Examples Gallery#

This gallery contains examples demonstrating the usage of mne-denoise.

DSS Examples#

Overview#

Examples demonstrating Denoising Source Separation (DSS) across evoked, spectral, temporal, and blind-separation use cases.

Files#

plot_01_dss_fundamentals.py: Core DSS concepts with trial-average and bandpass biases.
plot_02_artifact_correction.py: Blink and heartbeat correction with DSS.
plot_03_evoked_responses.py: Evoked-response denoising and contrast-focused DSS.
plot_04_spectral_dss.py: Frequency-specific component extraction on synthetic and real data.
plot_05_periodic_dss.py: Periodic signal extraction for SSVEP and quasi-periodic structure.
plot_06_temporal_dss.py: Time-shift and smoothness biases for temporally structured signals.
plot_07_spectrogram_dss.py: Time-frequency masking with spectrogram-based DSS.
plot_08_blind_source_separation.py: Blind source separation and FastICA equivalence.
plot_09_custom_bias.py: Defining custom DSS biases.
plot_10_benchmarking.py: Efficiency benchmarking against PCA, ICA, and averaging.
plot_11_wiener_masking.py: Adaptive Wiener masking for bursty signals.
plot_12_joint_dss.py: Joint DSS for multi-dataset repeatability.

Data Requirements#

Synthetic sections run directly with no external data.
Examples using MNE datasets download and cache them through MNE when needed.

References#

Särelä & Valpola (2005). Denoising Source Separation. J. Mach. Learn. Res.
de Cheveigné & Simon (2008). Denoising based on spatial filtering. J. Neurosci. Methods.
de Cheveigné & Parra (2014). Joint decorrelation. NeuroImage.

Fundamentals of DSS.

Artifact Correction with DSS.

Denoising Evoked Responses.

Denoising Rhythms (Spectral DSS).

Periodic Signals (SSVEP and Quasi-Periodic).

Temporal DSS: Time-Shift Regression & Smoothness.

Time-Frequency DSS: Spectrogram Masking.

Blind Source Separation and ICA Equivalence.

Custom DSS: Defining Your Own Bias.

Efficiency Benchmark: DSS vs PCA, ICA, and Averaging.

Adaptive Wiener Masking for Bursty Signals.

Joint DSS (Multi-Dataset Repeatability).

ZapLine Examples#

Overview#

Examples demonstrating ZapLine and ZapLine-plus for removing power-line artifacts from synthetic, epoched, continuous, and adaptive-cleaning scenarios.

Files#

plot_01_basic_usage.py: Basic ZapLine usage on synthetic line-noise data.
plot_02_parameter_tuning.py: Parameter tuning and real NoiseTools MEG data.
plot_03_epoched_data.py: Epoched ZapLine workflows and high-channel MEG data.
plot_04_adaptive_mode.py: ZapLine-plus style adaptive cleaning on non-stationary data.
plot_05_adaptive_advanced.py: Advanced harmonic and chunk-level adaptive outputs.

Data Requirements#

Synthetic sections run directly with no external data.
Examples using MNE datasets download and cache them through MNE when needed.
NoiseTools-backed examples download and cache the required .mat files into examples/zapline/data the first time they are run.

References#

de Cheveigné (2020). ZapLine: A simple and effective method to remove power line artifacts. NeuroImage.
Klug & Kloosterman (2022). Zapline-plus: A Zapline extension for automatic and adaptive removal of frequency-specific noise artifacts in M/EEG. Human Brain Mapping.

ZapLine: Line Noise Removal Fundamentals.

ZapLine: Parameter Tuning and Real Data.

ZapLine: Epoched Data and Real Data Examples.

ZapLine-plus: Adaptive Cleaning on Non-Stationary Noise.

ZapLine-plus: Advanced Settings and Features.