Main Content

AI for Signals

Signal labeling, feature engineering, dataset generation, anomaly detection

Signal Processing Toolbox™ provides functionality to perform signal labeling, feature engineering, and dataset generation for machine learning and deep learning workflows. The toolbox also offers an autoencoder object that you can train and use to detect anomalies in signal data.


Signal AnalyzerVisualize and compare multiple signals and spectra
Signal LabelerLabel signal attributes, regions, and points of interest, and extract features
EDF File AnalyzerView EDF or EDF+ files (depuis R2021a)
Experiment Manager Design and run experiments to train and compare deep learning networks (depuis R2020a)


développer tout

labeledSignalSetCreate labeled signal set
signalLabelDefinitionCreate signal label definition
countlabelsCount number of unique labels (depuis R2021a)
filenames2labelsGet list of labels from filenames (depuis R2022b)
folders2labelsGet list of labels from folder names (depuis R2021a)
framelblPartition label sequence into frames (depuis R2024a)
framesigPartition signal into frames (depuis R2024a)
splitlabelsFind indices to split labels according to specified proportions (depuis R2021a)
signalMaskModify and convert signal masks and extract signal regions of interest (depuis R2020b)
binmask2sigroiConvert binary mask to matrix of ROI limits (depuis R2020b)
extendsigroiExtend signal regions of interest to left and right (depuis R2020b)
extractsigroiExtract signal regions of interest (depuis R2020b)
mergesigroiMerge signal regions of interest (depuis R2020b)
removesigroiRemove signal regions of interest (depuis R2020b)
shortensigroiShorten signal regions of interest from left and right (depuis R2020b)
sigroi2binmaskConvert matrix of ROI limits to binary mask (depuis R2020b)
sigrangebinmaskLabel signal samples with values within a specified range (depuis R2023a)
edfinfoGet information about EDF/EDF+ file (depuis R2020b)
edfwriteCreate or modify EDF or EDF+ file (depuis R2021a)
edfheaderCreate header structure for EDF or EDF+ file (depuis R2021a)
edfreadRead data from EDF/EDF+ file (depuis R2020b)
signalDatastoreDatastore for collection of signals (depuis R2020a)
resizeResize data by adding or removing elements (depuis R2023b)
paddataPad data by adding elements (depuis R2023b)
trimdataTrim data by removing elements (depuis R2023b)
findchangeptsFind abrupt changes in signal
findpeaksFind local maxima
fsstFourier synchrosqueezed transform
stftShort-time Fourier transform
spectrogramSpectrogram using short-time Fourier transform
tfridgeTime-frequency ridges
instbwEstimate instantaneous bandwidth (depuis R2021a)
instfreqEstimate instantaneous frequency
powerbwPower bandwidth
pspectrumAnalyze signals in the frequency and time-frequency domains
spectralCrestSpectral crest for signals and spectrograms
spectralEntropySpectral entropy for signals and spectrograms
spectralFlatnessSpectral flatness for signals and spectrograms
spectralKurtosisSpectral kurtosis for signals and spectrograms
spectralSkewnessSpectral skewness for signals and spectrograms
scalarFeatureOptionsStore information for converting feature vectors to scalar values (depuis R2024a)
signalFrequencyFeatureExtractorStreamline signal frequency feature extraction (depuis R2021b)
signalTimeFeatureExtractorStreamline signal time feature extraction (depuis R2021a)
signalTimeFrequencyFeatureExtractorStreamline signal time-frequency feature extraction (depuis R2024a)
timeFrequencyScalarFeatureOptionsStore information for converting time-frequency feature vectors to scalar values (depuis R2024a)
zerocrossrateZero-crossing rate (depuis R2021b)
dlstftDeep learning short-time Fourier transform (depuis R2021a)
dlistftDeep learning inverse short-time Fourier transform (depuis R2024a)
stftLayerShort-time Fourier transform layer (depuis R2021b)
istftLayerInverse short-time Fourier transform layer (depuis R2024a)
deepSignalAnomalyDetectorCreate signal anomaly detector (depuis R2023a)