# Classification-of-Pitch-Imagery-from-EEG
This project is based on classification of audio electroencephalogram (EEG) data for 3 pitches: C4, D4, E4. Classification was done using Extreme Learning Machine Model in Matlab.
The data available was preprocessed according to the following description:
1. Original EEG raw data, 32 channels, .edf format, 5 subjects, 3 pitches.
2. Pre-processed data ran on EEGLab, extension from Matlab on the following process, saved in .set & .txt formats:
- Retain of channels for auditory imagery: F7, F8, AF3, AF4
- Retain of channels for auditory perception: T7, T8, TP7, TP8
- Passband filter to remove noise: 0.1-100Hz
- Notch Filter: 60Hz
- Epoch Extraction at time -0.25 to 1.5 seconds
- Baseline Removal [-252 0]
- Artifact Removal using ICA
- Alpha band IIR filter (8 - 15Hz)
- Automatic Epoch Rejection of Voltage over 100uV
## Approach for Data preprocessing and extraction:
.edf files for each pitch, c4,d4,e4 was respectively put into seperate folders and all converted to .mat files using the code file attached ‘readedf.m’. Usage:
```
[header, data] = readedf('filename.edf');
```
These mat files were then loaded into matlab and data for ⅘ subjects were concatenated and labelled for training dataset.
Labels are such as C4 => 0, D4 => 1, E4 =>2. The data for 8/32 channels was then extracted for channels of auditory imagery: F7, F8, AF3, AF4 and Auditory perception: T7, T8, TP7, TP8.
```
d = filepath;
ff = what(d);
con=[];
for j =1:length(ff.mat)
fname = strcat(d, ff.mat{j});
M=load(fname);
temp=M.data;
%for concatenating individual files
con=[con, temp];
%for concatenating sets
%con=vertcat(con, temp);
end
con = con'; %comment it out for concatenating sets
```
These files were all combined together to make the final training dataset attached as ‘Training_dataset.mat’. Rest of the ⅕ subject’s data was concatenated, labelled and extracted on 8 channels successively and put into ‘Test_dataset.mat’.
```
%labelling
data = load(filepath);
label = 2;
data = (data.data)';
[r,c]= size(data);
z = label.* ones(r,1);
data=horzcat(z,data);
```
Each dataset has the structure of labels in column 1 and data points of 8 channels in next 8 columns. Data of each subject is concatenated vertically.
## Training and testing of model:
ELM implementation of Mathworks was utilized and modified for our problem. The code files are available in the EA_SRC.zip along with the datasets. The code file ‘Demo_Classification.m’ takes our training and test datasets to perform classification on the ELM and Regularized ELM.
```
load('Training_dataset.mat'); %loading Training_dataset
con = con'; %transpose of dataset into column vectors
trainlabel=con(1,:); %extract labels from first column
traindata=con(2:9,:); %extract data values from rest
```
```
load('Test_dataset.mat'); %same as above steps for test dataset
con = con';
testlabel=con(1,:);
testdata=con(2:9,:);
```
**ELM and RELM was performed using an Neural network trained on our labels.**
```
method = {'ELM','RELM'};
nn.hiddensize = 200; %number of hidden neurons
nn.activefunction = 's'; %sigmoid
nn.inputsize = size(traindata,1);
nn.method = method{1}; %pick ELM or RELM
nn.type = 'classification';
```
## Improvements:
The results can be improved by:
- Increasing the number of hidden layers on the neural networks. Currently it uses 200 layers.
- Using a larger training dataset. This dataset was of only 4 subjects (approx. #50000) reduced to 8 channels and 5th subject was used as test data. The results can be much better with a larger dataset.
- Using a deep convolutional network for multi label classification.
没有合适的资源?快使用搜索试试~ 我知道了~
【信号识别-脑电分类】基于EASRC和ELM算法实现音频脑电图 (EEG) 数据分类附matlab代码.zip
![preview](https://csdnimg.cn/release/downloadcmsfe/public/img/white-bg.ca8570fa.png)
共27个文件
m:17个
mat:5个
png:3个
![preview-icon](https://csdnimg.cn/release/downloadcmsfe/public/img/scale.ab9e0183.png)
1.该资源内容由用户上传,如若侵权请联系客服进行举报
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
版权申诉
0 下载量 105 浏览量
2023-04-13
12:08:03
上传
评论 1
收藏 9.31MB ZIP 举报
温馨提示
1.版本:matlab2014/2019a,内含运行结果,不会运行可私信 2.领域:智能优化算法、神经网络预测、信号处理、元胞自动机、图像处理、路径规划、无人机等多种领域的Matlab仿真,更多内容可点击博主头像 3.内容:标题所示,对于介绍可点击主页搜索博客 4.适合人群:本科,硕士等教研学习使用 5.博客介绍: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si信
资源推荐
资源详情
资源评论
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![rar](https://img-home.csdnimg.cn/images/20210720083606.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
收起资源包目录
![package](https://csdnimg.cn/release/downloadcmsfe/public/img/package.f3fc750b.png)
![folder](https://csdnimg.cn/release/downloadcmsfe/public/img/folder.005fa2e5.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/TXT.png)
![folder](https://csdnimg.cn/release/downloadcmsfe/public/img/folder.005fa2e5.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![folder](https://csdnimg.cn/release/downloadcmsfe/public/img/folder.005fa2e5.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![folder](https://csdnimg.cn/release/downloadcmsfe/public/img/folder.005fa2e5.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![folder](https://csdnimg.cn/release/downloadcmsfe/public/img/folder.005fa2e5.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![folder](https://csdnimg.cn/release/downloadcmsfe/public/img/folder.005fa2e5.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
共 27 条
- 1
资源评论
![avatar-default](https://csdnimg.cn/release/downloadcmsfe/public/img/lazyLogo2.1882d7f4.png)
![avatar](https://profile-avatar.csdnimg.cn/0952dabfe4084a058a29f6b3884c6064_qq_59747472.jpg!1)
![avatar-vip](https://csdnimg.cn/release/downloadcmsfe/public/img/user-vip.1c89f3c5.png)
天天Matlab科研工作室
- 粉丝: 3w+
- 资源: 7251
上传资源 快速赚钱
我的内容管理 展开
我的资源 快来上传第一个资源
我的收益
登录查看自己的收益我的积分 登录查看自己的积分
我的C币 登录后查看C币余额
我的收藏
我的下载
下载帮助
![voice](https://csdnimg.cn/release/downloadcmsfe/public/img/voice.245cc511.png)
![center-task](https://csdnimg.cn/release/downloadcmsfe/public/img/center-task.c2eda91a.png)
最新资源
- 电气类117、变电站真实巡检电力设备检测数据集(7500多张+15类+YOLO格式txt标签)-第二部分
- 电气类、117.变电站真实巡检电力设备检测数据集(7500多张+15类+YOLO格式txt标签)-第一部分
- IMG_20180720_124347_01.jpg
- IMG20240621095811.jpg
- jQuery 库.docx
- 基于 C 实现的图像处理(BMP)课程设计
- ST MCSDK 6.3.0
- 基于 C++实现的虚拟航班订票系统【C++课程设计】
- 111111111111111111
- 海信智能电视刷机数据 LED43K5100U(0000) 生产用软件数据 务必确认机编一致 强制刷机 整机USB升级程序
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
![feedback](https://img-home.csdnimg.cn/images/20220527035711.png)
![feedback](https://img-home.csdnimg.cn/images/20220527035711.png)
![feedback-tip](https://img-home.csdnimg.cn/images/20220527035111.png)
安全验证
文档复制为VIP权益,开通VIP直接复制
![dialog-icon](https://csdnimg.cn/release/downloadcmsfe/public/img/green-success.6a4acb44.png)