SVM支持向量机和逻辑回归进行心音信号简单二分类

来源：互联网发布：mysql 写函数编辑：程序博客网时间：2024/04/29 22:57

%%%本程序读取training-a中150个心音信号作为训练集，后150个心音信号作为测试数据，采用SVM支持向量机和逻辑回归分类器%进行心音信号的分类%%clear;clc;rng=[0 1 149 1];%训练 rng=[r1 c1 r2 c2]定义读取csv文件的行列始末段rng1=[150 1 299 1];%测试train_label=csvread('./training-a/REFERENCE.csv',0,1,rng);%读取训练标签for i=1:length(train_label)    if train_label(i)<0        train_label(i)=2;    endendtest_label=csvread('./training-a/REFERENCE.csv',150,1,rng1);%读取测试标签for i=1:length(test_label)    if test_label(i)<0        test_label(i)=2;    endendfigure();subplot(211);bar(test_label);%画出测试数据的正确分类标签%%%对原始数据进行特征提取，构建n维的训练数据矩阵，样本大小为150train_data=[];test_data=[];for i=1:9    ss=feature_extraction(strcat('./training-a/a000',num2str(i),'.wav'));    train_data=[train_data;ss];endfor i=10:99    ss=feature_extraction(strcat('./training-a/a00',num2str(i),'.wav'));    train_data=[train_data;ss];endfor i=100:150    ss=feature_extraction(strcat('./training-a/a0',num2str(i),'.wav'));    train_data=[train_data;ss];end%对原始数据进行特征提取，构建n维的测试数据矩阵for i=151:300    ss=feature_extraction(strcat('./training-a/a0',num2str(i),'.wav'));    test_data=[test_data;ss];end%%%SVM支持向量机分类器% Factor = svmtrain( train_data,train_label);% predict_label = svmclassify(Factor, test_data);% accuracy = length(find(predict_label == test_label))/length(test_label)*100;% accuracy% subplot(212);% bar(predict_label);%绘制预测矩阵与正确答案进行比较%逻辑回归Factor = mnrfit(train_data, train_label);Scores = mnrval(Factor, test_data);S1=Scores(:,1);S2=Scores(:,2);predict_label=[];for i=1:length(S1)    if S1(i)<S2(i)        predict_label=[predict_label;2];    else        predict_label=[predict_label;1];    endendsubplot(212);bar(predict_label);accuracy = length(find(predict_label == test_label))/length(test_label)*100;accuracy

分类结果：

accuracy =    76

这里写图片描述
由于只采用了150个信号做训练集，训练好的分类器只有76%的预测率，心音信号来源于https://physionet.org/physiobank/database/challenge/2016/training.zip
REFERENCE.csv形式：

特征提取函数feature_extraction采用db6小波特征提取，函数代码如下：

function [ ss ] = feature_extraction(route )% [x,fs]=audioread('./training-a/a0001.wav');[x,fs]=audioread(route);x1=x(:,1); % 抽取第 1 声道level = 4;wname ='db6';%选取小波t=wpdec(x1,level,wname,'shannon');%小波分解% plot(t);t0=wprcoef(t,[3,0]);t1=wprcoef(t,[4,2]);t2=wprcoef(t,[4,3]);t3=wprcoef(t,[3,2]);t4=wprcoef(t,[4,6]);t5=wprcoef(t,[4,7]);t6=wprcoef(t,[1,1]);%构建特征向量s0=norm(t0);s1=norm(t1);s2=norm(t2);s3=norm(t3);s4=norm(t4);s5=norm(t5);s6=norm(t6);ss=[s0,s1,s2,s3,s4,s5,s6];%得到7维的特征向量%  figure();%  bar(ss); end

1 0