Machine Learning and Deep Learning for Signals
Signal Processing Toolbox™ provides functionality to perform signal labeling, feature engineering, and dataset generation for machine learning and deep learning workflows.
|Create labeled signal set|
|Create signal label definition|
|Count number of unique labels|
|Get list of labels from folder names|
|Find indices to split labels according to specified proportions|
|Modify and convert signal masks and extract signal regions of interest|
|Convert binary mask to matrix of ROI limits|
|Extend signal regions of interest to left and right|
|Extract signal regions of interest|
|Merge signal regions of interest|
|Remove signal regions of interest|
|Shorten signal regions of interest from left and right|
|Convert matrix of ROI limits to binary mask|
Datastores and Data Import
|Deep learning short-time Fourier transform|
|Short-time Fourier transform layer|
|Find abrupt changes in signal|
|Find local maxima|
|Find signal location using similarity search|
|Fourier synchrosqueezed transform|
|Estimate instantaneous bandwidth|
|Estimate instantaneous frequency|
|Spectral entropy of signal|
|Periodogram power spectral density estimate|
|Spectral kurtosis from signal or spectrogram|
|Analyze signals in the frequency and time-frequency domains|
|Welch’s power spectral density estimate|
|Streamline signal frequency feature extraction|
|Streamline signal time feature extraction|
- Choose an App to Label Ground Truth Data
Decide which app to use to label ground truth data: Image Labeler, Video Labeler, Ground Truth Labeler, Lidar Labeler, or Signal Labeler.
- Radar and Communications Waveform Classification Using Deep Learning (Phased Array System Toolbox)
This example shows how to classify radar and communications waveforms using the Wigner-Ville distribution (WVD) and a deep convolutional neural network (CNN).
- Label Radar Signals with Signal Labeler (Radar Toolbox)
Label the time and frequency features of pulse radar signals with added noise.
- Pedestrian and Bicyclist Classification Using Deep Learning (Radar Toolbox)
Classify pedestrians and bicyclists based on their micro-Doppler characteristics using a deep learning network and time-frequency analysis.
- Music Genre Classification Using Wavelet Time Scattering (Wavelet Toolbox)
Classify the genre of a musical excerpt using wavelet time scattering and the audio datastore.
- Wavelet Time Scattering Classification of Phonocardiogram Data (Wavelet Toolbox)
Classify human phonocardiogram recordings using wavelet time scattering and a support vector machine classifier.
- Train Spoken Digit Recognition Network Using Out-of-Memory Features
Train a spoken digit recognition network on out-of-memory auditory spectrograms using a transformed datastore.