Bat算法前馈神经网络（BA-FFNN）分类器MATLAB.zip资源-CSDN文库

共11个文件

jpg：9个

png：1个

pdf：1个

版权申诉

matlab

137 浏览量 2024-04-19 22:27:03 上传评论收藏 778KB ZIP 举报

资源推荐

资源详情

资源评论

收起资源包目录

Bat算法前馈神经网络（BA-FFNN）分类器MATLAB.zip （11个子文件）

Bat算法前馈神经网络（BA-FFNN）分类器MATLAB

GUI 1.jpg 54KB

Result 1.jpg 34KB

Before and After Pre-processing.png 352KB

GUI 3.jpg 38KB

BA-FFNN-classifier-for-classification-of-deep-features-in-DBT-CAD-system-main

Segmented ROIs.jpg 58KB

Result 4.jpg 32KB

GUI 2.jpg 43KB

Parameter and Object Space Function.jpg 52KB

Result 3.jpg 36KB

Implementation Codes.pdf 104KB

Result 2.jpg 33KB

Code for Training

% global filecount feat_train;

datapath=uigetdir('C:\','select path of Image Folder');% if you what to select in run time use this

command imageformat= 'jpg';

files = dir([datapath '/' '*.' imageformat]);

filecount=size({files.name},2); % Total no of image files in that folder

filenames={files.name};% all file names taken into a variable

%now to extract features file by file for

i=1:filecount

f=fullfile(datapath,char(filenames(i)));

breastRGB=imread(f); a =

size(breastRGB, 1); b =

size(breastRGB, 2);

breastRGB = imresize(breastRGB, sqrt(256 * 256 / (a * b)));

%histogram equalization

hist = histeq(breastRGB);

% active contour segmentation

% num_iter = 300; %

mu = 0.02;

seg = activeContour(hist,'whole',800,0.02,'vector'); im

= 255* repmat(uint8(seg),1,1,3);

output_folder = 'C:\Users\TOPE\Desktop\BREAST CANCER DETECTION\testFolder\eight.mat';

Output File Name = fullfile(output_folder,['seg' num2str(i) '.jpg']);

imwrite(im,outputFileName); toc end imds =

imageDatastore('segmented_images',...

'IncludeSubfolders',true,...

'LabelSource','foldernames');

% [imdsTrain,imdsTest] = splitEachLabel(imds,0.7,'randomized'); net

= alexnet;

inputSize = net.Layers(1).InputSize;

augimdsTrain = augmentedImageDatastore(inputSize(1:2),imds); %

augimdsTest = augmentedImageDatastore(inputSize(1:2),imdsTest);

layer = 'fc7';

featuresTrain = activations(net,augimdsTrain,layer,'OutputAs','rows');

% featuresTest = activations(net,augimdsTest,layer,'OutputAs','rows');

% [imdsTrain,imdsTest] = splitEachLabel(imds,0.7,'randomized'); net =

alexnet;

inputSize = net.Layers(1).InputSize;

augimdsTrain = augmentedImageDatastore(inputSize(1:2),imds); %

augimdsTest = augmentedImageDatastore(inputSize(1:2),imdsTest);

layer = 'fc7';

featuresTrain = activations(net,augimdsTrain,layer,'OutputAs','rows'); %

featuresTest = activations(net,augimdsTest,layer,'OutputAs','rows');

% [imdsTrain,imdsTest] = splitEachLabel(imds,0.7,'randomized'); net

= alexnet;

inputSize = net.Layers(1).InputSize;

augimdsTrain = augmentedImageDatastore(inputSize(1:2),imds); %

augimdsTest = augmentedImageDatastore(inputSize(1:2),imdsTest);

layer = 'fc7';

featuresTrain = activations(net,augimdsTrain,layer,'OutputAs','rows'); %

featuresTest = activations(net,augimdsTest,layer,'OutputAs','rows');

% YTrain = imdsTrain.Labels; %

YTest = imdsTest.Labels;

save('featuresTrain.mat','featuresTrain') %

save('featuresTest.mat','featuresTest') end

Code for Testing

% 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 gui (see VARARGIN)

% Choose default command line output for gui

handles.output = hObject; % Update handles

structure guidata(hObject, handles);

% UIWAIT makes gui wait for user response (see UIRESUME)

% uiwait(handles.figure1);

% --- Outputs from this function are returned to the command line. varargout{1}

= handles.output;

% --- Executes on button press in pushbutton5. function

pushbutton5_Callback(hObject, eventdata, handles)

% hObject handle to pushbutton5 (see GCBO)

% eventdata reserved - to be defined in a future version of MATLAB %

handles structure with handles and user data (see GUIDATA) global

feat

[filename, pathname] = uigetfile({'*.*';'*.bmp';'*.jpg';'*.gif'}, 'Browse DBT Test Image');

I = imread([pathname,filename]);

axes(handles.axes1) imshow(I)

if (filename == '1.jpg')

load('C:\Users\TOPE\Desktop\BREAST CANCER DETECTION\testFolder\one.mat')

testFeat = one elseif(filename == '2.jpg')

load('C:\Users\TOPE\Desktop\BREAST CANCER DETECTION\testFolder\two.mat')

testFeat = two elseif(filename == '3.jpg')

load('C:\Users\TOPE\Desktop\BREAST CANCER DETECTION\testFolder\three.mat')

testFeat = three elseif(filename == '4.jpg')

load('C:\Users\TOPE\Desktop\BREAST CANCER DETECTION\testFolder\four.mat')

testFeat = four elseif(filename == '5.jpg')

load('C:\Users\TOPE\Desktop\BREAST CANCER DETECTION\testFolder\five.mat')

testFeat = five elseif(filename == '6.jpg')

load('C:\Users\TOPE\Desktop\BREAST CANCER DETECTION\testFolder\six.mat')

testFeat = six elseif(filename == '7.jpg')

load('C:\Users\TOPE\Desktop\BREAST CANCER DETECTION\testFolder\seven.mat')

testFeat = seven elseif(filename == '8.jpg')

load('C:\Users\TOPE\Desktop\BREAST CANCER DETECTION\testFolder\eight.mat')

testFeat = eight elseif(filename == '9.jpg')

load('C:\Users\TOPE\Desktop\BREAST CANCER DETECTION\testFolder\nine.mat')

testFeat = nine elseif(filename == 'M.jpg')

load('C:\Users\TOPE\Desktop\BREAST CANCER DETECTION\testFolder\ten.mat')

testFeat = ten elseif(filename == 'N.jpg')

load('C:\Users\TOPE\Desktop\BREAST CANCER DETECTION\testFolder\eleven.mat')

testFeat = eleven elseif(filename == 'P.jpg')

load('C:\Users\TOPE\Desktop\BREAST CANCER DETECTION\testFolder\twelve.mat')

testFeat = twelve elseif(filename == 'Q.jpg')

load('C:\Users\TOPE\Desktop\BREAST CANCER DETECTION\testFolder\thirteen.mat')

testFeat = thirteen elseif(filename == 'R.jpg')

load('C:\Users\TOPE\Desktop\BREAST CANCER DETECTION\testFolder\fourteen.mat')

testFeat = fourteen elseif(filename == 'S.jpg')

load('C:\Users\TOPE\Desktop\BREAST CANCER DETECTION\testFolder\fiveteen.mat')

testFeat = fiveteen

end

% feat = testFeat;

load net1 test =

testFeat; res =

sim(net1,test'); [c,d]

= max(res); if (d==2)

set(handles.text3,'string','NORMAL')

elseif (d==1)

set(handles.text3,'string','ABNORMAL')

% clear all load

net res =

sim(net,test'); [a,b]

= max(res); if (b==1)

set(handles.text5,'string','BENIGN')

elseif (b==2)

set(handles.text5,'string','MALIGNANT')

end else

set(handles.text5,'string','NAN')

end

% --- Executes on button press in pushbutton4.

function pushbutton4_Callback(hObject, eventdata, handles)

dbtImage = getimage(handles.axes1);

% clear all load

net1 test = feat;

res = sim(net1,test);

[c,d] = max(res); if

(d==1)

set(handles.text3,'string','NORMAL')

elseif (d==2)

set(handles.text3,'string','ABNORMAL')

clear all load net res =

sim(net,test); [a,b] = max(res);

if (b==1)

set(handles.text5,'string','BENIGN')

elseif (b==2)

set(handles.text5,'string','MALIGNANT')

end end

% --- Executes on button press in pushbutton1. function

pushbutton1_Callback(hObject, eventdata, 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 featuresTrain load featuresAll

% --- Executes on button press in pushbutton3. function

pushbutton3_Callback(hObject, eventdata, handles)

% hObject handle to pushbutton3 (see GCBO)

% eventdata reserved - to be defined in a future version of MATLAB %

handles structure with handles and user data (see GUIDATA) normabn

% --- Executes on button press in pushbutton6. function

pushbutton6_Callback(hObject, eventdata, handles)

% hObject handle to pushbutton6 (see GCBO)

% eventdata reserved - to be defined in a future version of MATLAB

% handles structure with handles and user data (see GUIDATA)

set(handles.text3,'string','') set(handles.text5,'string','') clear

all %

Code for Segmentation (3D Active Contour)

%-- Default settings

% length term mu = 0.2 and default method = 'chan'

if(~exist('mu','var')) mu=0.2; end

if(~exist('method','var'))

method = 'chan'; end

%-- End default settings

%-- Initializations on input image I and mask

% resize original image

s = 200./min(size(I,1),size(I,2)); % resize scale

if s<1

I = imresize(I,s);

end

% auto mask settings

if ischar(mask)

switch lower (mask)

case 'small'

mask = maskcircle2(I,'small');

case 'medium'

mask = maskcircle2(I,'medium');

case 'large'

mask = maskcircle2(I,'large');

case 'whole'

mask = maskcircle2(I,'whole');

%mask = init_mask(I,30); case

'whole+small' m1 =

maskcircle2(I,'whole'); m2 =

maskcircle2(I,'small'); mask =

zeros(size(I,1),size(I,2),2);

mask(:,:,1) = m1(:,:,1); mask(:,:,2)

= m2(:,:,2); otherwise

error('unrecognized mask shape name (MASK).');

end else if s<1

mask = imresize(mask,s);

end

if size(mask,1)>size(I,1) || size(mask,2)>size(I,2)

error('dimensions of mask unmathch those of the image.') end

switch lower(method) case 'multiphase' if

(size(mask,3) == 1)

error('multiphase requires two masks but only gets one.')

end end end

switch lower(method) case

'chan' if size(I,3)== 3

P = rgb2gray(uint8(I));

P = double(P); elseif

size(I,3) == 2

P = 0.5.*(double(I(:,:,1))+double(I(:,:,2)));

else

P = double(I);

end

layer = 1;

case

'vector'

s = 200./min(size(I,1),size(I,2)); % resize scale

I = imresize(I,s); mask = imresize(mask,s);

layer = size(I,3); if layer == 1

display('only one image component for vector image')

end

P = double(I);

评论收藏

内容反馈

版权申诉

Matlab科研辅导帮

粉丝: 2w+
资源: 7664

Bat算法前馈神经网络（BA-FFNN）分类器MATLAB.zip

基于灰狼算法优化前馈神经网络实现数据分类附matlab代码.zip

【FNN回归预测】基于matlab蝙蝠算法优化前馈神经网络BA-FNN数据回归预测【含Matlab源码 2070期】

matlab神经网络和优化算法：58 使用前馈神经网络预测样本数据.zip

神经网络第4讲 前馈神经网络-BP神经网络.doc

神经网络第3讲 前馈神经网络-感知器.doc

精通前馈神经网络和线性神经网络通过matlab建模案例.zip

自定义数据集+标准前馈神经网络分类进行训练-python源码.zip

MATLAB-21 人工神经网络.zip_gentle1oq_trainddo_神经网络 matlab

matlab神经网络案例;7专题 精通前馈神经网络和线性神经网络通过matlab建模案例.zip

7专题 精通前馈神经网络和线性神经网络通过matlab建模案例.zip

网络游戏-基于凸组合算法优化前馈神经网络观测器的故障诊断方法.zip

matlab神经网络和优化算法：58使用前馈神经网络预测样本数据.zip

PID算法详解（包含很多PID文章和学习经验）

Matlab 基于支持向量机(SVM)的数据回归预测 SVM回归

LSTM时间序列神经网络预测MATLAB代码

Matlab 基于BP神经网络的数据分类预测 BP分类

ADRC控制器仿真 simulink 2017a版本

matlab2020b ubuntu.txt

2022建模国赛代码(三天坚持不易) 包括K-meas算法、bp预测、回归预测,(python和matlab做的).zip

基于蚁群算法的三维路径规划(matlab实现)

信号分选SDIF序列差直方图算法matlab仿真程序

基于智能优化算法的双层优化求解(matlab代码)

调频连续波（FMCW）雷达二维FFT代码matlab

基于蚁群算法的二维路径规划(matlab实现)

美赛各题常用算法程序与参考代码.rar

MATLAB深度学习入门实例（果树病虫害识别VGG19版）

锂电池BMS的Matlab仿真模型

PID仿真实验报告（含simulink仿真文件）

【全覆盖路径规划CCPP】基于matlab A_star算法移动机器人全覆盖路径规划【含Matlab源码 3392期】.mp4

最新资源

神经网络第4讲前馈神经网络-BP神经网络.doc

神经网络第3讲前馈神经网络-感知器.doc

matlab神经网络案例;7专题精通前馈神经网络和线性神经网络通过matlab建模案例.zip

7专题精通前馈神经网络和线性神经网络通过matlab建模案例.zip