njit-etd2003-081 - New Jersey Institute of Technology

njit-etd2003-081 - New Jersey Institute of Technology njit-etd2003-081 - New Jersey Institute of Technology

archives.njit.edu
from archives.njit.edu More from this publisher
20.01.2015 Views

295 Hotelling's T2 (Fourth Output) 15. The last output of the princomp function, t2, is Hotelling's T2, a statistical measure of the multivariate distance of each observation from the center of the data set. This is an analytical way to find the most extreme points in the data. >> [st2, index] = sort(t2); % Sort in ascending order. >> st2 = flipud(st2); % Values in descending order. >> index = flipud(index); % Indices in descending order. >> extreme = index(1) extreme = 10 >> names(extreme,:) ans = ecc It is not surprising that the ratings for COPD subject `ecc' is the furthest from the average COPD group.

296 B.2.7 Cluster Analysis Program This program is a MATLAB m-file. Upon starting MATLAB, type whitebg for a white graphic background. 1. The data needed is the data set formed from 15 HRV parameters as the results of PCA on real COPD/Normal data and cross-spectral analysis. The data set is saved as an ASCII file. In order to load it into MATLAB. Type: load Agul.asc; Note: Agul is the filename. If you now type whos, the file should show up as the variable Agul. 2. Run the program using the general format: [RITrue,RISelf,EstIndex]=DoClustering(Algorithm,Data,k,TrueID,Repetitions) [algo, self, 2]=DoClustering(kmeans, Agu1,5„2) Here, data is Agul, k=5 clusters and run 2 repetitions. 3. The program will run and output a plot with five separate clusters as asked in the above command.

296<br />

B.2.7 Cluster Analysis Program<br />

This program is a MATLAB m-file. Upon starting MATLAB, type whitebg for a white<br />

graphic background.<br />

1. The data needed is the data set formed from 15 HRV parameters as the results <strong>of</strong><br />

PCA on real COPD/Normal data and cross-spectral analysis. The data set is saved as an<br />

ASCII file. In order to load it into MATLAB. Type:<br />

load Agul.asc; Note: Agul is the filename.<br />

If you now type whos, the file should show up as the variable Agul.<br />

2. Run the program using the general format:<br />

[RITrue,RISelf,EstIndex]=DoClustering(Algorithm,Data,k,TrueID,Repetitions)<br />

[algo, self, 2]=DoClustering(kmeans, Agu1,5„2)<br />

Here, data is Agul, k=5 clusters and run 2 repetitions.<br />

3. The program will run and output a plot with five separate clusters as asked in the<br />

above command.

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!