Machine and Deep Learning for Signals

Signal labeling, feature engineering, dataset generation

Signal Processing Toolbox™ provides functionality to perform signal labeling, feature engineering, and dataset generation for machine learning and deep learning workflows.


expand all

labeledSignalSetCreate labeled signal set
signalLabelDefinitionCreate signal label definition
findchangeptsFind abrupt changes in signal
findpeaksFind local maxima
findsignalFind signal location using similarity search
fsstFourier synchrosqueezed transform
instfreqEstimate instantaneous frequency
pentropySpectral entropy of signal
periodogramPeriodogram power spectral density estimate
pkurtosisSpectral kurtosis from signal or spectrogram
powerbwPower bandwidth
pspectrumAnalyze signals in the frequency and time-frequency domains
pwelchWelch’s power spectral density estimate


Signal AnalyzerVisualize and compare multiple signals and spectra

Labeling Functionality

Signal LabelerLabel signals for analysis or machine and deep learning applications


Signal Classification Using Wavelet-Based Features and Support Vector Machines

Classify human electrocardiogram signals using wavelet-based feature extraction and a support vector machine classifier.

Classify Time Series Using Wavelet Analysis and Deep Learning

Classify ECG signals using the continuous wavelet transform and a deep convolutional neural network.

Related Information

Deep Learning in MATLAB (Deep Learning Toolbox)

Sequence Classification Using Deep Learning (Deep Learning Toolbox)

Featured Examples