我对睡眠障碍的识别感兴趣，但是我尝试了睡眠阶段分类的代码，但是我进入了睡眠障碍的编码部分，并找到了诸如能量，准确性，MSE，标准差，方差之类的参数。 所以，请帮我编码
function varargout = EEG_Application_Sleep(varargin)
% EEG_APPLICATION_SLEEP MATLAB code for EEG_Application_Sleep.fig
% EEG_APPLICATION_SLEEP, by itself, creates a new EEG_APPLICATION_SLEEP or raises the existing
% singleton*.
%
% H = EEG_APPLICATION_SLEEP returns the handle to a new EEG_APPLICATION_SLEEP or the handle to
% the existing singleton*.
%
% EEG_APPLICATION_SLEEP('CALLBACK',hObject,eventData,handles,...) calls the local
% function named CALLBACK in EEG_APPLICATION_SLEEP.M with the given input arguments.
%
% EEG_APPLICATION_SLEEP('Property','Value',...) creates a new EEG_APPLICATION_SLEEP or raises the
% existing singleton*. Starting from the left, property value pairs are
% applied to the GUI before EEG_Application_Sleep_OpeningFcn gets called. An
% unrecognized property name or invalid value makes property application
% stop. All inputs are passed to EEG_Application_Sleep_OpeningFcn via varargin.
%
% *See GUI Options on GUIDE's Tools menu. Choose "GUI allows only one
% instance to run (singleton)".
%
% See also: GUIDE, GUIDATA, GUIHANDLES
% Edit the above text to modify the response to help EEG_Application_Sleep
% Last Modified by GUIDE v2.5 22-Apr-2019 00:38:09
% Begin initialization code - DO NOT EDIT
gui_Singleton = 1;
gui_State = struct('gui_Name', mfilename, ...
'gui_Singleton', gui_Singleton, ...
'gui_OpeningFcn', @EEG_Application_Sleep_OpeningFcn, ...
'gui_OutputFcn', @EEG_Application_Sleep_OutputFcn, ...
'gui_LayoutFcn', [] , ...
'gui_Callback', []);
if nargin && ischar(varargin{1})
gui_State.gui_Callback = str2func(varargin{1});
end
if nargout
[varargout{1:nargout}] = gui_mainfcn(gui_State, varargin{:});
else
gui_mainfcn(gui_State, varargin{:});
end
% End initialization code - DO NOT EDIT
% --- Executes just before EEG_Application_Sleep is made visible.
function EEG_Application_Sleep_OpeningFcn(hObject, ~, handles, varargin)
% This function has no output args, see OutputFcn.
% hObject handle to figure
% eventdata reserved - to be defined in a future version of MATLAB
% handles structure with handles and user data (see GUIDATA)
% varargin command line arguments to EEG_Application_Sleep (see VARARGIN)
handles.output = hObject;
ah=axes('unit','normalized','position',[0 0 1 1]);
bg=imread('EEG-Brain1.jpg'); imagesc(bg);
set(ah,'handlevisibility','off','visible','off');
uistack(ah,'bottom');
handles.output = hObject;
% Choose default command line output for EEG_Signal_Processing_Analysis
handles.output = hObject;
% Update handles structure
guidata(hObject, handles);
% UIWAIT makes EEG_Application_Sleep wait for user response (see UIRESUME)
% uiwait(handles.figure1);
% --- Outputs from this function are returned to the command line.
function varargout = EEG_Application_Sleep_OutputFcn(~, ~, handles)
% varargout cell array for returning output args (see VARARGOUT);
% hObject handle to figure
% eventdata reserved - to be defined in a future version of MATLAB
% handles structure with handles and user data (see GUIDATA)
% Get default command line output from handles structure
varargout{1} = handles.output;
% --- Executes on button press in pushbutton1.
function pushbutton1_Callback(hObject, ~, handles)
% hObject handle to pushbutton1 (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles structure with handles and user data (see GUIDATA)
load('Features_8.mat')
load('Features_7.mat')
load('Features_6.mat')
load('Features_5.mat')
load('Features_4.mat')
load('Features_3.mat')
load('Features_2.mat')
load('Features_1.mat')
trainData=[feaures_S1; ...
feaures_S2; ...
feaures_S3; ...
feaures_S4; ...
feaures_S5; ...
feaures_S6; ...
feaures_S7; ...
feaures_S8];
class=[1 2 2 1 2 1 2 2];
SVMStruct = svmtrain (trainData, class);
originalFolder = pwd;
[baseFileName, folder] = uigetfile('*.*', 'Specify an image file');
fullImageFileName = fullfile(folder, baseFileName);
% Read in image into an array.
% [rgbImage storedColorMap] = imread(fullImageFileName);
%% Import the data
[~, ~, raw] = xlsread(fullImageFileName,'Sheet1');
% [~, ~, raw] = xlsread('C:\Users\SEM\OneDrive\Projects\2018\MATLAB\Oxford_excel\project_cancer\HCC cancerous 1551nm.ods','Sheet1','B1:C1551');
%% Create output variable
data = reshape([raw{:}],size(raw));
% figure,plot(data)
%% Allocate imported array to column variable names
% VarName2 = data(:,1);
% VarName3 = data(:,2);
%% Clear temporary variables
% clearvars data raw;
% subplot(2,1,1)
% plot(data(:,2))
% subplot(2,1,2)
% plot(data(:,1))
% load eegdata.mat;
% s=eegdata;
% s=LeftBackward3(:,1);
s=data;
s=s(1:3000);
figure,plot(s);title('Input signal');
%band pass filtering
y = bpfilt(s,0.2,60,500);
eeg=y;
f_s=500;
N=length(eeg);
t=[0:N-1]/f_s; %time period(total sample/Fs )
% figure
% plot(t,eeg); title('Raw ECG Data plotting ')
% xlabel('time')
% ylabel('amplitude')
w=50/(500/2);
bw=w;
[num,den]=iirnotch(w,bw); % notch filter implementation
eeg_notch=filter(num,den,eeg);
% figure,
N1=length(eeg_notch);
t1=[0:N1-1]/f_s;
figure; subplot(2,1,1); plot(eeg);
title('Notch filter input ')
subplot(2,1,2);plot(eeg_notch)
title('Notch filter output ')
N=length(eeg_notch);
% wavlet_dec_fun_a( ecg_notch,N )
waveletFunction = 'db8';
[C,L] = wavedec(eeg_notch,8,waveletFunction);
cD1 = detcoef(C,L,1);
cD2 = detcoef(C,L,2);
cD3 = detcoef(C,L,3);
cD4 = detcoef(C,L,4);
cD5 = detcoef(C,L,5);
cD6 = detcoef(C,L,6);
cD7 = detcoef(C,L,7);
cD8 = detcoef(C,L,8);
cA8 = appcoef(C,L,waveletFunction,8);
D1 = wrcoef('d',C,L,waveletFunction,1);
D2 = wrcoef('d',C,L,waveletFunction,2);
D3 = wrcoef('d',C,L,waveletFunction,3);
D4 = wrcoef('d',C,L,waveletFunction,4);
D5 = wrcoef('d',C,L,waveletFunction,5);
D6 = wrcoef('d',C,L,waveletFunction,6);
D7 = wrcoef('d',C,L,waveletFunction,7);
D8 = wrcoef('d',C,L,waveletFunction,8);
A8 = wrcoef('a',C,L,waveletFunction,8);
% axes(handles.axes3);plot(D5);title('GAMMA');
figure; subplot(5,1,3); plot(D5);title('GAMMA');
% axes(handles.axes4);plot(D6);title('BETA');
subplot(5,1,2); plot(D6);title('BETA');
% axes(handles.axes5);plot(D7);title('ALPHA');
subplot(5,1,1); plot(D7);title('ALPHA');
D8 = detrend(D8,0);
% axes(handles.axes6);plot(D8);title('THETA');
subplot(5,1,4); plot(D8);title('THETA');
Gamma = D5;
Beta = D6;
Alpha = D7;
Theta = D8;
Delta = A8;
% c=xlsread('data ep3');
% plot(c)
% ts=2;
% fs=500;
% [N,nu]=size(c);
% t=(1:N)*ts;
% h=figure
% plot(t,c,'r');
% title('eeg data');
%
% y=fft(c);
% ps1=abs(y).^2;
% freq=(1:N)*fs/N;
% h2=figure
% plot (freq,20*log(ps1),'b')
% title ('power spectrum using fft method')
%
% waveletFunction = 'db8';
% [C,L] = wavedec(c,8,waveletFunction);
%
% cD1 = detcoef(C,L,1);
% cD2 = detcoef(C,L,2);
% cD3 = detcoef(C,L,3);
% cD4 = detcoef(C,L,4);
% cD5 = detcoef(C,L,5); %GAMA
% cD6 = detcoef(C,L,6); %BETA
% cD7 = detcoef(C,L,7); %ALPHA
% cD8 = detcoef(C,L,8); %THETA
% cA8 = appcoef(C,L,waveletFunction,8); %DELTA
% D1 = wrcoef('d',C,L,waveletFunction,1);
% D2 = wrcoef('d',C,L,waveletFunction,2);
% D3 = wrcoef('d',C,L,waveletFunction,3);
% D4 = wrcoef('d',C,L,waveletFunction,4);
% D5 = wrcoef('d',C,L,waveletFunction,5); %GAMMA
% D6 = wrcoef('d',C,L,waveletFunction,6); %BETA
% D7 = wrcoef('d',C,L,waveletFunction,7); %ALPHA
% D8 = wrcoef('d',C,L,waveletFunction,8); %THETA
% A8 = wrcoef('a',C,L,waveletFunction,8); %DELTA
%
% Gamma = cD5;
% figure; subplot(5,1,3); plot(1:1:length(Gamma),Gamma);title('GAMMA');
%
% Beta = cD6;
% subplot(5,1,2); plot(1:1:length(Beta), Beta); title('BETA');
%
%
% Alpha = cD7;
% subplot(5,1,1); plot(1:1:length(Alpha),Alpha); title('ALPHA');
%
%
% Theta = cD8;
% subplot(5,1,4); plot(1:1:length(Theta),Theta);title('THETA');
%
%
% Delta = cA8;
% subplot(5,1,5);plot(1:1:length(Delta),Delta);title('DELTA');
% fprintf('energy of gamma')
% SIGNALENERGY1=sum(abs(D5).^2)
% fprintf('energy of beta')
% SIGNALENERGY2=sum(abs(D6).^2)
% fprintf('energy of alpha')
% SIGNALENERGY3=sum(abs(D7).^2);
% fprintf('energy of theta')
% SIGNALENERGY4=sum(abs(D8).^2)
% fprintf('energy of delta')
% SIGNALENERGY5=sum(abs(A8).^2)
%
% el3=[SIGNALENERGY1;SIGNALENERGY2;SIGNALENERGY3;SIGNALENERGY4;SIGNALENERGY5]
% axes(handles.axes7);plot(A8);title('Delta');
subplot(5,1,5); plot(A8);title('Delta');
D5 = detrend(D5,0);
xdft = fft(D5);
freq = 0:N/length(D5):N/2;
xdft = xdft(1:length(D5)/2+1);
% axes(handles.axes8);plot(freq,abs(xdft));title('GAMMA-FREQUENCY');
figure;subplot(513);plot(freq,abs(xdft));title('GAMMA-FREQUENCY');
[~,I] = max(abs(xdft));
fprintf('Gamma:Maximum occurs at %3.2f Hz.\n',freq(I));
set(handles.text7, 'String', freq(I));
D6 = detrend(D6,0);
xdft2 = fft(D6);
freq2 = 0:N/length(D6):N/2;
xdft2 = xdft2(1:length(D6)/2+1);
% axes(handles.axes9);plot(freq2,abs(xdft2));title('BETA');
subplot(512);plot(freq,abs(xdft2));title('BETA');
[~,I] = max(abs(xdft2));
fprintf('Beta:Maximum occurs at %3.2f Hz.\n',freq2(I));
set(handles.text8, 'String', freq2(I));
D7 = detrend(D7,0);
xdft3 = fft(D7);
freq3 = 0:N/length(D7):N/2;
xdft3 = xdft3(1:length(D7)/2+1);
[~,I] = max(abs(xdft3));
fprintf('Alpha:Maximum occurs at %f Hz.\n',freq3(I));
set(handles.text9, 'String', freq3(I));
% axes(handles.axes10);plot(freq3,abs(xdft3));title('ALPHA');
subplot(511);plot(freq,abs(xdft3));title('ALPHA');
xdft4 = fft(D8);
freq4 = 0:N/length(D8):N/2;
xdft4 = xdft4(1:length(D8)/2+1);
% axes(handles.axes11);plot(freq4,abs(xdft4));title('THETA');
subplot(514);plot(freq,abs(xdft4));title('THETA');
[~,I] = max(abs(xdft4));
fprintf('Theta:Maximum occurs at %f Hz.\n',freq4(I));
set(handles.text10, 'String', freq4(I));
A8 = detrend(A8,0);
xdft5 = fft(A8);
freq5 = 0:N/length(A8):N/2;
xdft5 = xdft5(1:length(A8)/2+1);
% axes(handles.axes12);plot(freq4,abs(xdft5));title('DELTA');
subplot(515);plot(freq,abs(xdft5));title('DELTA');
[~,I] = max(abs(xdft5));
fprintf('Delta:Maximum occurs at %f Hz.\n',freq5(I));
set(handles.text11, 'String', freq5(I));
Alpha = D7;
Theta = D8;
Delta = A8;
pw_A = pwelch(Alpha); SA = std(pw_A); vA=var(pw_A);
pw_B = pwelch(Beta); SB = std(pw_B); vB=var(pw_B);
pw_G = pwelch(Gamma); SG = std(pw_G); vG=var(pw_G);
pw_T = pwelch(Theta); ST = std(pw_T); vT=var(pw_T);
pw_D = pwelch(Delta); SD = std(pw_D); vD=var(pw_D);
% Right forward train 1-channel5
% features_mat1_RF1_5=[SG SB SA ST SD];
% features_mat2_RF1_5=[vG vB vA vT vD];
features_mat1_RB1_5=[SG SB SA ST SD];
% features_mat2_RB1_5=[vG vB vA vT vD];
feaures_S= [SG SB SA ST SD];
feaures_V = [vG vB vA vT vD];
feaures_S_param=feaures_S*10^8;
feaures_V_param=feaures_V*10^12;
% max(data)
% Type_S = predict(mdS,feaures_S)
% Type_V = predict(mdV,feaures_V)
xx=25;
process_dll
input_data= feaures_S;
result = svmclassify(SVMStruct, feaures_S);
temp_H=ones(100,100,'uint8')*255;
temp_L=ones(100,100,'uint8')*0;
gimg(:,:,1)=temp_L;
gimg(:,:,2)=temp_H;
gimg(:,:,3)=temp_L;
rimg(:,:,1)=temp_H;
rimg(:,:,2)=temp_L;
rimg(:,:,3)=temp_L;
bimg(:,:,1)=temp_L;
bimg(:,:,2)=temp_L;
bimg(:,:,3)=temp_H;
% disp('feature v')
feaures_V_param(1,1);
if(feaures_V_param(1,1)>1.204 && feaures_V_param(1,1)<1.3046)
axes(handles.axes1)
imshow(gimg)
pause(0.25)
axes(handles.axes1)
imshow(ones)
pause(0.25)
axes(handles.axes1)
imshow(gimg)
pause(0.25)
axes(handles.axes1)
imshow(ones)
pause(0.25)
axes(handles.axes1)
imshow(gimg)
pause(0.25)
axes(handles.axes1)
imshow(ones)
axes(handles.axes1)
imshow(gimg)
disp('normal ');
set(handles.text1, 'String', 'normal ');
voice_play('normal ');
else
if(result==1)
axes(handles.axes1)
imshow(rimg)
pause(0.25)
axes(handles.axes1)
imshow(ones)
pause(0.25)
axes(handles.axes1)
imshow(rimg)
pause(0.25)
axes(handles.axes1)
imshow(ones)
pause(0.25)
axes(handles.axes1)
imshow(rimg)
pause(0.25)
axes(handles.axes1)
imshow(ones)
axes(handles.axes1)
imshow(rimg)
disp('stage1');
set(handles.text1, 'String', 'stage1');
voice_play('stage1');
else
axes(handles.axes1)
imshow(bimg)
pause(0.25)
axes(handles.axes1)
imshow(ones)
pause(0.25)
axes(handles.axes1)
imshow(bimg)
pause(0.25)
axes(handles.axes1)
imshow(bimg)
pause(0.25)
axes(handles.axes1)
imshow(bimg)
pause(0.25)
axes(handles.axes1)
imshow(ones)
axes(handles.axes1)
imshow(bimg)
disp('stage2');
set(handles.text1, 'String', 'stage2');
voice_play('stage2');
end
end
% Choose default command line output for EEG_Application_Sleep
handles.output = hObject;
% Update handles structure
guidata(hObject, handles);
% --- Executes on mouse press over axes background.
% --- Executes when figure1 is resized.
% function figure1_ResizeFcn(hObject, eventdata, handles)
% % hObject handle to figure1 (see GCBO)
% % eventdata reserved - to be defined in a future version of MATLAB
% % handles structure with handles and user data (see GUIDATA)
%
%
% % --------------------------------------------------------------------
% function Untitled_1_Callback(hObject, eventdata, handles)
% % hObject handle to Untitled_1 (see GCBO)
% % eventdata reserved - to be defined in a future version of MATLAB
% % handles structure with handles and user data (see GUIDATA)
% --- Executes during object creation, after setting all properties.
% hObject handle to axes3 (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles empty - handles not created until after all CreateFcns called
% Hint: place code in OpeningFcn to populate axes3
% --- Executes during object deletion, before destroying properties.
% hObject handle to figure1 (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles structure with handles and user data (see GUIDATA)
% --- Executes during object deletion, before destroying properties.
% hObject handle to figure1 (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles struc
具有句柄和用户数据的实体（请参阅GUIDATA）