mne_hfo.LineLengthDetector¶
-
class
mne_hfo.LineLengthDetector(threshold=3, win_size=100, overlap=0.25, sfreq=None, filter_band=(30, 100), scoring_func='f1', n_jobs=- 1, hfo_name='hfo', verbose=False)[source]¶ Line-length detection algorithm.
Original paper defines HFOS as “(HFOs), which we collectively term as all activity >40 Hz (including gamma, high-gamma, ripple, and fast ripple oscillations), may have a fundamental role in the generation and spread of focal seizures”
In the paper, data were sampled at 200 Hz and bandpass-filtered (0.1 – 100 Hz) during acquisition. Data were further digitally bandpass-filtered (4th-order Butterworth, forward-backward filtering,
0.1 – 85 Hz) to minimize potential artifacts due to aliasing. (IIR for forward-backward pass).Compared to RMS detector, they utilize line-length metric.
- Parameters
filter_band : tuple(float, float) | None
Low cut-off frequency at index 0 and high cut-off frequency at index 1.
threshold: float
Number of standard deviations to use as a threshold
win_size: int
Sliding window size in samples
overlap: float
Fraction of the window overlap (0 to 1)
offset: int
Offset which is added to the final detection. This is used when the function is run in separate windows. Default = 0
hfo_name: str
What to name the events detected (i.e. fast ripple if freq_band is (250, 500)).
Notes
For processing, a sliding window is used.
For post-processing, any events that overlap are considered to be the same.
References
- 1
A. B. Gardner, G. A. Worrell, E. Marsh, D. Dlugos, and B. Litt, “Human and automated detection of high-frequency oscillations in clinical intracranial EEG recordings,” Clin. Neurophysiol., vol. 118, no. 5, pp. 1134–1143, May 2007.
- 2
Esteller, R. et al. (2001). Line length: an efficient feature for seizure onset detection. In Engineering in Medicine and Biology Society, 2001. Proceedings of the 23rd Annual International Conference of the IEEE (Vol. 2, pp. 1707-1710). IEEE.
- Attributes
-
Return dictionary of HFO start/end points.
Return list of HFO start/end points for each channel.
Higher frequency band for HFO definition.
Return HFO detections as a dataframe.
HFO event array.
Return HFO detections as an event.tsv DataFrame.
Lower frequency band for HFO definition.
Step size of each window.
Methods
fit(X[, y])Fit the model according to the optionally given training data.
fit_predict(X[, y])Perform fit on X and returns labels for X.
get_params([deep])Get parameters for this estimator.
predict(X)Scikit-learn override predict function.
score(X, y[, sample_weight])Return the score of the HFO prediction.
set_params(**params)Set the parameters of this estimator.
-
property
chs_hfos_dict¶ Return dictionary of HFO start/end points.
-
property
chs_hfos_list¶ Return list of HFO start/end points for each channel.
-
fit(X, y=None)¶ Fit the model according to the optionally given training data.
- Parameters
X : mne.io.Raw of shape (n_samples, n_features) | pd.DataFrame
Training vector, where n_samples is the number of samples and n_features is the number of features. In MNE-HFO, n_features are the number of time points in the EEG data, and n_samples are the number of channels.
y : array-like of shape (n_samples, n_output)
Target vector relative to X.
- Returns
self
Fitted estimator.
Notes
All detectors use a sliding window to compute HFOs in windows.
-
fit_predict(X, y=None)¶ Perform fit on X and returns labels for X.
Returns -1 for outliers and 1 for inliers.
- Parameters
- X{array-like, sparse matrix, dataframe} of shape (n_samples, n_features)
y : Ignored
Not used, present for API consistency by convention.
- Returns
y : ndarray of shape (n_samples,)
1 for inliers, -1 for outliers.
-
get_params(deep=True)¶ Get parameters for this estimator.
- Parameters
deep : bool, default=True
If True, will return the parameters for this estimator and contained subobjects that are estimators.
- Returns
params : dict
Parameter names mapped to their values.
-
property
h_freq¶ Higher frequency band for HFO definition.
-
property
hfo_df¶ Return HFO detections as a dataframe.
-
property
hfo_event_arr¶ HFO event array.
- Returns
hfo_event_arr : np.ndarray
Array that is (n_chs, n_samples), which has a value of
1if
-
property
hfo_event_df¶ Return HFO detections as an event.tsv DataFrame.
-
property
l_freq¶ Lower frequency band for HFO definition.
-
predict(X)¶ Scikit-learn override predict function.
Just directly computes HFOs using
fitfunction.- Parameters
X : mne.io.Raw | pd.DataFrame
Input data.
- Returns
ypred : list[list[tuple]]
List of HFO events per channel in order of
ch_namesof input data. HFO events are stored as list of tuples: onset and offset of the HFO event.
-
score(X, y, sample_weight=None)¶ Return the score of the HFO prediction.
- Parameters
X : np.ndarray
Channel data to detect HFOs on.
y : pd.DataFrame
Event Dataframe of true labels
- sample_weight :
- Returns
- float
-
set_params(**params)¶ Set the parameters of this estimator.
The method works on simple estimators as well as on nested objects (such as
Pipeline). The latter have parameters of the form<component>__<parameter>so that it’s possible to update each component of a nested object.- Parameters
**params : dict
Estimator parameters.
- Returns
self : estimator instance
Estimator instance.
-
property
step_size¶ Step size of each window.
Window increment over the samples of signal.