libsvm output prediction probability for multi-label classification - matlab

I am trying to use libsvm (with Matlab interface) to run some multi-label classification problem. Here is some toy problem using IRIS data:
load fisheriris;
featuresTraining = [meas(1:30,:); meas(51:80,:); meas(101:130,:)];
featureSelectedTraining = featuresTraining(:,1:3);
groundTruthGroupTraining = [species(1:30,:); species(51:80,:); species(101:130,:)];
[~, ~, groundTruthGroupNumTraining] = unique(groundTruthGroupTraining);
featuresTesting = [meas(31:50,:); meas(81:100,:); meas(131:150,:)];
featureSelectedTesting = featuresTesting(:,1:3);
groundTruthGroupTesting = [species(31:50,:); species(81:100,:); species(131:150,:)];
[~, ~, groundTruthGroupNumTesting] = unique(groundTruthGroupTesting);
% Train the classifier
optsStruct = ['-c ', num2str(2), ' -g ', num2str(4), '-b ', 1];
SVMClassifierObject = svmtrain(groundTruthGroupNumTraining, featureSelectedTraining, optsStruct);
optsStruct = ['-b ', 1];
[predLabelTesting, predictAccuracyTesting, ...
predictScoresTesting] = svmpredict(groundTruthGroupNumTesting, featureSelectedTesting, SVMClassifierObject, optsStruct);
However, for the predict probabilities I have got (the first 12 rows of results showed here)
1.08812899093155 1.09025554950852 -0.0140009056912001
0.948911671379753 0.947899227815959 -0.0140009056926024
0.521486301840914 0.509673405799383 -0.0140009056926027
0.914684487894784 0.912534150299246 -0.0140009056926027
1.17426551505833 1.17855350325579 -0.0140009056925103
0.567801459258613 0.557077025701113 -0.0140009056926027
0.506405203427106 0.494342606399178 -0.0140009056926027
0.930191457490471 0.928343421250020 -0.0140009056926027
1.16990617214906 1.17412523596840 -0.0140009056926026
1.16558843984163 1.16986137054312 -0.0140009056926015
0.879648874624610 0.876614924593740 -0.0140009056926027
-0.151223818963057 -0.179682730685229 -0.0140009056925999
I am confused that how some of the probabilities are larger than 1 and some of them are negative?
However, the predicted label seems quite accurate:
1
1
1
1
1
1
1
1
1
1
1
3
with final output of
Accuracy = 93.3333% (56/60) (classification)
Then how to interpret the results of the predicted probabilities? Thanks a lot. A.

The output of an svm are not probabilities!
The score's sign indicates whether it belongs to class A or class B. And if the score is 1 or -1 it is on the margin, although that is not particularly useful to know.
If you really need probabilities, you can convert them using Platt scaling. You basically apply a sigmoid function to them.

I understand that this answer is probably too late, but it may benefit people encountering the same problem.
libsvm can in fact produce probabilities, for which the option '-b' is used.
I think the mistake you made is in the way you defined the optsStruct variable. It should be defined like this: ['-b ' num2str(1)] OR ['-b 1'].
The same applies to the options sent to the svmtrain.

Related

EEG data classification with SWLDA using matlab

I want to ask your help in EEG data classification.
I am a graduate student trying to analyze EEG data.
Now I am struggling with classifying ERP speller (P300) with SWLDA using Matlab
Maybe there is something wrong in my code.
I have read several articles, but they did not cover much details.
My data size is described as below.
size(target) = [300 1856]
size(nontarget) = [998 1856]
row indicates the number of trials, column indicates spanned feature
(I stretched data [64 29] (for visual representation I did not select ROI)
I used stepwisefit function in Matlab to classify target vs non-target
Code is attached below.
ingredients = [targets; nontargets];
heat = [class_targets; class_nontargets]; % target: 1, non-target: -1
randomized_set = shuffle([ingredients heat]);
for k=1:10 % 10-fold cross validation
parition_factor = ceil(size(randomized_set,1) / 10);
cv_test_idx = (k-1)*parition_factor + 1:min(k * parition_factor, size(randomized_set,1));
total_idx = 1:size(randomized_set,1);
cv_train_idx = total_idx(~ismember(total_idx, cv_test_idx));
ingredients = randomized_set(cv_train_idx, 1:end-1);
heat = randomized_set(cv_train_idx, end);
[W,SE,PVAL,INMODEL,STATS,NEXTSTEP,HISTORY]= stepwisefit(ingredients, heat, 'penter', .1);
valid_id = find(INMODEL==1);
v_weights = W(valid_id)';
t_ingredients = randomized_set(cv_test_idx, 1:end-1);
t_heat = randomized_set(cv_test_idx, end); % true labels for test set
v_features = t_ingredients(:, valid_id);
v_weights = repmat(v_weights, size(v_features, 1), 1);
predictor = sum(v_weights .* v_features, 2);
m_result = predictor > 0; % class A: +1, B: 0
t_heat(t_heat==-1) = 0;
acc(k) = sum(m_result==t_heat) / length(m_result);
end
p.s. my code is currently very inefficient and might be bad..
In my assumption, stepwisefit calculates significant coefficients every steps, and valid column would be remained.
Even though it's not LDA, but for binary classification, LDA and linear regression are not different.
However, results were almost random chance.. (for other binary data on the internet, it worked..)
I think I made something wrong, and your help can correct me.
I will appreciate any suggestion and tips to implement classifier for ERP speller.
Or any idea for implementing SWLDA in Matlab code?
The name SWLDA is only used in the context of Brain Computer Interfaces, but I bet it has another name in a more general context.
If you track the recipe of SWLDA you will end up in Krusienski 2006 papers ("A comparison..." and "Toward enhanced P300..") and from there the book where stepwise logarithmic regression is explained: "Draper Smith, Applied Regression Analysis, 1981". However, as far as I am aware of, no paper gives actually the complete recipe on how to implement it (and their details and secrets).
My approach was using stepwiseglm:
H=predictors;
TH=variables;
lbs=labels % (1,2)
if (stepwiseflag)
mdl = stepwiseglm(H', lbs'-1,'constant','upper','linear','distr','binomial');
if (mdl.NumEstimatedCoefficients>1)
inmodel = [];
for i=2:mdl.NumEstimatedCoefficients
inmodel = [inmodel str2num(mdl.CoefficientNames{i}(2:end))];
end
H = H(inmodel,:);
TH = TH(inmodel,:);
end
end
lbls = classify(TH',H',lbs','linear');
You can also use a k-fold cross validaton approach using matlab cvpartition.
c = cvpartition(lbs,'k',10);
opts = statset('display','iter');
fun = #(XT,yT,Xt,yt)...
(sum(~strcmp(yt,classify(Xt,XT,yT,'linear'))));

libsvm: optimization finished, #iter = 1 nu = nan

I use libsvm to train a svm model in matlab, but when I call
model = svmtrain(labels,Feature,'-t 0');
It gives me this result:
*
optimization finished, #iter = 1
nu = nan
obj = nan, rho = nan
nSV = 0, nBSV = 0
Total nSV = 0
My positive and negative samples are of almost equal number: 935 vs 904 so this problem is not caused by unbalanced training dataset. Also I tried other kernels and none of them work.
You do not want to use svmtrain any more. The new version is templatesvm paired with fitcecoc. The datapages on both functions are quite extensive.
You'll eventually want to use your model to predict other data, use predict for that.
I recently encoutered similar problems when trying to classify terrain in a point cloud with more than two classes. templatesvm and fitcecoc solved my problems.
The code I used is as follows, where trainingdata is my 5 dimensional training data and groups contains the label for each class, which correspond to the cell array classes.
SVMtemp = templateSVM('KernelFunction','polynomial','IterationLimit',1e4,...
'PolynomialOrder',4,'OutlierFraction',ExpOut,...
'Standardize',true); % Create SVM template
Model = fitcecoc(trainingdata(:,4:8),groups,'learners',SVMtemp,'ClassNames',...
classes); % Create the SVM model

Matlab function adapt() doesn't seem to work

I have the following code implemented in Matlab. I want to train the perceptron using a batch algorithm to separate this liniar separable points. So, in order to do that I use adapt() function but it doesn't seem to work. What I mean by that is that my perceptron is not able to classify the points as they should be. It has some weights which are not useful in any way. On the other hand, when I use train() function everything goes according to plan.The perceptron is able to classify the points with accuracy. Can anyone explain to me what is wrong with my code? Thanks in advance!
function problema2_1()
p = -1 + ( 1 + 1) .* rand(3,5);
for i = 1 : length(p)
if 2 * p(1,i) - p(2,i) + p(3,i) < 0
t(i) = -1;
else
t(i) = 1;
end
end
net = newp([-1 1; -1 1; -1 1],1,'hardlims');
net.adaptParam.passes = 1000000;
net = adapt(net,p,t);
plotpv(p,hardlim(t));
hold on
plotpc(net.IW{1,1,1},net.b{1});
t - sim(net,p)
end
adapt only runs passes through your training data once and thus makes very small updates to the network weights. Meanwhile train iterates on the training data several times until a stopping condition is met.
The examples in the Matlab documentation for adapt should provide some clarification. I suspect your line net.adaptParam.passes = 1000000 isn't doing what you think it's doing.
As an immediate fix, just try looping over your net = adapt(net,p,t) several times to verify that the resultant network seems to be converging to the one obtained when using train().

Bag of words not correctly labeling responses

I am trying to implement Bag of Words in opencv and has come with the implementation below. I am using Caltech 101 database. However, since its my first time and not being familiar, I have planned to used two image sets from the database, the chair image set and the soccer ball image set. I have coded for the svm using this.
Everything went allright, except when I call classifier.predict(descriptor) , I do not get the label vale as intended. I always get a0 instead of '1', irrespective of my test image. The number of images in the chair dataset is 10 and in the soccer ball dataset is 10. I labelled chair as 0 and soccer ball as 1 . The links represent the samples of each categories, the top 10 is of chairs, the bottom 10 is of soccer balls
function hello
clear all; close all; clc;
detector = cv.FeatureDetector('SURF');
extractor = cv.DescriptorExtractor('SURF');
links = {
'http://i.imgur.com/48nMezh.jpg'
'http://i.imgur.com/RrZ1i52.jpg'
'http://i.imgur.com/ZI0N3vr.jpg'
'http://i.imgur.com/b6lY0bJ.jpg'
'http://i.imgur.com/Vs4TYPm.jpg'
'http://i.imgur.com/GtcwRWY.jpg'
'http://i.imgur.com/BGW1rqS.jpg'
'http://i.imgur.com/jI9UFn8.jpg'
'http://i.imgur.com/W1afQ2O.jpg'
'http://i.imgur.com/PyX3adM.jpg'
'http://i.imgur.com/U2g4kW5.jpg'
'http://i.imgur.com/M8ZMBJ4.jpg'
'http://i.imgur.com/CinqIWI.jpg'
'http://i.imgur.com/QtgsblB.jpg'
'http://i.imgur.com/SZX13Im.jpg'
'http://i.imgur.com/7zVErXU.jpg'
'http://i.imgur.com/uUMGw9i.jpg'
'http://i.imgur.com/qYSkqEg.jpg'
'http://i.imgur.com/sAj3pib.jpg'
'http://i.imgur.com/DMPsKfo.jpg'
};
N = numel(links);
trainer = cv.BOWKMeansTrainer(100);
train = struct('val',repmat({' '},N,1),'img',cell(N,1), 'pts',cell(N,1), 'feat',cell(N,1));
for i=1:N
train(i).val = links{i};
train(i).img = imread(links{i});
if ndims(train(i).img > 2)
train(i).img = rgb2gray(train(i).img);
end;
train(i).pts = detector.detect(train(i).img);
train(i).feat = extractor.compute(train(i).img,train(i).pts);
end;
for i=1:N
trainer.add(train(i).feat);
end;
dictionary = trainer.cluster();
extractor = cv.BOWImgDescriptorExtractor('SURF','BruteForce');
extractor.setVocabulary(dictionary);
for i=1:N
desc(i,:) = extractor.compute(train(i).img,train(i).pts);
end;
a = zeros(1,10)';
b = ones(1,10)';
labels = [a;b];
classifier = cv.SVM;
classifier.train(desc,labels);
test_im =rgb2gray(imread('D:\ball1.jpg'));
test_pts = detector.detect(test_im);
test_feat = extractor.compute(test_im,test_pts);
val = classifier.predict(test_feat);
disp('Value is: ')
disp(val)
end
These are my test samples:
Soccer Ball
(source: timeslive.co.za)
Chair
Searching through this site I think that my algorithm is okay, even though I am not quite confident about it. If anybody can help me in finding the bug, it will be appreciable.
Following Amro's code , this was my result:
Distribution of classes:
Value Count Percent
1 62 49.21%
2 64 50.79%
Number of training instances = 61
Number of testing instances = 65
Number of keypoints detected = 38845
Codebook size = 100
SVM model parameters:
svm_type: 'C_SVC'
kernel_type: 'RBF'
degree: 0
gamma: 0.5063
coef0: 0
C: 62.5000
nu: 0
p: 0
class_weights: 0
term_crit: [1x1 struct]
Confusion matrix:
ans =
29 1
1 34
Accuracy = 96.92 %
Your logic looks fine to me.
Now I guess you'll have to tweak the various parameters if you want to improve the classification accuracy. This includes the clustering algorithm parameters (such as the vocabulary size, clusters initialization, termination criteria, etc..), the SVM parameters (kernel type, the C coefficient, ..), the local features algorithm used (SIFT, SURF, ..).
Ideally, whenever you want to perform parameter selection, you ought to use cross-validation. Some methods already have such mechanism embedded (CvSVM::train_auto for instance), but for the most part you'll have to do this manually...
Finally you should follow general machine learning guidelines; see the whole bias-variance tradeoff dilemma. The online Coursera ML class discusses this topic in detail in week 6, and explains how to perform error analysis and use learning curves to decide what to try next (do we need to add more instances, increase model complexity, and so on..).
With that said, I wrote my own version of the code. You might wanna compare it with your code:
% dataset of images
% I previously saved them as: chair1.jpg, ..., ball1.jpg, ball2.jpg, ...
d = [
dir(fullfile('images','chair*.jpg')) ;
dir(fullfile('images','ball*.jpg'))
];
% local-features algorithm used
detector = cv.FeatureDetector('SURF');
extractor = cv.DescriptorExtractor('SURF');
% extract local features from images
t = struct();
for i=1:numel(d)
% load image as grayscale
img = imread(fullfile('images', d(i).name));
if ~ismatrix(img), img = rgb2gray(img); end
% extract local features
pts = detector.detect(img);
feat = extractor.compute(img, pts);
% store along with class label
t(i).img = img;
t(i).class = find(strncmp(d(i).name,{'chair','ball'},4));
t(i).pts = pts;
t(i).feat = feat;
end
% split into training/testing sets
% (a better way would be to use cvpartition from Statistics toolbox)
disp('Distribution of classes:')
tabulate([t.class])
tTrain = t([1:7 11:17]);
tTest = t([8:10 18:20]);
fprintf('Number of training instances = %d\n', numel(tTrain));
fprintf('Number of testing instances = %d\n', numel(tTest));
% build visual vocabulary (by clustering training descriptors)
K = 100;
bowTrainer = cv.BOWKMeansTrainer(K, 'Attempts',5, 'Initialization','PP');
clust = bowTrainer.cluster(vertcat(tTrain.feat));
fprintf('Number of keypoints detected = %d\n', numel([tTrain.pts]));
fprintf('Codebook size = %d\n', K);
% compute histograms of visual words for each training image
bowExtractor = cv.BOWImgDescriptorExtractor('SURF', 'BruteForce');
bowExtractor.setVocabulary(clust);
M = zeros(numel(tTrain), K);
for i=1:numel(tTrain)
M(i,:) = bowExtractor.compute(tTrain(i).img, tTrain(i).pts);
end
labels = vertcat(tTrain.class);
% train an SVM model (perform paramter selection using cross-validation)
svm = cv.SVM();
svm.train_auto(M, labels, 'SvmType','C_SVC', 'KernelType','RBF');
disp('SVM model parameters:'); disp(svm.Params)
% evaluate classifier using testing images
actual = vertcat(tTest.class);
pred = zeros(size(actual));
for i=1:numel(tTest)
descs = bowExtractor.compute(tTest(i).img, tTest(i).pts);
pred(i) = svm.predict(descs);
end
% report performance
disp('Confusion matrix:')
confusionmat(actual, pred)
fprintf('Accuracy = %.2f %%\n', 100*nnz(pred==actual)./numel(pred));
Here are the output:
Distribution of classes:
Value Count Percent
1 10 50.00%
2 10 50.00%
Number of training instances = 14
Number of testing instances = 6
Number of keypoints detected = 6300
Codebook size = 100
SVM model parameters:
svm_type: 'C_SVC'
kernel_type: 'RBF'
degree: 0
gamma: 0.5063
coef0: 0
C: 312.5000
nu: 0
p: 0
class_weights: []
term_crit: [1x1 struct]
Confusion matrix:
ans =
3 0
1 2
Accuracy = 83.33 %
So the classifier correctly labels 5 out of 6 images from the test set, which is not bad for a start :) Obviously you'll get different results each time you run the code due to the inherent randomness of the clustering step.
What is the number of images you are using to build your dictionary i.e. what is N? From your code, it seems that you are only using a 10 images (those listed in links). I hope this list is truncated down for this post else that would be too few. Typically you need in the order of 1000 or much more images to build the dictionary and the images need not be restricted to only these 2 classes that you are classifying. Otherwise, with only 10 images and 100 clusters your dictionary is likely to be messed up.
Also, you might want to use SIFT as a first choice as it tends to perform better than the other descriptors.
Lastly, you can also debug by checking the detected keypoints. You can get OpenCV to draw the keypoints. Sometimes your keypoint detector parameters are not set properly, resulting in too few keypoints getting detected, which in turn gives poor feature vectors.
To understand more about the BOW algorithm, you can take a look at these posts here and here. The second post has a link to a free pdf for an O'Reilley book on computer vision using python. The BOW model (and other useful stuff) is described in more details inside that book.
Hope this helps.

Bad results when testing libsvm in matlab

can someone help me to solve this?
I want to test whether this classification is already good or not. So, I try with data testing=data training. it will give 100% (acc) if the classification is good.
this is the code that I found from this site:
data= [170 66 ;
160 50 ;
170 63 ;
173 61 ;
168 58 ;
184 88 ;
189 94 ;
185 88 ]
labels=[-1;-1;-1;-1;-1;1;1;1];
numInst = size(data,1);
numLabels = max(labels);
testVal = [1 2 3 4 5 6 7 8];
trainLabel = labels(testVal,:);
trainData = data(testVal,:);
testData=data(testVal,:);
testLabel=labels(testVal,:);
numTrain = 8; numTest =8
%# train one-against-all models
model = cell(numLabels,1);
for k=1:numLabels
model{k} = svmtrain(double(trainLabel==k), trainData, '-c 1 -t 2 -g 0.2 -b 1');
end
%# get probability estimates of test instances using each model
prob = zeros(numTest,numLabels);
for k=1:numLabels
[~,~,p] = svmpredict(double(testLabel==k), testData, model{k}, '-b 1');
prob(:,k) = p(:,model{k}.Label==1); %# probability of class==k
end
%# predict the class with the highest probability
[~,pred] = max(prob,[],2);
acc = sum(pred == testLabel) ./ numel(testLabel) %# accuracy
C = confusionmat(testLabel, pred) %# confusion matrix
and this is the results:
optimization finished, #iter = 16
nu = 0.645259 obj = -2.799682,
rho = -0.437644 nSV = 8, nBSV = 1 Total nSV = 8
Accuracy = 100% (8/8) (classification)
acc =
0.3750
C =
0 5
0 3
I dont know why there's two accuracy, and its different. the first one is 100% and the second one is 0.375. is my code false? it should be 100% not 37.5%. Can u help me to correct this code??
If your using libsvm then you should change the name of the MEX file since Matlab already has a svm toolbox with the name svmtrain. However, the code is running so it seems you did change the name just not on the code you provided.
The second one is wrong, don't know exactly why. However, I can tell you that you will almost always get 100% accuracy if you use the test_Data = training_Data. That result really does not mean anything, since the algorithm can be overfit and not be shown in your results. Test your algorithm against new data and that will give you a realistic accuracy.
Is that the code you're using? I don't think your svmtrain invocation is valid. You should have svmtrain(MAT, VECT, ...) where MAT is a matrix of data, and VECT is a vector with the labels of each row of MAT. The remaining parameters are string-value pairs, meaning you'll have a string identifier and its corresponding valie.
When I ran your code (Linux, R2011a) I got an error on the svmtrain call. Running with svmtrain(trainData, double(trainLabel==k)) gave a valid output (for that line). Of course, it appears that you're not using pure matlab, as your svmpredict call isn't native matlab, but rather a matlab binding from LIBSVM...
C = confusionmat(testLabel, pred)
swap their positions
C= confusionmat(pred,testLabel)
or use this
[ConMat,order] = confusionmat(pred,testLabel)
shows the confusion matrix and the class order
The problem is in
[~,~,p] = svmpredict(double(testLabel==k), testData, model{k}, '-b 1');
p does not contain the predicted labels, it has the probability estimates of the labels being correct. LIBSVM's svmpredict already calculates accuracy for you correctly, that's why it says 100% in the debug output.
The fix is simple:
[p,~,~] = svmpredict(double(testLabel==k), testData, model{k}, '-b 1');
According to LIBSVM's Matlab bindings README:
The function 'svmpredict' has three outputs. The first one,
predictd_label, is a vector of predicted labels. The second output,
accuracy, is a vector including accuracy (for classification), mean
squared error, and squared correlation coefficient (for regression).
The third is a matrix containing decision values or probability
estimates (if '-b 1' is specified). If k is the number of classes
in training data, for decision values, each row includes results of
predicting k(k-1)/2 binary-class SVMs. For classification, k = 1 is a
special case. Decision value +1 is returned for each testing instance,
instead of an empty vector. For probabilities, each row contains k values
indicating the probability that the testing instance is in each class.
Note that the order of classes here is the same as 'Label' field
in the model structure.
I am sorry to tell that all answers are totally wrong!!
The main error done in the code is:
numLabels = max(labels);
because it returns (1), although it should return 2 if the labels are positive numbers, and then svmtrain/svmpredict will loop twice.
Anyway, change line labels=[-1;-1;-1;-1;-1;1;1;1];
to labels=[2;2;2;2;2;1;1;1];
and it will work successfully ;)