OSCR

Joint MVMD-based optimal feature selection and FW-LS-TWSVM for motor imagery recognition.

Code ↔ Paper

1 match between paragraphs of the paper and lines of its authors' code, computed by the harvester (lexical-v1). Click a colored paragraph or line to see its counterpart.

The 1 match
  1. [1] § Experiments and results › Experimental Results › Comparison of different frequency band decomposition methods ↔ SH_CSP_FB_withing_session.m, lines 1–45 · score 0.84 · 12–18 Hz, 24–30 Hz, 8–12 Hz, 18–24 Hz, Fixed Bandwidth, FB

Paper

Loaded from Europe PMC by your browser, not stored by OSCR: doi.org · Europe PMC

The paper is loaded when this pane is shown.

The authors' code

MATLAB · 158 lines · 6 KB · no license · 1 match

  1. % FB means fixed bandwidth,固定频带
  2. % 初步设定为4个频带，分别为：
  3. % 8-12Hz，mu节律
  4. % 12-18Hz
  5. % 18-24Hz
  6. % 24-30Hz，后三个为beta节律的分解，以提出更多的细节特征
  8. clear,clc;
  9. % 获取所有文件名
  10. files = dir('D:\Download\pyproject\testEEGNet\Data\19228725\*.mat');
  11. low_freq = [8,12,18,24];
  12. high_freq = [12,18,24,30];
  13. acc_result = zeros(25,5);
  14. imf_num = 4;
  15. for subj = 1:25
  16. for ses =1:5
  17. fixed_bandwidth_file_name = ['D:\Download\pyproject\testEEGNet\Data\19228725\fixed_bandwidth\subj_', num2str(subj),'_sess',num2str(ses),'_decomp.mat'];
  18. % 读取当前session的数据
  19. file_name = sprintf('sub-%03d_ses-%02d_task_motorimagery_eeg.mat', subj, ses);
  20. load(fullfile('D:\Download\pyproject\testEEGNet\Data\Shanghaidata',file_name));
  21. % 截取前500个点，即前5秒的数据
  22. data_subset = data(:, :, 1:500);
  23. % 获取数据的维度
  24. data_num_dimensions=size(data_subset);
  26. if ~exist(fixed_bandwidth_file_name,'file')
  27. % 对于所有数据，进行固定频带分解操作
  29. all_decomp_data = zeros(data_num_dimensions(1),data_num_dimensions(2), data_num_dimensions(3), imf_num);
  30. result = cell(1, imf_num);
  31. for trial = 1:data_num_dimensions(1)
  32. trial_data = zeros(data_num_dimensions(2), data_num_dimensions(3), imf_num);
  33. for channel =1:data_num_dimensions(2)
  34. for i =1:4
  35. trial_data(channel,:,i)=bandpass_filter_within_range(data_subset(trial,channel,:),low_freq(i),high_freq(i),250);
  36. end
  37. end
  38. all_decomp_data(trial,:,:,:)=trial_data;
  39. if mod(trial,10)==0
  40. disp(['Subject ',num2str(subj),' Session ',num2str(ses),' trial',num2str(trial),'/',num2str(data_num_dimensions(1)),'Finished!']);
  41. end
  42. end
  43. save(fixed_bandwidth_file_name, 'all_decomp_data', 'labels');
  44. end
  45. load(fixed_bandwidth_file_name);
  47. % 存储到cell中
  48. for imf_ver = 1:imf_num
  49. result{imf_ver}=all_decomp_data(:,:,:,imf_ver);
  50. end
  52. % 计算csp协方差矩阵和特征矩阵
  53. % 最后得到的csp特征矩阵为一个1×8的cell,其中每个数据的shape为sample × 4
  54. csp_matrix_result = cell(1, imf_num);
  55. csp_feature_result = cell(1, imf_num);
  57. for i = 1:imf_num
  58. EEGSignal = struct('x',reshape(result{i},[data_num_dimensions(3),data_num_dimensions(2),data_num_dimensions(1)]),'y',labels);
  59. csp_matrix_result{i} = learnCSP(EEGSignal);
  60. csp_feature_result{i} = extractCSPFeatures(EEGSignal,csp_matrix_result{i},2);
  61. end
  63. % 获取imf_num个频带拼接起来的特征矩阵sample × imf_num*4
  64. combined_features_matrix = [];
  65. % 遍历 cell 数组的每个元素
  66. for i = 1:imf_num
  67. % 获取当前 cell 中的矩阵
  68. current_matrix = csp_feature_result{i};
  69. % 将当前矩阵与 combined_matrix 水平拼接
  70. if isempty(combined_features_matrix)
  71. combined_features_matrix = current_matrix;
  72. else
  73. combined_features_matrix = horzcat(combined_features_matrix, current_matrix);
  74. end
  75. end
  77. % 逐步回归挑选特征
  79. % [~,~,~,eval,~,~,~]=stepwisefit(combined_features_matrix, double(labels'),'display','off','inmodel',inmodel_para);
  80. [~,~,~,eval,~,~,~]=stepwisefit(combined_features_matrix, double(labels'),'display','off');
  81. final_index=find(eval);
  82. if isempty(final_index)
  83. final_index=1:(imf_num*4);
  84. end
  85. altered_combined_features_matrix = combined_features_matrix(:,final_index);
  86. csp_feature_result = altered_combined_features_matrix;
  87. X=csp_feature_result;
  88. Y=labels;
  90. % 创建 SVM 分类器
  91. SVMModel = fitcsvm(X, Y, 'KernelFunction', 'linear', 'Standardize', true);
  93. % 设置 5 折交叉验证
  94. CVSVMModel = crossval(SVMModel, 'KFold', 5);
  96. % 计算每折的预测标签
  97. predictedLabels = kfoldPredict(CVSVMModel);
  99. % 计算混淆矩阵
  100. confMat = confusionmat(Y, predictedLabels);
  102. % 提取TP, FP, FN, TN
  103. TP = confMat(2,2);
  104. FP = confMat(1,2);
  105. FN = confMat(2,1);
  106. TN = confMat(1,1);
  108. % 计算 Precision 和 Recall
  109. Precision = TP / (TP + FP);
  110. Recall = TP / (TP + FN);
  112. % 计算 F1 Score
  113. F1_score = 2 * (Precision * Recall) / (Precision + Recall);
  115. % 计算 Accuracy
  116. accuracy = (TP + TN) / (TP + TN + FP + FN);
  119. acc_result(subj,ses) = accuracy;
  120. f1_result(subj,ses) = F1_score;
  122. end
  123. end
  124. % file_name = ['SH_fixed_bandwidth_withing_session_result.xlsx'];
  125. % xlswrite(file_name,acc_result);
  126. matrix = acc_result;
  128. % 计算矩阵中所有值的平均值
  129. overallMean = mean(matrix(:));
  131. % 输出结果
  132. disp(['The overall mean of all values in the matrix is: ', num2str(overallMean)]);
  134. % 计算每行的最大值
  135. rowMaxValues = max(matrix, [], 2); % 返回每行的最大值，得到 25x1 的向量
  137. % 计算这些最大值的平均值
  138. meanOfRowMaxValues = mean(rowMaxValues);
  140. % 输出结果
  141. disp(['The mean of the maximum values of each row is: ', num2str(meanOfRowMaxValues)]);
  143. matrix = f1_result;
  145. % 计算矩阵中所有值的平均值
  146. overallMean = mean(matrix(:));
  148. % 输出结果
  149. disp(['The overall mean of all values in the matrix is: ', num2str(overallMean)]);
  151. % 计算每行的最大值
  152. rowMaxValues = max(matrix, [], 2); % 返回每行的最大值，得到 25x1 的向量
  154. % 计算这些最大值的平均值
  155. meanOfRowMaxValues = mean(rowMaxValues);
  157. % 输出结果
  158. disp(['The mean of the maximum values of each row is: ', num2str(meanOfRowMaxValues)]);

SH_CSP_FB_withing_session.m at commit 5500aa6, no license · at the source

Overview

Authors: Jun Zhi1, Qichen Zhang1, Yimin Li1, Juqin Zhang2, Peisen Liu1, Jiaofen Nan1, Yanting Li1, Duan Li1
  1. School of Electronics and Information, Zhengzhou University of Light Industry, 166 Science Avenue, Zhengzhou, 450001 Henan China
  2. Faculty of Engineering, Huanghe Science and Technology College, Zhengzhou, 450063 China
Institutions: Zhengzhou University of Light Industry (China); Huanghe Science and Technology College (China)
Journal: Scientific reports, volume 16, issue 1, article 15648
Dates: received 3 April 2025; accepted 26 March 2026; published online 1 April 2026
Type: Research article · Language: English
License: CC BY-NC-ND
Identifiers: DOI 10.1038/s41598-026-46642-3 · PMID 41922634 · PMCID PMC13187188 · OpenAlex W7147657485
Open access: gold, a free copy (OpenAlex)
Status: code verified
Categories: EEG (modality), human (organism)
Methods: Statistics, Machine learning, Connectivity
Keywords: Motor imagery, EEG, Brain computer interface, Signal decomposition, Computational models, Computational neuroscience, Machine learning
MeSH: Brain-Computer Interfaces*, Imagination*, Support Vector Machine*, Algorithms, Electroencephalography, Humans, Signal Processing, Computer-Assisted (* major topic)
Topic: EEG and Brain-Computer Interfaces (Cognitive Neuroscience, Neuroscience), according to OpenAlex
Funding: the Key Science Research Project of Colleges and Universities in Henan Province (25A520003); the Key Science and Technology Program of Henan Province (262102211021, 262102211056)
Citations: not cited yet (Europe PMC); 49 references in the paper

Abstract

The abstract is not reproduced here: the paper's license (CC BY-NC-ND) does not allow it. Read it in the paper, at the publisher or on Europe PMC.

Repository

Its files are read in the Code ↔ Paper reader above, with 1 match between paragraphs and lines of code.

Luser-hub/FW-LS-TWSVM

License: none: the authors keep all their rights
State: the link answers, verified on 28 September 2026
Evidence: files inventoried
Commit: 5500aa68a2411c1d8f52f22f0fcaa350a912347e, 19 January 2026
Languages: MATLAB (23)
Size: 27 files, 23 scripts
Software Heritage: not archived
Found in: “Code availability”
Holds: README
Not found: license file, CITATION.cff, environment file, tests, continuous integration, documentation
Tools: Statistics and Machine Learning Toolbox (13 files), Signal Processing Toolbox (1 file)
Availability: 1 check, the latest on 28 September 2026: the link answers
  • 28 September 2026: the link answers
24 files
At the source: github.com/Luser-hub/FW-LS-TWSVM

Code availability statement

The paper has a code availability statement. Its license (CC BY-NC-ND) does not allow reproducing it here; in short, from what the harvester recognized in it:

Read it in the paper: doi.org/10.1038/s41598-026-46642-3.

Tracing map

Proposed by the machine: these links were found in the paper and verified at the source, without human review. The map will receive a Zenodo DOI once one of the paper's authors has validated it with their ORCID.

What the map holds:

  • 1 repository of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
  • 23 scripts, each with its path and the digest of its content;
  • 1 match between paragraphs of the paper and lines of the code (method lexical-v1);
  • neither the text of the paper nor the code itself.

Its JSON (tracing-map.json) is deposited on Zenodo with its DOI once the map is validated.

Data

No dataset and no data link were found in the paper.

Data availability statement

The paper has a data availability statement. Its license (CC BY-NC-ND) does not allow reproducing it here; in short, from what the harvester recognized in it:

  • no repository, dataset or request procedure was recognized in it

Read it in the paper: doi.org/10.1038/s41598-026-46642-3.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 28 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 8 authors, 7 keywords, 7 MeSH terms, 2 funders, 31 references.

Cite

This paper

Zhi, J., Zhang, Q., Li, Y., Zhang, J., Liu, P., Nan, J., Li, Y., & Li, D. (2026). Joint MVMD-based optimal feature selection and FW-LS-TWSVM for motor imagery recognition. Scientific reports, 16(1), 15648. https://doi.org/10.1038/s41598-026-46642-3

BibTeX

@article{zhi2026joint,
author = {Zhi, Jun and Zhang, Qichen and Li, Yimin and Zhang, Juqin and Liu, Peisen and Nan, Jiaofen and Li, Yanting and Li, Duan},
title = {{Joint MVMD-based optimal feature selection and FW-LS-TWSVM for motor imagery recognition}},
journal = {Scientific reports},
year = {2026},
month = apr,
volume = {16},
number = {1},
pages = {15648},
publisher = {Nature Publishing Group},
issn = {2045-2322},
doi = {10.1038/s41598-026-46642-3},
url = {https://doi.org/10.1038/s41598-026-46642-3},
pmid = {41922634},
pmcid = {PMC13187188}
}

RIS

TY - JOUR
AU - Zhi, Jun
AU - Zhang, Qichen
AU - Li, Yimin
AU - Zhang, Juqin
AU - Liu, Peisen
AU - Nan, Jiaofen
AU - Li, Yanting
AU - Li, Duan
TI - Joint MVMD-based optimal feature selection and FW-LS-TWSVM for motor imagery recognition
T2 - Scientific reports
J2 - Sci Rep
PY - 2026
DA - 2026/04/01
VL - 16
IS - 1
SP - 15648
SN - 2045-2322
PB - Nature Publishing Group
DO - 10.1038/s41598-026-46642-3
UR - https://doi.org/10.1038/s41598-026-46642-3
LA - en
ER -

CSL-JSON

{
"id": "10.1038/s41598-026-46642-3",
"type": "article-journal",
"title": "Joint MVMD-based optimal feature selection and FW-LS-TWSVM for motor imagery recognition",
"container-title": "Scientific reports",
"author": [
{
"family": "Zhi",
"given": "Jun"
},
{
"family": "Zhang",
"given": "Qichen"
},
{
"family": "Li",
"given": "Yimin"
},
{
"family": "Zhang",
"given": "Juqin"
},
{
"family": "Liu",
"given": "Peisen"
},
{
"family": "Nan",
"given": "Jiaofen"
},
{
"family": "Li",
"given": "Yanting"
},
{
"family": "Li",
"given": "Duan"
}
],
"container-title-short": "Sci Rep",
"volume": "16",
"issue": "1",
"page": "15648",
"DOI": "10.1038/s41598-026-46642-3",
"PMID": "41922634",
"PMCID": "PMC13187188",
"ISSN": "2045-2322",
"publisher": "Nature Publishing Group",
"URL": "https://doi.org/10.1038/s41598-026-46642-3",
"language": "en",
"issued": {
"date-parts": [
[
2026,
4,
1
]
]
}
}

The tracing map gets a citation of its own once an author has validated it and it has a DOI.

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.1038/s41597-026-07807-x [code]
A Multimodal fNIRS-EEG Dataset for Unilateral Limb Motor Imagery.
Journal: Scientific data
In common: Signal Processing Toolbox, Statistics and Machine Learning Toolbox, EEG, 3 references
[2] doi:10.1038/s41598-026-56070-y [code]
SSDLabeler: realistic semi-synthetic data generation for multi-label artifact classification in EEG.
Journal: Scientific reports
In common: Signal Processing Toolbox, Statistics and Machine Learning Toolbox, EEG, 1 reference
[3] doi:10.3390/s26134045
Brain Signal for Secure EEG Biometric Authentication: A Comprehensive Survey.
Journal: Sensors (Basel, Switzerland)
In common: EEG, 2 references
[4] doi:10.1371/journal.pcbi.1014112 [code]
Opposing cortical forces: Alpha slowing and sensorimotor mu acceleration during motor-related BCI training.
Journal: PLoS computational biology
In common: EEG, 2 references
[5] doi:10.1038/s41598-026-50997-y [code]
Comprehensive benchmarking and explainable machine learning analysis of EEG imagery activity recognition.
Journal: Scientific reports
In common: EEG, 2 references
[6] doi:10.1371/journal.pone.0358552 [code]
High-frequency stimulation-induced secondary hyperalgesia shifts temporal order judgment and increases precuneus nodal degree in healthy adults.
Journal: PloS one
In common: Signal Processing Toolbox, Statistics and Machine Learning Toolbox, EEG
[7] doi:10.1162/imag.a.1353 [code]
Model-based cardiac field artefact correction for OP-MEG.
Journal: Imaging neuroscience (Cambridge, Mass.)
In common: Signal Processing Toolbox, Statistics and Machine Learning Toolbox, EEG
[8] doi:10.7554/elife.108408 [code]
Frequency and laminar profile of feature-specific visual activity revealed by interleaved EEG-fMRI.
Journal: eLife
In common: Signal Processing Toolbox, Statistics and Machine Learning Toolbox, EEG
[9] doi:10.1371/journal.pbio.3003982 [code]
No evidence for modulation of the readiness potential by respiratory phase during natural breathing.
Journal: PLoS biology
In common: Signal Processing Toolbox, Statistics and Machine Learning Toolbox, EEG
[10] doi:10.1371/journal.pbio.3003938 [code]
Theta oscillations tag episodic memories for sleep-dependent consolidation.
Journal: PLoS biology
In common: Signal Processing Toolbox, Statistics and Machine Learning Toolbox, EEG

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion, reproductions, activity

Discussion: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.