Machine Learning 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.

Apps

Signal Analyzer	Visualize and compare multiple signals and spectra
Signal Labeler	Label signal attributes, regions, and points of interest

Functions

expand all

Signal Labeling

`labeledSignalSet`	Create labeled signal set
`signalLabelDefinition`	Create signal label definition

Datastores

signalDatastore Datastore for collection of signals

Feature Extraction

`findchangepts`	Find abrupt changes in signal
`findpeaks`	Find local maxima
`findsignal`	Find signal location using similarity search
`fsst`	Fourier synchrosqueezed transform
`instfreq`	Estimate instantaneous frequency
`pentropy`	Spectral entropy of signal
`periodogram`	Periodogram power spectral density estimate
`pkurtosis`	Spectral kurtosis from signal or spectrogram
`powerbw`	Power bandwidth
`pspectrum`	Analyze signals in the frequency and time-frequency domains
`pwelch`	Welch’s power spectral density estimate

Topics

Radar Waveform Classification Using Deep Learning (Phased Array System Toolbox)

This example shows how to classify radar waveform types of generated synthetic data using the Wigner-Ville distribution (WVD) and a deep convolutional neural network (CNN).

Pedestrian and Bicyclist Classification Using Deep Learning (Phased Array System Toolbox)

This example shows how to classify pedestrians and bicyclists based on their micro-Doppler characteristics using a deep learning network and time-frequency analysis.

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.