 dim = 137/178 = 76.9663%
		LOO recog. rate of KNNC using 12 dim = 137/178 = 76.9663%
		LOO recog. rate of KNNC using 13 dim = 137/178 = 76.9663%

Effect of input normalization of PCA over WINE dataset

DS=prData('wine');
recogRate1=pcaPerfViaKnncLoo(DS);
DS.input=inputNormalize(DS.input);
recogRate2=pcaPerfViaKnncLoo(DS);
plot(1:length(recogRate1), 100*recogRate1, '.-', 1:length(recogRate2), 100*recogRate2, '.-'); grid on
xlabel('No. of projected features based on PCA');
ylabel('LOO recognition rates using KNNC (%)');
legend('Without input normalization', 'With input normalization', 'location', 'southwest');

Published with MATLAB® R2018a