12
༒༑༐༏ بIslamic University Gaza Faculty of Engineering Department of Computer Engineering Neural Networks Assignment # 3 +4 Prepared By: Natheer A. Abu Jarir 120120820 Submitted to: Associate Professor: Mohammed Alhanjouri 2014

Homwork3 4

Embed Size (px)

DESCRIPTION

Third Assignment: Use all your data (F0, F1, F2, F3, and F4) for speaker classification (M, W, or C) by using Multi-layer Forward Neural Network with backpropagation training. Fourth Assignment: Use all data to classify 5 classes of vowels as following: 1st class: 1st, 2nd, and 3rd columns. 2nd class: 4th and 5th columns. 3rd class: 6th and 7th columns. 4th class: 8th, 9th, and 10th columns. 5th class: 11th and 12th columns. by using Multi-layer Forward Neural Network with backpropagation training.

Citation preview

Page 1: Homwork3 4

بسم ميحرلا نمحرلا هللا

Islamic University – Gaza

Faculty of Engineering

Department of Computer Engineering

Neural Networks

Assignment # 3 +4

Prepared By:

Natheer A. Abu Jarir 120120820

Submitted to:

Associate Professor: Mohammed Alhanjouri

2014

Page 2: Homwork3 4

Third Assignment :

Use all your data (F0, F1, F2, F3, and F4) for speaker classification

(M, W, or C) by using Multi-layer Forward Neural Network with

backpropagation training.

Matlab Code Neural Network :

close all, clear all, clc, format compact

% loading data

M = [138 135 129 127 123 123 121 129 133

143 133 130

342 427 476 580 588 768 652 497

269 378 623 474

2322 2034 2089 1799 1952 1333 997 910

1122 997 1200 1379

3000 2684 2691 2605 2601 2522 2538 2459

2434 2343 2550 1710

3657 3616 3649 3677 3624 3687 3486 3384

3400 3357 3557 3334 ];

W = [ 227 224 219 214 215 215 210 217 230

235 218 217

437 483 536 731 669 936 781 555

519 459 753 523

2761 2365 2530 2058 2349 1551 1136 1035

1225 1105 1426 1588

3372 3053 3047 2979 2972 2815 2824 2828

2827 2735 2933 1929

4352 4334 4319 4294 4290 4299 3923 3927

4052 4115 4092 3914 ];

C = [ 246 241 237 230 228 229 225 236 243

249 236 237

452 511 564 749 717 1002 803 597

568 494 749 586

3081 2552 2656 2267 2501 1688 1210 1137

1490 1345 1546 1719

3702 3403 3323 3310 3289 2950 2982 2987

3072 3988 3145 2143

4572 4575 4422 4671 4409 4307 3919 4167

4328 4276 4320 3788];

% define inputs (combine samples from all four classes)

P=[M W C];

Page 3: Homwork3 4

% define output coding for classes

a = [+1 +1]';

b = [+1 -1]';

c = [-1 +1]';

% define targets

T = [repmat(a,1,length(man)) repmat(b,1,length(woman)) ...

repmat(c,1,length(child))];

%# create ANN of one hidden layer with 7 nodes

net = feedforwardnet(10);

%# set params

net.layers{1}.transferFcn = 'logsig';

net.trainFcn = 'trainscg'; %# training function

net.trainParam.epochs = 5000; %# max number of iterations

net.trainParam.lr =.1; %# learning rate

net.performFcn = 'mse'; %# mean-squared error function

net.divideFcn = 'dividerand';

%# how to divide data

net.divideParam.trainRatio = 70/100; %# training set

net.divideParam.valRatio = 15/100; %# validation set

net.divideParam.testRatio = 30/100; %# testing set

% %

%# training

net = init(net);

[net,tr] = train(net, P,T);

%# testing

y_hat = net(ptest);

perf = perform(net, T, y_hat);

err = gsubtract(T, y_hat);

Results:

Page 4: Homwork3 4
Page 5: Homwork3 4
Page 6: Homwork3 4

Fourth Assignment:

Use all data to classify 5 classes of vowels as following:

1st class: 1st, 2nd, and 3rd columns.

2nd class: 4th and 5th columns.

3rd class: 6th and 7th columns.

4th class: 8th, 9th, and 10th columns.

5th class: 11th and 12th columns.

by using Multi-layer Forward Neural Network with backpropagation

training.

Matlab Code Neural Network :

close all, clear all, clc, format compact

class1 = [ 138 135 129

227 224 219

246 241 237

342 427 476

437 483 536

452 511 564

2322 2034 2089

2761 2365 2530

3081 2552 2656

3000 2684 2691

3372 3053 3047

3702 3403 3323

3657 3616 3649

4352 4334 4319

4572 4575 4422 ];

class2 = [ 127 123

214 215

230 228

580 588

731 669

749 717

1799 1952

2058 2349

2267 2501

2605 2601

2979 2972

3310 3289

3677 3624

4294 4290

4671 4409 ];

Page 7: Homwork3 4

class3 = [ 123 121

215 210

229 225

768 652

936 781

1002 803

1333 997

1551 1136

1688 1210

2522 2538

2815 2824

2950 2982

3687 3486

4299 3923

4307 3919];

class4 = [ 129 133 143

217 230 235

236 243 249

497 269 378

555 519 459

597 568 494

910 1122 997

1035 1225 1105

1137 1490 1345

2459 2434 2343

2828 2827 2735

2987 3072 3988

3384 3400 3357

3927 4052 4115

4167 4328 4276];

class5 = [ 133 130

218 217

236 237

623 474

753 523

749 586

1200 1379

1426 1588

1546 1719

2550 1710

2933 1929

3145 2143

3557 3334

4092 3914

4320 3788];

Page 8: Homwork3 4

% define inputs (combine samples from all four classes)

P=[class1 class2 class3 class4 class5];

% define output coding for classes

a = [+1 +1 +1]';

b = [+1 -1 +1]';

c = [-1 +1 +1]';

d = [+1 -1 -1]';

e = [-1 +1 -1]';

% define targets

T = [repmat(a,1,length(class1)) repmat(b,1,length(class2)) ...

repmat(c,1,length(class3)) repmat(d,1,length(class4)) ...

repmat(e,1,length(class5))];

%# create ANN of one hidden layer with 7 nodes

net = feedforwardnet(10);

%# set params

net.layers{1}.transferFcn = 'logsig';

net.layers{2}.transferFcn = 'purelin';

net.trainFcn = 'trainscg'; %# training function

net.trainParam.epochs = 5000; %# max number of iterations

net.trainParam.lr =.1; %# learning rate

net.performFcn = 'mse'; %# mean-squared error function

net.divideFcn = 'dividerand';

%# how to divide data

net.divideParam.trainRatio = 70/100; %# training set

net.divideParam.valRatio = 15/100; %# validation set

net.divideParam.testRatio = 30/100; %# testing set

%# training

net = init(net);

[net,tr] = train(net, P,T);

%# testing

y_hat = net(ptest);

perf = perform(net, T, y_hat);

err = gsubtract(T, y_hat);

Results:

Page 9: Homwork3 4
Page 10: Homwork3 4
Page 11: Homwork3 4
Page 12: Homwork3 4

References:

[1] Neural Networks: MATLAB examples.

[2] http://www.mathworks.com/help/nnet/index.html.