SSDLabeler: realistic semi-synthetic data generation for multi-label artifact classification in EEG.
5 blocks of code here have a permanent identifier (oscr:b:…), listed with the matches below: citable for good, with a page of its own. Select a match and press Cite to copy it. What a block identifier is.
The 8 matches · 2 of them tie a paragraph to a whole file without given lines: weak matches, whose lines are not tinted
- [1] § Methods › Semi-synthetic data generation (SSDLabeler) ↔ SSDLabeler/SSDLabeler.m, lines 1 to 88 · score 0.86 · brain ICs, raw EEG recordings, clean EEG epochs, raw EEG epochs, artifact components, multi artifact · block
oscr:b:F36K4MNDBHHQ4-T· Report a mismatch - [2] § Methods › Semi-synthetic data generation (SSDLabeler) ↔ SSDLabeler/SSDLabeler.m, lines 1 to 88 · score 0.71 · artifact presence, ICLabel, SSDLabeler, confident, Raw EEG, ICs · block
oscr:b:F36K4MNDBHHQ4-T· Report a mismatch - [3] § Methods › SSD labeler for artifact annotation › SSDLabeler hyperparameter optimization ↔ SSDLabeler/main.m, the whole file · a weak match · score 0.63 · PSD verification, probability threshold, ICLabel, SSDLabeler, motor, hyperparameters · block
oscr:b:25Q0MA77PR1B2-5· Report a mismatch - [4] § Methods › Model › Model architecture and losses ↔ EEG_Artifact_Classification/artifact_classification/module/eeg_artifact_classification.py, lines 158 to 166 · score 0.58 · binary cross entropy, loss, predictions, classification · block
oscr:b:R8SXYVWS4CQ10-3· Report a mismatch - [5] § Methods › SSD labeler for artifact annotation ↔ SSDLabeler/main.m, the whole file · a weak match · score 0.56 · PSD verification, PSD thresholding, events, labeler, RMS, channel · block
oscr:b:25Q0MA77PR1B2-5· Report a mismatch - [6] § Methods › Dataset and preprocessing ↔ EEG_Artifact_Classification/main_EEGArtifact.py, lines 42 to 110 · score 0.55 · cross validation, artifact classification, subset, training, model, raw · block
oscr:b:37KMW1Y9MW5JR-Y· Report a mismatch - [7] § Methods › ICA and artifact IC selection ↔ SSDLabeler/SSDLabeler.m, lines 123 to 131 · score 0.53 · mixing matrix, clean EEG, reconstructing, brain, heart, signals · block
oscr:b:JX84RWY4PW0Y4-Q· Report a mismatch - [8] § Methods › Model ↔ EEG_Artifact_Classification/main_EEGArtifact.py, lines 42 to 110 · score 0.51 · EEG encoder, artifact classification, module, model, trained, SSD · block
oscr:b:37KMW1Y9MW5JR-Y· Report a mismatch
Paper
Loaded from Europe PMC by your browser; OSCR does not store it: doi.org · Europe PMC
The paper is loaded when this pane is shown.
The authors' code
MATLAB · 473 lines · 19 KB · CC-BY-SA-4.0 · 3 matches
- function [SSD, contamination_label_all] = SSDLabeler(EEG_data, fs, target_fs, locs, EEG_channels, ...
- event_idx, trial_mixing, prob_threshold, mix_artifact, thresh_use, clean_use, ...
- thresh_e, thresh_h, thresh_l, thresh_c, thresh_o, thresh_m)
- % SSDLabeler
- % -------------------------------------------------------------------------
- % Generate semi-synthetic EEG datasets (SSD) using ICA + ICLabel-derived
- % artifact component signals, plus RMS/PSD-based epoch-level artifact masks.
- %
- % The function:
- % 1) Filters + epochs raw EEG around event indices
- % 2) Runs PCA+FastICA, then ICLabel to identify IC classes (A)
- % 3) Reconstructs:
- % - "clean" EEG from Brain ICs
- % - artifact-only signals (Eye/Muscle/Heart/Line/Channel/Other ICs)
- % 4) Computes epoch-level artifact presence masks:(B)
- % - Eye/Heart/Line/Channel/Other: Standardized RMS thresholds
- % - Muscle: PSD-template correlation threshold
- % 4.1) Mixes artifacts together (C)
- % 5) Generates mixed trials according to one of the supported modes:
- % A) SSDLabel (A+B+C): add artifact signals only when that epoch is
- % flagged by RMS/PSD masks (multi-artifact per epoch allowed)
- % B) Single-artifact (A+B): generate separate datasets per artifact
- % type (one artifact type at a time), only when that epoch is flagged
- % C) A+C: add all artifact signals regardless of masks (debug/ablation)
- %
- % Outputs:
- % SSD : [N x nChannels x nSamples] dataset
- % contamination_label_all : [N x 7] labels [clean, eye, muscle, heart, line, channel, other]
- %
- % -------------------------------------------------------------------------
- % Inputs
- % -------------------------------------------------------------------------
- % EEG_data : [nChannels x nTime] continuous EEG recording (raw or minimally processed).
- % NOTE: channels should correspond to 'locs' and 'EEG_channels'.
- %
- % fs : Original sampling rate (Hz) of EEG_data (e.g., 500).
- %
- % target_fs : Target sampling rate (Hz) after resampling (e.g., 125).
- % trial_length_sec * target_fs determines the samples per epoch.
- %
- % locs : EEGLAB-style channel locations struct array (chanlocs).
- % Used by ICLabel for topography features.
- %
- % EEG_channels : Vector of channel indices used for ICA/ICLabel (e.g., 1:19).
- % This should match the channels in EEG_data that are EEG (exclude EOG if desired).
- %
- % event_idx : Vector of sample indices (in fs) indicating epoch start points
- % (e.g., movement event onset indices). Each event creates a
- % trial_length_sec-long epoch if it fits in EEG_data.
- %
- % trial_mixing : Integer controlling trial mixing replication.
- % In the current method, ONLY trial_mixing == 0 is supported
- % (because only the 3 requested generation modes are enabled).
- %
- % prob_threshold : ICLabel confidence threshold in [0,1].
- % If max class probability for an IC < prob_threshold, that IC is treated as "unassigned"
- % (i.e., not included in brain or artifact groups via thresholding).
- %
- % mix_artifact : Boolean selecting generation mode:
- % - true : multi-artifact mixing modes (SSDLabel or A+C)
- % - false : single-artifact-per-dataset mode (A+B)
- %
- % thresh_use : Boolean selecting whether RMS/PSD epoch masks are respected:
- % - true : SSDLabel (A+B+C) or mode (A+B) mode uses masks to decide which artifacts
- % are injected into each epoch
- % - false : A+C mode injects ALL artifact signals for every epoch (debug/ablation)
- %
- % clean_use : Boolean controlling final dataset assembly:
- % - true : SSD = [clean_EEG_epochs; raw_epochs; generated_mixed_epochs]
- % labels = [clean_label; artifact_label; mix_label]
- % - false : SSD = [raw_epochs; generated_mixed_epochs]
- % labels = [artifact_label; mix_label]
- %
- % thresh_e : Percentile (0–100) for Eye RMS z-score thresholding.
- % Higher => fewer epochs labeled as Eye artifact (more conservative).
- %
- % thresh_h : Percentile (0–100) for Heart RMS z-score thresholding.
- %
- % thresh_l : Percentile (0–100) for Line-noise RMS z-score thresholding.
- %
- % thresh_c : Percentile (0–100) for Channel-noise RMS z-score thresholding.
- %
- % thresh_o : Percentile (0–100) for Other RMS z-score thresholding.
- %
- % thresh_m : Muscle PSD-template correlation threshold (typically in [-1, 1], often ~0.6–0.9).
- % Epochs with corr(Pxx_avg, template_PSD) < thresh_m are labeled as Muscle artifact.
- % -------------------------------------------------------------------------
- %% -------------------- Params --------------------
- trial_length_sec = 3;
- lp = 1;
- hp = 50;
- order = 6600;
- powerline_freq = 60;
- %% -------------------- 1) Filter + detrend --------------------
- EEG_data = filter_notch(EEG_data, fs, powerline_freq);
- EEG_data = filter_data(EEG_data, fs, lp, hp, order);
- EEG_data = detrend(EEG_data')';
- %% -------------------- 2) Epoch --------------------
- [epochs3d, ~] = epoch_by_events(EEG_data, event_idx, trial_length_sec*fs);
- % epochs3d: [ch x samp x trials]
- [num_channels, num_samples_fs, num_trials] = size(epochs3d);
- % ICA expects [ch x time]
- EEG_ica = reshape(epochs3d, num_channels, num_samples_fs*num_trials);
- %% -------------------- 3) ICA (PCA whitening + fastICA) --------------------
- [mixing_matrix, unmixing_matrix, IC] = run_fastica_with_pca(EEG_ica, fs);
- %% -------------------- 4) ICLabel --------------------
- class_prob = run_iclabel(EEG_ica, fs, locs, EEG_channels, mixing_matrix, unmixing_matrix);
- thresh_class_index = iclabel_threshold_classes(class_prob, prob_threshold);
- icIdx = ic_indices_from_thresh(thresh_class_index);
- brain_ic_index = icIdx.brain;
- if isempty(brain_ic_index)
- warning('No brain IC recovered! Please check.')
- end
- %% -------------------- 5) Build clean EEG + per-artifact reconstructed signals (at fs) --------------------
- EEG_clean_fs = mixing_matrix(:, brain_ic_index) * IC(brain_ic_index, :);
- Signal_fs.eye = mixing_matrix(:, icIdx.eye) * IC(icIdx.eye, :);
- Signal_fs.muscle = mixing_matrix(:, icIdx.muscle) * IC(icIdx.muscle, :);
- Signal_fs.heart = mixing_matrix(:, icIdx.heart) * IC(icIdx.heart, :);
- Signal_fs.line = mixing_matrix(:, icIdx.line) * IC(icIdx.line, :);
- Signal_fs.channel = mixing_matrix(:, icIdx.channel) * IC(icIdx.channel, :);
- Signal_fs.other = mixing_matrix(:, icIdx.other) * IC(icIdx.other, :);
- %% -------------------- 6) Resample + reshape to [trials x ch x samples] --------------------
- num_samples_target = trial_length_sec * target_fs;
- EEG_epochs = to_trials(EEG_clean_fs, num_channels, num_samples_target, num_trials, fs, target_fs);
- Signal_trials.eye = to_trials(Signal_fs.eye, num_channels, num_samples_target, num_trials, fs, target_fs);
- Signal_trials.muscle = to_trials(Signal_fs.muscle, num_channels, num_samples_target, num_trials, fs, target_fs);
- Signal_trials.heart = to_trials(Signal_fs.heart, num_channels, num_samples_target, num_trials, fs, target_fs);
- Signal_trials.line = to_trials(Signal_fs.line, num_channels, num_samples_target, num_trials, fs, target_fs);
- Signal_trials.channel = to_trials(Signal_fs.channel, num_channels, num_samples_target, num_trials, fs, target_fs);
- Signal_trials.other = to_trials(Signal_fs.other, num_channels, num_samples_target, num_trials, fs, target_fs);
- % Artifact-added (for RMS/PSD detection)
- EEG_plus.eye = EEG_epochs + Signal_trials.eye;
- EEG_plus.muscle = EEG_epochs + Signal_trials.muscle;
- EEG_plus.heart = EEG_epochs + Signal_trials.heart;
- EEG_plus.line = EEG_epochs + Signal_trials.line;
- EEG_plus.channel = EEG_epochs + Signal_trials.channel;
- EEG_plus.other = EEG_epochs + Signal_trials.other;
- %% -------------------- 7) RMS-based detection for eye/heart/line/channel/other --------------------
- rms_clean_mean = epoch_rms_mean(EEG_epochs);
- z_eye = (epoch_rms_mean(EEG_plus.eye) - rms_clean_mean) ./ std(rms_clean_mean);
- z_heart = (epoch_rms_mean(EEG_plus.heart) - rms_clean_mean) ./ std(rms_clean_mean);
- z_line = (epoch_rms_mean(EEG_plus.line) - rms_clean_mean) ./ std(rms_clean_mean);
- z_chan = (epoch_rms_mean(EEG_plus.channel) - rms_clean_mean) ./ std(rms_clean_mean);
- z_other = (epoch_rms_mean(EEG_plus.other) - rms_clean_mean) ./ std(rms_clean_mean);
- eye_artifact_idx = z_eye > prctile(z_eye, thresh_e);
- heart_artifact_idx = z_heart > prctile(z_heart, thresh_h);
- line_artifact_idx = z_line > prctile(z_line, thresh_l);
- channel_artifact_idx = z_chan > prctile(z_chan, thresh_c);
- other_artifact_idx = z_other > prctile(z_other, thresh_o);
- %% -------------------- 8) Muscle detection with PSD-template correlation --------------------
- muscle_artifact_idx = muscle_psd_template_mask(EEG_plus.muscle, target_fs, thresh_m);
- %% -------------------- 9) Build masks struct --------------------
- artifactMasks.eye = eye_artifact_idx;
- artifactMasks.muscle = muscle_artifact_idx;
- artifactMasks.heart = heart_artifact_idx;
- artifactMasks.line = line_artifact_idx;
- artifactMasks.channel = channel_artifact_idx;
- artifactMasks.other = other_artifact_idx;
- %% -------------------- 10) Build "epochs_all" (resampled original) --------------------
- epochs_all = to_trials(reshape(epochs3d, num_channels, []), num_channels, num_samples_target, num_trials, fs, target_fs);
- %% -------------------- 11) Generation stage (ONLY 3 MODES) --------------------
- if ~(trial_mixing == 0)
- error('Only trial_mixing == 0 is supported in this refactor (per your requested modes).');
- end
- if thresh_use == true && mix_artifact == true
- % SSDLabel: A+B+C
- [trial_mix_data, trial_mix_label] = gen_SSDLabel_ABC(EEG_epochs, Signal_trials, artifactMasks);
- elseif mix_artifact == false
- % A+B: single-artifact mixing
- [trial_mix_data, trial_mix_label] = gen_singleArtifact_AB(EEG_epochs, Signal_trials, artifactMasks);
- elseif thresh_use == false && mix_artifact == true
- % A+C: no RMS or PSD verification
- [trial_mix_data, trial_mix_label] = gen_allArtifacts_AC(EEG_epochs, Signal_trials, artifactMasks);
- else
- error('Unsupported configuration. Only the 3 requested generation modes are enabled.');
- end
- %% -------------------- 12) Labels for clean + artifact (non-mixed) --------------------
- clean_label = make_clean_labels(size(EEG_epochs,1));
- artifact_label = make_artifact_labels(size(EEG_epochs,1), artifactMasks);
- %% -------------------- 13) Concatenate outputs --------------------
- if clean_use
- contamination_label_all = [clean_label; artifact_label; trial_mix_label];
- SSD = [EEG_epochs; epochs_all; trial_mix_data];
- else
- contamination_label_all = [artifact_label; trial_mix_label];
- SSD = [epochs_all; trial_mix_data];
- end
- end
- %% ========================================================================
- % Helpers
- % ========================================================================
- function [epochs3d, valid_mask] = epoch_by_events(EEG, event_idx, epoch_samples)
- n_ch = size(EEG,1);
- epochs3d = [];
- valid_mask = false(size(event_idx));
- for i = 1:numel(event_idx)
- idx = event_idx(i);
- if idx + epoch_samples - 1 <= size(EEG,2)
- epochs3d = cat(3, epochs3d, EEG(:, idx:(idx+epoch_samples-1)));
- valid_mask(i) = true;
- end
- end
- if isempty(epochs3d)
- epochs3d = zeros(n_ch, epoch_samples, 0);
- end
- end
- function [A, W, IC] = run_fastica_with_pca(X, fs)
- [dewhitening, ~, latent] = pca(X','Centered','off');
- whitening = inv(dewhitening);
- PC = whitening * X;
- latent = 100 * latent / sum(latent);
- n_pcs = sum(latent > 0.01*mean(latent));
- [~, mixing, unmixing] = fastica(PC(1:n_pcs,:), 'approach','defl','g','tanh','maxNumIterations',fs);
- IC = unmixing * PC(1:n_pcs,:);
- A = dewhitening(:,1:n_pcs) * mixing;
- W = unmixing * whitening(1:n_pcs,:);
- end
- function class_prob = run_iclabel(EEG_ica, fs, locs, EEG_channels, A, W)
- data_len = size(EEG_ica,2);
- t = linspace(0, data_len/fs, data_len);
- EEG_struct = struct();
- EEG_struct.times = t;
- EEG_struct.data = EEG_ica;
- EEG_struct.chanlocs = locs;
- EEG_struct.srate = fs;
- EEG_struct.trials = 1;
- EEG_struct.pnts = data_len;
- EEG_struct.icawinv = A;
- EEG_struct.icaweights = W;
- EEG_struct.icaact = W * EEG_ica;
- EEG_struct.icachansind = EEG_channels;
- EEG_struct.ref = 'averef';
- EEG_struct = iclabel(EEG_struct);
- class_prob = EEG_struct.etc.ic_classification.ICLabel.classifications;
- end
- function thresh_class_index = iclabel_threshold_classes(class_prob, prob_threshold)
- [nIC, ~] = size(class_prob);
- thresh_class_index = zeros(1, nIC);
- for i = 1:nIC
- [mx, idx] = max(class_prob(i,:));
- if mx >= prob_threshold
- thresh_class_index(i) = idx;
- else
- thresh_class_index(i) = 0;
- end
- end
- end
- function icIdx = ic_indices_from_thresh(thresh_class_index)
- icIdx.brain = find(thresh_class_index == 1);
- icIdx.muscle = find(thresh_class_index == 2);
- icIdx.eye = find(thresh_class_index == 3);
- icIdx.heart = find(thresh_class_index == 4);
- icIdx.line = find(thresh_class_index == 5);
- icIdx.channel = find(thresh_class_index == 6);
- icIdx.other = find(thresh_class_index == 7);
- end
- function Xtr = to_trials(Xfs, n_ch, n_samp, n_trials, fs, target_fs)
- Xrs = resample(Xfs', target_fs, fs)'; % [ch x (samples_target*trials)]
- Xtr = reshape(Xrs, n_ch, n_samp, n_trials);
- Xtr = permute(Xtr, [3 1 2]); % [trials x ch x samp]
- end
- function m = epoch_rms_mean(X)
- m = squeeze(mean(sqrt(mean(X.^2, 3)), 2)); % [trials x 1]
- end
- function muscle_mask = muscle_psd_template_mask(EEG_plus_muscle, target_fs, corr_threshold)
- [epoch_num, channel_num, ~] = size(EEG_plus_muscle);
- frequencies = 1:50;
- template_PSD = exp(-1 * (1:length(frequencies)) / 20)';
- PSD_corr = zeros(epoch_num, 1);
- for i = 1:epoch_num
- epoch_data = squeeze(EEG_plus_muscle(i,:,:)); % [ch x samp]
- Pxx_all = zeros(length(frequencies), channel_num);
- for ch = 1:channel_num
- Pxx_all(:, ch) = pwelch(epoch_data(ch,:), [], [], frequencies, target_fs);
- end
- Pxx_avg = mean(Pxx_all, 2);
- PSD_corr(i) = corr(Pxx_avg, template_PSD);
- end
- muscle_mask = PSD_corr < corr_threshold;
- end
- function L = make_clean_labels(n)
- L = zeros(n,7);
- L(:,1) = 1;
- end
- function L = make_artifact_labels(n, masks)
- L = zeros(n,7);
- L(masks.eye, 2) = 1;
- L(masks.muscle, 3) = 1;
- L(masks.heart, 4) = 1;
- L(masks.line, 5) = 1;
- L(masks.channel, 6) = 1;
- L(masks.other, 7) = 1;
- no_art = sum(L(:,2:7),2) < 1;
- L(no_art,1) = 1;
- end
- %% ========================================================================
- % ONLY 3 GENERATION FUNCTIONS
- % ========================================================================
- function [trial_mix_data, trial_mix_label] = gen_SSDLabel_ABC(EEG_epochs, Signal_trials, masks)
- % thresh_use==true, trial_mixing==0, mix_artifact==true
- disp('SSDLabel')
- nTrials = size(EEG_epochs,1);
- trial_mix_data = [];
- trial_mix_label = [];
- for i = 1:nTrials
- mixed_trial = squeeze(EEG_epochs(i,:,:));
- if masks.eye(i)
- mixed_trial = mixed_trial + squeeze(Signal_trials.eye(i,:,:));
- end
- if masks.muscle(i)
- mixed_trial = mixed_trial + squeeze(Signal_trials.muscle(i,:,:));
- end
- if masks.heart(i)
- mixed_trial = mixed_trial + squeeze(Signal_trials.heart(i,:,:));
- end
- if masks.line(i)
- mixed_trial = mixed_trial + squeeze(Signal_trials.line(i,:,:));
- end
- if masks.channel(i)
- mixed_trial = mixed_trial + squeeze(Signal_trials.channel(i,:,:));
- end
- if masks.other(i)
- mixed_trial = mixed_trial + squeeze(Signal_trials.other(i,:,:));
- end
- temp_label = [0, masks.eye(i), masks.muscle(i), masks.heart(i), masks.line(i), masks.channel(i), masks.other(i)];
- if sum(temp_label) == 0
- temp_label = [1,0,0,0,0,0,0];
- end
- trial_mix_data = cat(1, trial_mix_data, reshape(mixed_trial, [1, size(mixed_trial,1), size(mixed_trial,2)]));
- trial_mix_label = [trial_mix_label; temp_label];
- end
- end
- function [trial_mix_data, trial_mix_label] = gen_singleArtifact_AB(EEG_epochs, Signal_trials, masks)
- % trial_mixing==0, mix_artifact==false
- nTrials = size(EEG_epochs,1);
- trial_mix_data = [];
- trial_mix_label = [];
- for art = 2:7
- if art == 2 && sum(masks.eye) < 1, continue; end
- if art == 3 && sum(masks.muscle) < 1, continue; end
- if art == 4 && sum(masks.heart) < 1, continue; end
- if art == 5 && sum(masks.line) < 1, continue; end
- if art == 6 && sum(masks.channel) < 1, continue; end
- if art == 7 && sum(masks.other) < 1, continue; end
- for i = 1:nTrials
- mixed_trial = squeeze(EEG_epochs(i,:,:));
- temp_label = [0,0,0,0,0,0,0];
- if art == 2 && masks.eye(i)
- mixed_trial = mixed_trial + squeeze(Signal_trials.eye(i,:,:));
- temp_label = [0,1,0,0,0,0,0];
- elseif art == 3 && masks.muscle(i)
- mixed_trial = mixed_trial + squeeze(Signal_trials.muscle(i,:,:));
- temp_label = [0,0,1,0,0,0,0];
- elseif art == 4 && masks.heart(i)
- mixed_trial = mixed_trial + squeeze(Signal_trials.heart(i,:,:));
- temp_label = [0,0,0,1,0,0,0];
- elseif art == 5 && masks.line(i)
- mixed_trial = mixed_trial + squeeze(Signal_trials.line(i,:,:));
- temp_label = [0,0,0,0,1,0,0];
- elseif art == 6 && masks.channel(i)
- mixed_trial = mixed_trial + squeeze(Signal_trials.channel(i,:,:));
- temp_label = [0,0,0,0,0,1,0];
- elseif art == 7 && masks.other(i)
- mixed_trial = mixed_trial + squeeze(Signal_trials.other(i,:,:));
- temp_label = [0,0,0,0,0,0,1];
- end
- if sum(temp_label) == 0
- temp_label = [1,0,0,0,0,0,0];
- end
- trial_mix_data = cat(1, trial_mix_data, reshape(mixed_trial, [1, size(mixed_trial,1), size(mixed_trial,2)]));
- trial_mix_label = [trial_mix_label; temp_label];
- end
- end
- end
- function [trial_mix_data, trial_mix_label] = gen_allArtifacts_AC(EEG_epochs, Signal_trials, masks)
- % thresh_use==false, trial_mixing==0, mix_artifact==true
- nTrials = size(EEG_epochs,1);
- trial_mix_data = [];
- trial_mix_label = [];
- for i = 1:nTrials
- mixed_trial = squeeze(EEG_epochs(i,:,:));
- mixed_trial = mixed_trial + squeeze(Signal_trials.eye(i,:,:));
- mixed_trial = mixed_trial + squeeze(Signal_trials.muscle(i,:,:));
- mixed_trial = mixed_trial + squeeze(Signal_trials.heart(i,:,:));
- mixed_trial = mixed_trial + squeeze(Signal_trials.line(i,:,:));
- mixed_trial = mixed_trial + squeeze(Signal_trials.channel(i,:,:));
- mixed_trial = mixed_trial + squeeze(Signal_trials.other(i,:,:));
- temp_label = [0, masks.eye(i), masks.muscle(i), masks.heart(i), masks.line(i), masks.channel(i), masks.other(i)];
- if sum(temp_label) == 0
- temp_label = [1,0,0,0,0,0,0];
- end
- trial_mix_data = cat(1, trial_mix_data, reshape(mixed_trial, [1, size(mixed_trial,1), size(mixed_trial,2)]));
- trial_mix_label = [trial_mix_label; temp_label];
- end
- end
SSDLabeler.m at commit 10158c5, under CC-BY-SA-4.0 · at the source
Overview
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 8 matches between paragraphs and lines of code.
AkimaCon/SSDLabeler
10158c5989af6d7f8abba8d067b715f667bede6b, 5 June 2026Availability: 1 check, the latest on 27 September 2026: the link answers
- 27 September 2026: the link answers
17 files
- EEG_Artifact_Classificat
ion/ , Python, 14 linesartifact_classification/ datasets/ __init__.py - EEG_Artifact_Classificat
ion/ , Python, 265 linesartifact_classification/ datasets/ preprocessing_SSD.py - EEG_Artifact_Classificat
ion/ , Python, 2 linesartifact_classification/ model/ __init__.py - EEG_Artifact_Classificat
ion/ , Python, 45 linesartifact_classification/ model/ eeg_encoder.py - EEG_Artifact_Classificat
ion/ , Python, 11 linesartifact_classification/ model/ model.py - EEG_Artifact_Classificat
ion/ , Python, 1 lineartifact_classification/ module/ __init__.py - EEG_Artifact_Classificat
ion/ , Python, 191 lines, 1 matchartifact_classification/ module/ eeg_artifact_classificat ion.py - EEG_Artifact_Classificat
ion/ , Python, 2 linesartifact_classification/ utils/ __init__.py - EEG_Artifact_Classificat
ion/ , Python, 44 linesartifact_classification/ utils/ checkpoint.py - EEG_Artifact_Classificat
ion/ , Python, 24 linesartifact_classification/ utils/ yaml_config_hook.py - EEG_Artifact_Classificat
ion/ , Jupyter, 286 linesevaluation.ipynb - EEG_Artifact_Classificat
ion/ , Python, 112 lines, 2 matchesmain_EEGArtifact.py - EEG_Artifact_Classificat
ion/ , Shell, 3 linessequential_artifact_clas sification.sh - SSDLabeler/
SSDLabeler.m , MATLAB, 473 lines, 3 matches - SSDLabeler/
main.m , MATLAB, 92 lines, 2 matches - LICENSE, License, 253 lines
- README.md, Text, 124 lines
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:
- it points to the authors' code: AkimaCon/
SSDLabeler
Read it in the paper: doi.org/10.1038/s41598-026-56070-y.
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;
- 15 scripts, each with its path and the digest of its content;
- 8 matches 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
Datasets cited
- physionet.org/
content/ , at PhysioNet; found in “Data availability”eegmmidb
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:
- it points to a dataset: physionet.org/
content/ eegmmidb
Read it in the paper: doi.org/10.1038/s41598-026-56070-y.
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, 27 September 2026: the first record
Recorded: type, language, journal, volume, issue, pages, dates, 4 authors, 9 keywords, 5 MeSH terms, 31 references.
Cite
This paper
Akama, T., Connelly, A., Minamikawa, S., & Polouliakh, N. (2026). SSDLabeler: realistic semi-synthetic data generation for multi-label artifact classification in EEG. Scientific reports, 16(1), 25980. https://
BibTeX
@article{akama2026ssdlab
author = {Akama, Taketo and Connelly, Akima and Minamikawa, Shun and Polouliakh, Natalia},
title = {{SSDLabeler: realistic semi-synthetic data generation for multi-label artifact classification in EEG}},
journal = {Scientific reports},
year = {2026},
month = jun,
volume = {16},
number = {1},
pages = {25980},
publisher = {Nature Publishing Group},
issn = {2045-2322},
doi = {10.1038/
url = {https://
pmid = {42259834},
pmcid = {PMC13487299}
}
RIS
TY - JOUR
AU - Akama, Taketo
AU - Connelly, Akima
AU - Minamikawa, Shun
AU - Polouliakh, Natalia
TI - SSDLabeler: realistic semi-synthetic data generation for multi-label artifact classification in EEG
T2 - Scientific reports
J2 - Sci Rep
PY - 2026
DA - 2026/
VL - 16
IS - 1
SP - 25980
SN - 2045-2322
PB - Nature Publishing Group
DO - 10.1038/
UR - https://
LA - en
ER -
CSL-JSON
{
"id": "10.1038/
"type": "article-journal",
"title": "SSDLabeler: realistic semi-synthetic data generation for multi-label artifact classification in EEG",
"container-title": "Scientific reports",
"author": [
{
"family": "Akama",
"given": "Taketo"
},
{
"family": "Connelly",
"given": "Akima"
},
{
"family": "Minamikawa",
"given": "Shun"
},
{
"family": "Polouliakh",
"given": "Natalia"
}
],
"container-title-short":
"volume": "16",
"issue": "1",
"page": "25980",
"DOI": "10.1038/
"PMID": "42259834",
"PMCID": "PMC13487299",
"ISSN": "2045-2322",
"publisher": "Nature Publishing Group",
"URL": "https://
"language": "en",
"issued": {
"date-parts": [
[
2026,
6,
8
]
]
}
}
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:10.3390/s25010231 [code]
- DHCT-GAN: Improving EEG Signal Quality with a Dual-Branch Hybrid CNN-Transformer Network.Journal: Sensors (Basel, Switzerland)In common: ICLabel, EEGLAB, Signal Processing Toolbox, 4 other tools, EEG, 8 references
- [2] doi:10.1523/eneuro.0160-22.2022 [code]
- Improved Manual Annotation of EEG Signals through Convolutional Neural Network Guidance.Journal: eNeuroIn common: ICLabel, EEGLAB, Signal Processing Toolbox, 6 other tools, EEG, 5 references
- [3] doi:10.1038/s41598-025-28855-0 [code]
- ReHA-Net: a ReVIN-hybrid attention network with multiscale convolution for robust EEG artifact removal in brain-computer interfaces.Journal: Scientific reportsIn common: ICLabel, EEGLAB, Signal Processing Toolbox, 4 other tools, EEG, 5 references
- [4] doi:10.1111/cns.70632 [code]
- LRR-UNet: A Deep Unfolding Network With Low-Rank Recovery for EEG Signal Denoising.Journal: CNS neuroscience & therapeuticsIn common: ICLabel, EEGLAB, Signal Processing Toolbox, 4 other tools, EEG, 3 references
- [5] doi:10.3390/s22082853 [code]
- Scorepochs: A Computer-Aided Scoring Tool for Resting-State M/
EEG Epochs. Journal: Sensors (Basel, Switzerland)In common: EEGLAB, Signal Processing Toolbox, Statistics and Machine Learning Toolbox, 2 other tools, physionet.org/content/eegmmidb, EEG, 3 references - [6] doi:10.1016/j.ebiom.2024.105259 [code]
- Machine learning of brain-specific biomarkers from EEG.Journal: EBioMedicineIn common: ICLabel, PyTorch, Statistics and Machine Learning Toolbox, 4 other tools, EEG, 4 references
- [7] doi:10.3390/s26134019 [code]
- NeuroStat: An Open-Source EEG Connectivity Platform for Randomised Controlled Trials.Journal: Sensors (Basel, Switzerland)In common: ICLabel, pandas, Matplotlib, 1 other tool, physionet.org/content/eegmmidb, EEG, 3 references
- [8] doi:10.3390/life13020391 [code]
- On the Influence of Aging on Classification Performance in the Visual EEG Oddball Paradigm Using Statistical and Temporal Features.Journal: Life (Basel, Switzerland)In common: EEGLAB, seaborn, scikit-learn, 3 other tools, EEG, 5 references
- [9] doi:10.1002/hbm.70528 [code]
- Explainable AI Insights Into EEG Classification and Its Alignment to Neural Correlates.Journal: Human brain mappingIn common: ICLabel, PyTorch, seaborn, 4 other tools, EEG, 3 references
- [10] doi:10.3390/s23115051
- Decoding Multi-Class Motor Imagery and Motor Execution Tasks Using Riemannian Geometry Algorithms on Large EEG Datasets.Journal: Sensors (Basel, Switzerland)In common: physionet.org/content/eegmmidb, EEG, 5 references
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.
Claim this paper
Correct its record
Say what each link of this record is, remove the ones that are not the paper's, add the ones that are missing. The correction becomes a new version of the record, in its Versions section.
Validate its tracing map
You validate the map as this page shows it: 1 repository of the authors' code, each at its verified commit and with its license, 15 scripts, and 8 matches between paragraphs and code (see the Code and Map sections). It then receives a DOI on Zenodo, with you (your ORCID iD) and OSCR as its creators; the code itself is not deposited.
The map's fingerprint: sha256:ab328aaf21477b6c…
Add the badge to the code's README
If you are an author or a maintainer of this paper's code, you can add this badge. It says what OSCR knows of the paper (its code, its validated tracing map) and links the code to this page. Paste one of these snippets under the README's title. Keep the two marks around it, so that the badge can be replaced in place and is never added twice. OSCR changes nothing in your repository.
Markdown
<!-- oscr-badge:start -->
[](https://openscicode.org/badge/doi/10.1038/s41598-026-56070-y)
<!-- oscr-badge:end -->reStructuredText
.. oscr-badge:start
.. image:: https://openscicode.org/badge/doi/10.1038/s41598-026-56070-y.svg
:target: https://openscicode.org/badge/doi/10.1038/s41598-026-56070-y
:alt: OSCR
.. oscr-badge:endHTML
<!-- oscr-badge:start -->
<a href="https://openscicode.org/badge/doi/10.1038/s41598-026-56070-y"><img src="https://openscicode.org/badge/doi/10.1038/s41598-026-56070-y.svg" alt="OSCR"></a>
<!-- oscr-badge:end -->On GitHub, open the README, choose Edit (the pencil), paste the snippet under the title, then "Commit changes".
If you choose to, you can have the badge kept up to date for you, with oscr badge --write from the command line or with the GitHub Action in your repository's workflows. Every other form and option (a card, AsciiDoc, LaTeX, shields.io) is on the badge 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: code errors and mismatches between the code and the paper about this paper and its code, from readers and its authors, beside the paper and its tracing map.
Report a mismatch between the code and the paper · Report a code error (signed in)
Reproductions: reports from readers who ran the authors' code and did not get the paper's result, what they ran, with which environment, commit and data.
Report a reproduction failure (signed in)
Versions of its code: the releases of its code tied to a version of this paper (the preprint, the accepted manuscript, the version of record…), each with the tracing map versioned with it.
Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.
