Rev | Line | |
---|
[80] | 1 | %SONAR 208 objects with 60 features in 2 classes |
---|
| 2 | % |
---|
| 3 | % X = SONAR |
---|
| 4 | % |
---|
| 5 | %This is the data set used by Gorman and Sejnowski in their study of the |
---|
| 6 | %classification of sonar signals using a neural network. The task is to |
---|
| 7 | %train a network to discriminate between sonar signals bounced off a |
---|
| 8 | %metal cylinder and those bounced off a roughly cylindrical rock. |
---|
| 9 | |
---|
[137] | 10 | function a = sonar |
---|
[80] | 11 | |
---|
[137] | 12 | a = pr_loadmatfile; |
---|
| 13 | if isempty(a) |
---|
| 14 | opt.labfeat = 61; |
---|
| 15 | opt.classnames = {'mines' 'rocks'}; |
---|
| 16 | opt.desc = 'The Sonar dataset from the undocumented databases from UCI. The task is to train a network to discriminate between sonar signals bounced off a metal cylinder and those bounced off a roughly cylindrical rock.'; |
---|
| 17 | opt.link = 'ftp://ftp.ics.uci.edu/pub/machine-learning-databases/undocumented/connectionist-bench/sonar'; |
---|
[158] | 18 | opt.dsetname = 'Sonar'; |
---|
[137] | 19 | a = pr_download('http://prtools.tudelft.nl/prdatasets/sonar.dat',[],opt); |
---|
| 20 | end |
---|
[158] | 21 | a = setname(a,'Sonar'); |
---|
[80] | 22 | |
---|
| 23 | return |
---|
Note: See
TracBrowser
for help on using the repository browser.