Online Retraining

Select a model.
Select a previously trained model.
Train a new predictive model for sleep staging or respiratory scoring of polysomnographic recording. While training is in progress, you may navigate away from the page or close your browser. Trained models may be saved for later use. Select an existing model to test on out-of-sample data, or configure and train a new model.

Sleep Staging

Model configuration.
Configuration
Multiclass models use a softmax function to produce probabilities for each sleep stage or respiratory event for each analysed epoch of recording. The maximum allowed tree depth (or path length) limits the complexity of each decision tree. Higher values allow trees to model higher-order feature interactions, and increase model capacity, complexity, and the likelihood of overfitting. Lower values constrain complexity and may improve generalisation. Maximum number of histogram bins per feature used to approximate candidate split thresholds during tree building. Higher values allow finer thresholds, while lower values smooth the model.
Class imbalance (highly uneven class representation within the training data) may be corrected by adjusting class weights.
Model Information
Feature Selection
Feature Description
EEG Delta Power Total Welch-averaged band power (Z²) of the EEG in the Delta (0.5-4Hz) band.
EEG Theta Power Total Welch-averaged band power (Z²) of the EEG in the Theta (4-8Hz) band.
EEG Alpha Power Total Welch-averaged band power (Z²) of the EEG in the Alpha (8-13Hz) band.
EEG Sigma Power Total Welch-averaged band power (Z²) of the EEG in the Sigma (11-16Hz) band.
EEG Delta-Theta Ratio Ratio of the total Welch-averaged band power (Z²) in the Delta (0.5-4Hz) and Theta (4-8Hz) bands.
EEG Theta-Alpha Ratio Ratio of the total Welch-averaged band power (Z²) in the Theta (4-8Hz) and Alpha (8-13Hz) bands.
EEG Theta-Sigma Ratio Ratio of the total Welch-averaged band power (Z²) in the Theta (4-8Hz) and Sigma (11-16Hz) bands.
EEG Theta-Beta Ratio Ratio of the total Welch-averaged band power (Z²) in the Theta (4-8Hz) and Beta (16-24Hz) bands.
EEG SEF50 Spectral edge frequency below which 50% of total EEG power lies.
EEG SEF95 Spectral edge frequency below which 95% of total EEG power lies.
EEG P10 10th percentile value of the full-wave rectified EEG.
EEG P50 50th percentile value of the full-wave rectified EEG.
EEG P90 90th percentile value of the full-wave rectified EEG.
EEG RMS Root mean square of the full-wave rectified EEG.
EEG Shannon Entropy Shannon entropy of the EEG. A static measure of regularity.
EEG Permutation Entropy Permutation entropy of the EEG where the embedding delay equals 1, and m equals 4. A dynamic measure of regularity.
EEG Spectral Entropy Shannon entropy of the normalized EEG Welch-averaged band power spectrum.
EEG Complexity Lempel-Ziv Complexity of the binarised EEG. A measure of repeating sequences.
EEG DFA Short Detrended fluctuation analysis of the EEG over 9 log-spaced windows, where the minimum window size is 24, and the maximum is 96. A measurement of self-affinity.
EEG DFA Long Detrended fluctuation analysis of the EEG over 9 log-spaced windows, where the minimum window size is 96, and the maximum is 360. A measurement of self-affinity.
EEG Power Total Welch-averaged band power (Z²) of the EEG.
EEG Power Mean Mean frequency (spectral centroid) of the EEG power spectral density.
EEG Power Variance Second central moment about frequency (spectral variance) of the EEG power spectral density.
EEG Power Skewness Third standardized central moment about frequency (spectral skewness) of the EEG power spectral density.
EEG Power Kurtosis Fourth standardized central moment about frequency (spectral excess kurtosis) of the EEG power spectral density.
EOG Slow Eye Movement Band Total Welch-averaged band power (Z²) of the EOG in the 0.5-1Hz band.
EOG Rapid Eye Movement Band Total Welch-averaged band power (Z²) of the EOG in the 1-7Hz band.
EOG P10 10th percentile value of the full-wave rectified EOG.
EOG P50 50th percentile value of the full-wave rectified EOG.
EOG P90 90th percentile value of the full-wave rectified EOG.
EOG RMS Root mean square of the full-wave rectified EOG.
EOG Shannon Entropy Shannon entropy of the EOG. A static measure of regularity.
EOG Permutation Entropy Permutation entropy of the EOG where the embedding delay equals 1, and m equals 4. A dynamic measure of regularity.
EOG Spectral Entropy Shannon entropy of the normalized EOG Welch-averaged band power spectrum.
EOG Complexity Lempel-Ziv Complexity of the binarised EOG. A measure of repeating sequences.
EOG DFA Short Detrended fluctuation analysis of the EOG over 9 log-spaced windows, where the minimum window size is 48, and the maximum is 192. A measurement of self-affinity.
EOG DFA Long Detrended fluctuation analysis of the EOG over 9 log-spaced windows, where the minimum window size is 192, and the maximum is 360. A measurement of self-affinity.
EOG Power Total Welch-averaged band power (Z²) of the EOG.
EOG Power Mean Mean frequency (spectral centroid) of the EOG power spectral density.
EOG Power Variance Second central moment about frequency (spectral variance) of the EOG power spectral density.
EOG Power Skewness Third standardized central moment about frequency (spectral skewness) of the EOG power spectral density.
EOG Power Kurtosis Fourth standardized central moment about frequency (spectral excess kurtosis) of the EOG power spectral density.
EMG P10 10th percentile value of the full-wave rectified EMG.
EMG P50 50th percentile value of the full-wave rectified EMG.
EMG P90 90th percentile value of the full-wave rectified EMG.
EMG RMS Root mean square of the full-wave rectified EMG.
EMG Shannon Entropy Shannon entropy of the full-wave rectified EMG. A static measure of regularity.
EMG Permutation Entropy Permutation entropy of the full-wave rectified EMG where the embedding delay equals 1, and m equals 4. A dynamic measure of regularity.
EMG Spectral Entropy Shannon entropy of the normalized EMG Welch-averaged band power spectrum.
EMG Complexity Lempel-Ziv Complexity of the full-wave rectified and binarised EMG. A measure of repeating sequences.
EMG DFA Short Detrended fluctuation analysis of the full-wave rectified EMG over 9 log-spaced windows, where the minimum window size is 12, and the maximum is 48. A measurement of self-affinity.
EMG DFA Long Detrended fluctuation analysis of the full-wave rectified EMG over 9 log-spaced windows, where the minimum window size is 48, and the maximum is 192. A measurement of self-affinity.
EMG Power Total Welch-averaged band power (Z²) of the EMG.
EMG Power Mean Mean frequency (spectral centroid) of the EMG power spectral density.
EMG Power Variance Second central moment about frequency (spectral variance) of the EMG power spectral density.
EMG Power Skewness Third standardized central moment about frequency (spectral skewness) of the EMG power spectral density.
EMG Power Kurtosis Fourth standardized central moment about frequency (spectral excess kurtosis) of the EMG power spectral density.
Select training data.
Select a precomputed dataset to use for model training. Only datasets specifically configured for training are available. Cross-validation results are available during model testing.
Training configuration and summary.
Bayesian Optimization
Number of objective function evaluations.
Number of candidates evaluated per iteration.
Configure the Bayesian Optimizer and search space for each hyperparameter. The number of iterations determines how many points are evaluated, and the number of candidates controls the resolution of the acquisition search.
Training Progress
Training in progress. You may use the analysis functionality or close your browser.

Optimization Iteration 1 of 30

Current Parameters: Eta=0.023, Gamma=7.476, Lambda=0.024, MinChildWeight=38.129, Subsample=0.861
0
0.4
0.8
Iteration
Multiclass Log Loss
Bayesian Optimization is used to search the hyperparameter ranges provided. This process attempts to balance exploration and exploitation to select the optimal values for the trained model. Gaussian Process Regression (GPR) and the Expected Improvement acquisition function are used. For each set of hyperparameters, models are trained using the appropriate solver. K-fold cross-validation is used to produce a validation error which is input into the GPR that underpins the Bayesian Optimization. The most optimal hyperparameters, as determined by the optimization process, are then used to train the final model. You may save the trained model when training is complete. Saved models are accessible immediately through the Analysis area of the platform.