Index in position 1 exceeds array bounds. Index must not exceed 24. Error in RNN_CW2 (line 20) GlucoseReadings_T = GlucoseReadings_T(ind, :);
1 view (last 30 days)
Show older comments
clc; clear all; close all;
load GlucoseReadings.mat
rand('seed', 0)
GlucoseReadings_T = GlucoseReadings';
GR_outputC1 = categorical(GR_output);
CS = categories(GR_outputC1);
train_index = []; val_index = []; test_index = [];
for i = 1 : length(CS)
indi = find(GR_outputC1==CS{i});
% Shuffling data
indi = indi(randperm(length(indi)));
% 2/3---train, 1/6---val, 1/6---test
index1 = round(length(indi)*2/3);
index2 = round(length(indi)*(2/3+1/6));
train_index = [train_index indi(1:index1)];
val_index = [val_index indi(1+index1:index2)];
test_index = [test_index indi(1+index2:end)];
end
ind = [train_index val_index test_index];
GlucoseReadings_T = GlucoseReadings_T(ind, :);
GR_output = categorical(GR_output(ind));
% Split Data
GlucoseReadings_train = GlucoseReadings_T;
train_GlucoseReadings = GlucoseReadings_train(1:17,:);
train_GR_output = GR_output(1:17);
% Data Batch
GlucoseReadingsTrain=(reshape(train_GlucoseReadings', [1438,17]));
val_GlucoseReadings = GlucoseReadings_train(18:21,:);
val_GR_output = GR_output(18:21);
GlucoseReadingsVal=(reshape(val_GlucoseReadings', [1438,4]));
test_GlucoseReadings =GlucoseReadings_train(18:21,:);
test_GR_output = Gr_output(22:24);
GlucoseReadingsTest=(reshape(test_GlucoseReadings', [1438,3]));
numFeatures = size(GlucoseReadings_T,2);
% number of hidden units represent the size of the data
numHiddenUnits = 24;
%number of classes represent different patients normal,LIS,type2....
numClasses = length(categories(categorical(GR_output)));
layers = [ ...
sequenceInputLayer(numFeatures)
%dropoutLayer(0.5)
instanceNormalizationLayer
bilstmLayer(round(numHiddenUnits/2),'OutputMode','sequence')
fullyConnectedLayer(numClasses)
instanceNormalizationLayer
softmaxLayer
classificationLayer];
options = trainingOptions('adam', ...
'MaxEpochs',100, ...
'GradientThreshold',1, ...
'Verbose',false, ...
'ValidationData',{GlucoseReadingsVal, val_GR_output},...
'LearnRateDropFactor',0.2,...
'LearnRateDropPeriod',5,...
'Plots','training-progress');
% Train
net = trainNetwork(GlucoseReadingsTrain,train_GR_output,layers,options);
% Test
miniBatchSize = 27;
GR_outputPred = classify(net,GlucoseReadingsTest, ...
'MiniBatchSize',miniBatchSize,...
'ExecutionEnvironment', 'cpu');
acc = mean(GR_outputPred(:) == categorical(test_GR_output(:)))
figure
t = confusionchart(categorical(test_GR_output(:)),GR_outputPred(:));
0 Comments
Accepted Answer
yanqi liu
on 23 Feb 2022
clc; clear all; close all;
load GlucoseReadings.mat
rand('seed', 0)
GlucoseReadings_T = GlucoseReadings';
GR_outputC1 = categorical(GR_output);
len = min(length(GR_outputC1),size(GlucoseReadings_T,1));
GlucoseReadings_T = GlucoseReadings_T(1:len,:);
GR_outputC1 = GR_outputC1(1:len);
CS = categories(GR_outputC1);
train_index = []; val_index = []; test_index = [];
for i = 1 : length(CS)
indi = find(GR_outputC1==CS{i});
% Shuffling data
indi = indi(randperm(length(indi)));
% 2/3---train, 1/6---val, 1/6---test
index1 = round(length(indi)*2/3);
index2 = round(length(indi)*(2/3+1/6));
train_index = [train_index indi(1:index1)];
val_index = [val_index indi(1+index1:index2)];
test_index = [test_index indi(1+index2:end)];
end
ind = [train_index val_index test_index];
GlucoseReadings_T = GlucoseReadings_T(ind, :);
GR_output = categorical(GR_output(ind));
% Split Data
GlucoseReadings_train = GlucoseReadings_T;
train_GlucoseReadings = GlucoseReadings_train(1:17,:);
train_GR_output = GR_output(1:17);
% Data Batch
GlucoseReadingsTrain=(reshape(train_GlucoseReadings', [1438,size(train_GlucoseReadings,1)]));
val_GlucoseReadings = GlucoseReadings_train(18:21,:);
val_GR_output = GR_output(18:21);
GlucoseReadingsVal=(reshape(val_GlucoseReadings', [1438,size(val_GlucoseReadings,1)]));
test_GlucoseReadings =GlucoseReadings_train(22:24,:);
test_GR_output = GR_output(22:24);
GlucoseReadingsTest=(reshape(test_GlucoseReadings', [1438,size(test_GlucoseReadings,1)]));
numFeatures = size(GlucoseReadings_T,2);
% number of hidden units represent the size of the data
numHiddenUnits = 24;
%number of classes represent different patients normal,LIS,type2....
numClasses = length(categories(categorical(GR_output)));
layers = [ ...
sequenceInputLayer(numFeatures)
%dropoutLayer(0.5)
instanceNormalizationLayer
bilstmLayer(round(numHiddenUnits/2),'OutputMode','sequence')
fullyConnectedLayer(numClasses)
instanceNormalizationLayer
softmaxLayer
classificationLayer];
options = trainingOptions('adam', ...
'MaxEpochs',100, ...
'GradientThreshold',1, ...
'Verbose',false, ...
'ValidationData',{GlucoseReadingsVal, val_GR_output},...
'LearnRateDropFactor',0.2,...
'LearnRateDropPeriod',5,...
'Plots','training-progress');
% Train
net = trainNetwork(GlucoseReadingsTrain,train_GR_output,layers,options);
% Test
miniBatchSize = 27;
GR_outputPred = classify(net,GlucoseReadingsTest, ...
'MiniBatchSize',miniBatchSize,...
'ExecutionEnvironment', 'cpu');
acc = mean(GR_outputPred(:) == categorical(test_GR_output(:)))
figure
t = confusionchart(categorical(test_GR_output(:)),GR_outputPred(:));
0 Comments
More Answers (0)
See Also
Categories
Find more on Sequence and Numeric Feature Data Workflows in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!