基于matlab实现AdaBoost数据分类

✅作者简介：热爱科研的Matlab仿真开发者，修心和技术同步精进，matlab项目合作可私信。

🍎个人主页：Matlab科研工作室

🍊个人信条：格物致知。

⛄ 内容介绍

在不平衡数据集中,由于少类样本和多类样本的不平衡,在分类过程中容易产生难以分类和错误分类的现象.针对不平衡数据集的分类特点,设计出一种组合分类器,适用于不平衡数据集的分类

⛄ 完整代码

%% -------------------------------------------------------------------

% Descrption : AdaBoost Classification Demo

% Reference : http://staff.ustc.edu.cn/~xjchen99/teaching/ImageUnderstanding/Robust%20real-time%20face%20detection.ppt

%% -------------------------------------------------------------------

function adaboostDemo

close all

clear all

clc

%% Settings

weakLearnerNum = 16; % how many weak classifiers will learn during AdaBoost training

displayTrainingProcess = 1; % whether display training process

%% generate samples

r = sqrt(rand(100,1)); % radius

t = 2*pi*rand(100,1); % angle

positive = [r.*cos(t), r.*sin(t)];

r = sqrt(3*rand(100,1)+1); % radius

t = 2*pi*rand(100,1); % angle

negative = [r.*cos(t), r.*sin(t)];

figure(1)

hold on

plot(positive(:,1),positive(:,2),'.r')

plot(negative(:,1),negative(:,2),'.b')

ezpolar(@(x)1);ezpolar(@(x)2);

axis equal

hold off

%% AdaBoost training process

data = [positive; negative];

labels = [ones(size(positive,1),1); -ones(size(negative,1),1)];

weights = [ones(size(positive,1),1) ./ (2*size(positive,1)); ones(size(negative,1),1) ./ (2*size(negative,1))];

weakLearners = zeros(weakLearnerNum,4); % [dimension, threshold, polarity, errorRate]

for t = 1 : weakLearnerNum

    % re-normalize the weights

    weights = weights ./ sum(weights);

    % select best classifier

    [dimension, threshold, polarity, errorRate] = selectBestClassifier(data, labels, weights);

    % update sample weights

    weights = updateSampleWeights(data, labels, weights, dimension, threshold, polarity, errorRate, displayTrainingProcess);

    % load weak classifier

    weakLearners(t,:) = [dimension, threshold, polarity, errorRate];

end

%% AdaBoosting predict process

figure(3)

hold on

for i = 1 : size(data,1)

    % classify by weak classifiers

    x = data(i,:);

    if adaboostingPredict(x, weakLearners) == 1

        plot(x(1), x(2), '.r');

    else

        plot(x(1), x(2), '.b');

    end

end

ezpolar(@(x)1);ezpolar(@(x)2);

axis equal

hold off

%% Classify sample

function label = adaboostingPredict(x, weakLearners)

dimensions = weakLearners(:,1);

thresholds = weakLearners(:,2);

polarities = weakLearners(:,3);

errorRates = weakLearners(:,4);

beta = errorRates ./ (1-errorRates);

alpha = log(1./beta);

features = x(dimensions);

hypothesis = (polarities' .* features)' < (polarities .* thresholds);

label = (alpha' * hypothesis) > (sum(alpha) * 0.5);

%% Update samples weights

function weights = updateSampleWeights(data, labels, weights, dimension, threshold, polarity, errorRate, displayTrainingProcess)

% classify data by current threshold

positive = find(polarity.*data(:,dimension) < polarity*threshold);

negative = find(polarity.*data(:,dimension) >= polarity*threshold);

% find the correct samples

positive(find(labels(positive) ~= 1)) = [];

negative(find(labels(negative) ~= -1)) = [];

corrects = [positive; negative];

weights(corrects) = weights(corrects) .* (errorRate / (1-errorRate));

% plot current weak classifier and weighted samples

if displayTrainingProcess == 1

    figure(2)

    clf(figure(2),'reset')

    hold on

    for i = 1 : size(data,1)

        color = 'y'; % default : incorrect classfied samples

        if ~isempty(find(positive == i)) % correct classified positive samples

            color = 'r';

        end

        if ~isempty(find(negative == i)) % correct classified negative samples

            color = 'b';

        end

        plot(data(i,1), data(i,2), 'o', 'MarkerEdgeColor', 'k', 'MarkerFaceColor', color, 'MarkerSize', weights(i)*size(data,1)*10);

    end

    if dimension == 1

        line([threshold, threshold], [-2, 2], 'LineWidth', 4, 'Color', [.8 .8 .8])

    else

        line([-2, 2], [threshold, threshold], 'LineWidth', 4, 'Color', [.8 .8 .8])

    end

    ezpolar(@(x)1);ezpolar(@(x)2);

    axis equal

    hold off

    pause

end

%% Select best classifier

function [bestDim, bestThreshold, bestPolarity, bestErrorRate] = selectBestClassifier(data, labels, weights)

bestDim = 0;

bestThreshold = 0;

bestPolarity = 0;

bestErrorRate = sum(weights);

for dim = 1 : size(data,2)

    [threshold, polarity, errorRate] = buildFeatureClassifier(data(:,dim), labels, weights);

    if errorRate <= bestErrorRate

        bestDim = dim;

        bestThreshold = threshold;

        bestPolarity = polarity;

        bestErrorRate = errorRate;

    end

end

%% Build feature classifier

function [bestThreshold, bestPolarity, bestErrorRate] = buildFeatureClassifier(data, labels, weights)

bestThreshold = 0;

bestPolarity = 0;

bestErrorRate = sum(weights);

% sort data

[data, index] = sort(data);

labels = labels(index);

weights = weights(index);

% generate possible splitters

splitters = data(1:end-1) + 0.5 * (data(2:end) - data(1:end-1));

for i = 1 : size(splitters,1)

    threshold = splitters(i);

    for polarity = -1 : 2 : 1 % polarity is (+) / (-)

        positive = find(polarity.*data < polarity*threshold);

        negative = find(polarity.*data >= polarity*threshold);

        positive(find(labels(positive) == 1)) = []; % dimiss correct samples

        negative(find(labels(negative) == -1)) = [];

        incorrects = [positive; negative];

        errorRate = sum(weights(incorrects));

        if errorRate <= bestErrorRate

            bestThreshold = threshold;

            bestPolarity = polarity;

            bestErrorRate = errorRate;

        end

    end

end

⛄ 运行结果

⛄ 参考文献

[1]董庆伟. "基于Adaboost算法的不平衡数据集分类效果研究." 长春师范大学学报 41.6(2022):4.

❤️部分理论引用网络文献，若有侵权联系博主删除

❤️ 关注我领取海量matlab电子书和数学建模资料