fuzzynetme.m

模糊神经网络的源码,课程设主计.主要用来识别电子鼻的信号.

0.315325 0.712474 0.921206
-0.052928 0.494101 0.635728
0.141766 0.670794 0.760876
0.008599 0.387486 0.947277
0.229758 0.515161 0.738411
0.134957 0.398260 0.885137
0.111348 0.769630 0.735744
0.133963 0.672229 0.890373
0.124627 0.442527 0.773654
0.107462 0.492535 0.797023
0.337611 0.528615 1.145781
0.416004 0.699016 0.672188
0.197794 0.590739 0.900863
0.273005 0.675062 0.920654
0.184871 0.641239 0.741380
0.360592 0.628703 0.559738
0.352078 0.614140 0.939540
0.101144 0.623587 0.809769
0.344834 0.599050 0.689387
0.241832 0.611011 0.810027
0.300606 0.685237 0.632546
0.315010 0.743986 0.879612
0.230214 0.644426 0.829833
0.248017 0.495882 0.847419
0.192809 0.555193 0.918667
0.250953 0.648363 0.573767
0.121296 0.642049 0.681178
0.087167 0.695241 0.891608
0.191314 0.590457 0.905993
0.142956 0.593265 0.787073
0.195933 0.622829 0.836336
0.237299 0.724017 0.848046
0.261891 0.697078 0.887312
0.075740 0.672585 0.861448
0.212134 0.537969 0.791445
0.178345 0.472797 0.766171
0.090934 0.513567 0.767410
0.224723 0.566075 0.665635
0.278951 0.629553 0.626396
0.325850 0.625509 0.864444
0.386198 0.585117 0.947265
0.186887 0.667300 0.718277
0.274593 0.561257 0.629010
0.236627 0.494309 0.746264
0.289616 0.775644 0.800168
0.232198 0.469460 0.698161
0.274975 0.804692 0.814183
0.286955 0.566231 0.841978
0.280761 0.653330 0.798050
0.305449 0.546973 0.892574
0.253589 0.462887 0.831105
0.246836 0.613317 0.971417
0.262470 0.617391 0.767338
0.300860 0.578183 0.584115
0.207768 0.666284 0.684327
0.161581 0.612896 0.852357
0.051277 0.491834 0.826126
0.094900 0.634321 0.836388
0.222077 0.586113 0.781286
0.355240 0.647251 1.009560
0.328522 0.572896 0.901232
0.259481 0.637578 0.793849
0.145001 0.556328 0.904438
0.338647 0.588203 0.716482
-0.041180 0.474669 0.764142
0.232134 0.661005 0.723340
0.248878 0.733179 0.845457
0.203448 0.567606 1.008187
0.210770 0.539824 0.833425
0.239668 0.500122 0.752636
0.831678 0.804795 0.155644
0.776735 0.752671 0.292266
0.600872 0.760260 0.094742
0.703883 0.618274 0.125947
0.802556 0.841052 0.335573
1.019829 0.847680 0.057950
0.719935 0.627003 0.054897
0.779208 0.984299 0.102984
0.714717 0.881637 0.063705
0.736667 0.927627 0.270017
0.683876 0.812036 0.241429
0.935873 0.877326 0.228867
0.821752 0.636409 0.235778
0.658073 0.804085 0.259118
0.864133 0.727434 0.036387
0.837794 0.711635 0.152326
0.753672 0.632802 0.333204
0.729950 0.685134 0.209652
0.688781 0.653460 0.179887
0.888247 0.554939 0.283036
0.827616 0.815725 0.123248
0.778103 0.746102 0.370644
0.912180 0.692752 0.337098
0.554514 0.905204 0.191223
0.872538 0.975459 0.354120
0.751266 0.605758 0.260688
0.801079 0.927546 0.170891
0.810413 0.752277 0.264001
0.810722 0.831253 0.108270
0.785440 0.846528 0.248993
0.717758 0.738610 0.377319
0.904174 0.837551 0.181111
0.730882 0.946788 0.173416
0.908320 0.827785 0.155115
0.806731 0.830277 0.268638
0.962947 0.743818 0.044955
0.723100 0.748437 0.211055
0.576942 1.032520 0.176863
0.655460 0.774835 0.231659
0.719657 0.793798 0.210118
0.856185 0.736512 0.083819
0.745491 0.904876 0.078868
0.614603 0.678210 0.149167
0.766720 0.841743 0.233907
0.621775 0.851495 0.264958
0.753677 0.673176 0.253822
0.634466 0.856511 0.274433
0.800969 0.814248 0.306370
0.721594 0.734700 0.399198
0.762666 1.010526 0.131430
0.723995 0.746513 0.291180
0.920509 0.752647 0.351505
0.835864 0.675044 0.272346
0.960085 0.644697 0.245942
0.617062 0.710566 0.214540
0.773034 0.847974 0.333181
0.811874 0.794947 0.286792
0.924066 0.696867 0.021767
0.875469 0.742721 0.202775
0.652457 0.876541 0.209465
0.910923 0.847990 0.145468
0.845968 0.801343 0.286391
0.827287 0.751551 0.218773
0.678928 0.711872 0.101925
0.702351 0.735599 0.110806
0.798099 0.648096 0.198124
0.839430 0.803990 0.103557
0.941250 0.867365 0.198033
0.868871 0.736422 0.149492
0.794166 0.866339 0.217233
0.826525 0.967986 0.141155
0.768885 0.920184 0.211553
0.735452 0.801158 0.090833
0.775080 0.637230 0.348050
0.737967 0.848903 0.276251
0.898889 0.757651 0.364313
0.804421 0.974257 0.258476
0.915697 0.878662 0.230761
0.570624 0.801617 0.165452
0.844996 0.775701 0.173766
0.739133 0.991206 0.280132
0.826122 0.697692 0.191861
0.719255 0.651628 0.245861
0.733357 0.703129 0.193641
0.822288 0.703160 0.357634
1.023937 0.607714 0.195500
0.750138 0.893237 0.106830
0.855337 0.788532 -0.015447
0.765459 0.737548 0.274907
0.790182 0.701960 0.172857
0.594376 0.759853 0.261366
0.632404 0.758662 -0.011820
0.880324 0.621815 -0.081820
0.687138 0.750646 0.249603
0.904426 0.687127 0.075188
0.864466 0.969955 0.244271
0.898628 0.681909 0.024510
0.799802 0.868238 0.163611
0.983841 0.977414 0.245467
0.824878 0.676021 0.068454
0.967516 0.895312 0.439989
0.767357 0.806826 0.119205
0.705723 0.905739 0.435416
0.765963 0.841722 -0.127443
0.865840 0.634624 0.388677
0.742227 0.817760 0.228885
0.793123 0.633102 0.197346
0.733566 0.968495 0.318109
0.838422 0.953400 0.338916
0.784272 0.771455 0.151093
0.719869 0.870907 0.105571
0.806801 0.746634 0.115673
0.847680 0.596256 0.218292
0.766288 0.704322 0.089228
0.822841 0.904921 0.133948
0.788285 0.669427 0.281401
0.895724 0.750321 0.074742
0.838632 0.610562 0.112404
0.855888 0.534568 0.036229
0.896815 0.603062 0.167309
0.789412 0.870773 0.179302
0.630953 0.858211 0.228326
0.674898 0.864880 0.172793
0.711003 0.690316 0.294852
0.834538 0.727207 0.294235
0.879269 0.979664 0.096464
0.820038 0.697624 0.234470
0.776988 0.801927 0.045260
0.746219 0.796985 0.185915
0.980697 0.992286 0.189712
0.713018 0.753727 0.176623
0.802319 0.837681 0.228531
0.787266 0.869900 0.170249
0.886901 0.930392 0.278421
0.778220 0.835627 0.194745
0.845548 0.617844 0.119720
0.691448 0.727179 0.188282
0.628561 0.776312 0.224174
0.862713 0.993634 0.277240
0.765490 0.768461 0.144680
0.824317 0.842126 0.053161
0.768397 0.677690 0.338811
0.739637 0.862360 0.031372
0.912304 0.887888 0.284121
0.906346 0.753940 0.097006
0.966168 0.809663 0.256732
0.874635 0.851286 0.047502
0.786787 0.696199 0.201465
0.857948 0.720304 0.083902
0.716376 0.740731 0.167288
0.785207 0.600256 0.207106
0.764181 0.609576 0.186104
0.670882 0.885844 0.143628
1.023023 0.831343 0.308951
0.775161 0.831437 0.209720
0.712506 0.732263 0.220539
0.787360 1.018250 0.247800
0.730108 0.721646 0.016262
0.860980 0.908725 0.221863
0.840676 0.790879 0.205979
0.694084 0.928993 0.296258
0.734086 0.734211 0.245261
0.927880 0.579765 0.074929
0.957072 0.782010 0.187191
0.868486 0.864737 0.157944
0.801733 0.859830 0.257984
1.018797 0.678677 0.163247
0.740327 0.770519 0.190785
0.747708 0.940523 0.131064
0.807147 0.896275 0.206115
0.921184 0.592717 0.219388
0.689103 0.808430 0.267128
0.854005 0.884039 0.195166
0.770415 0.685312 0.147119
0.734074 1.024665 0.288993
0.910705 0.862889 0.378147
0.799909 0.736274 0.236056
0.716706 0.769349 0.189817
0.850130 0.782498 0.333608
0.877958 0.782907 0.127847
0.837537 0.973095 0.115956
0.614384 0.735866 0.173554
0.659471 0.816549 -0.009519
0.756123 0.846472 0.238308
0.775094 0.694292 0.225554
0.724050 0.822051 0.054886
0.888969 0.750418 0.162054
0.543629 0.829535 0.280533
0.896727 0.835773 0.166744
0.812514 0.645252 0.270328
0.867305 0.678824 0.129758
0.773276 1.018349 0.230349
0.687777 0.862674 0.207810
0.779720 0.819054 0.180125
0.764586 0.702748 0.234426
1.008211 0.744494 0.195414
0.812520 0.903604 0.055420
0.874461 0.760863 0.232654
0.828726 0.869687 0.214416
0.936624 0.779057 0.197698
];


numPts=600;  
trnData=data(1:2:numPts,:); %训练数据集
chkData=data(2:2:numPts,:); %检验数据集
%绘制检验数据集和检验数据集的分布图
figure;
epoch=1:300;     
plot(epoch,trnData(:,3),'o',epoch,chkData(:,3),'kx'); 
legend('训练数据集','检验数据集');
fismat = genfis1(data,[2 3],char('gaussmf','gaussmf'));%采用网格方式生成初始Sugeno型模糊推理系统
                                                       %隶属度函数选用高斯函数
figure;  %绘制初始隶属度函数曲线
[x,mf]=plotmf(fismat,'input',1);
subplot(2,2,1),plot(x,mf);
xlabel('input 1 (gaussmf)');
[x,mf]=plotmf(fismat,'input',2);
subplot(2,1,2),plot(x,mf);
xlabel('input 2 (gaussmf)');
title('初始隶属度函数');

numEpochs = 130; %训练次数为40
%利用自适应神经算法进行模糊系统的训练（参数学习），采用反向传播算法
[fismat1,trnErr,ss,fismat2,chkErr] = anfis(trnData,fismat,numEpochs,NaN,chkData,1);
%计算训练后神经网络模糊系统的输出与训练数据的均方根误差
trnOut = evalfis([trnData(:,1) trnData(:,2)]',fismat1);
trnRNSE = norm(trnOut - trnData(:,3)) / sqrt(length(trnOut));
figure;
epoch=1:numEpochs
plot(epoch,trnErr,'o',epoch,chkErr,'kx');
%绘制训练过程中的最小二乘误差变化情况，如果和核对数据的误差同时减小，
%模型才是有效的
legend('训练数据误差','校验数据误差');
hold on;
plot(epoch,[trnErr chkErr]);
hold off;

%下面绘制训练后模糊推理系统的隶属度函数曲线
figure;
[x,mf]=plotmf(fismat1,'input',1);
subplot(2,2,1),plot(x,mf);
xlabel('input 1 (gaussmf)');

[x,mf]=plotmf(fismat1,'input',2);
subplot(2,1,2),plot(x,mf);
xlabel('input 2 (gaussmf)');
title('训练后的隶属度函数');
%绘制训练后的神经网络模糊推理系统的输入/输出分布图
figure;
anfis_y=evalfis([data(:,1) data(:,2)]',fismat1);
epoch=1:600;
plot(epoch,data(:,3),'o',epoch,anfis_y,'kx');
legend('原始数据集','结果模糊系统曲线');