Main Content

Working with Signals

Multiresolution analysis, wavelet time scattering, continuous wavelet transform, nondecimated discrete wavelet transform, Wigner-Ville distribution, mel spectrogram

Wavelet scattering enables you to produce low-variance data representations that minimize differences within a class while preserving discriminability across classes. Wavelet scattering requires few user-specified parameters to produce compact representations of data which are robust against time shifts on a scale you define. You can use these representations in conjunction with machine learning algorithms for classification and regression.

You can use the continuous wavelet transform (CWT) to generate 2-D time-frequency maps of time series data, which can be used with 2-D convolutional networks. Generating time-frequency representations for use in deep CNNs is a powerful approach for signal classification. The ability of the CWT to simultaneously capture steady-state and transient behavior in time series data makes the wavelet-based time-frequency representation particularly robust when paired with deep CNNs.

With a Signal Processing Toolbox™ license you can include the short-time Fourier transform into your machine learning and deep learning workflows. You can also use Signal Labeler (Signal Processing Toolbox) to label signals for analysis or for use in machine learning and deep learning applications. Signal Labeler saves data as labeledSignalSet objects. With a Audio Toolbox™ license you can Import and Play Audio File Data in Signal Labeler (Signal Processing Toolbox). You can also use melSpectrogram (Audio Toolbox) for feature extraction.


Signal LabelerLabel signal attributes, regions, and points of interest, and extract features


espandi tutto

cwtLayerContinuous wavelet transform (CWT) layer (Da R2022b)
modwtLayerMaximal overlap discrete wavelet transform (MODWT) layer (Da R2022b)
stftLayerShort-time Fourier transform layer (Da R2021b)
array2cwtfiltersConvert deep-learning CWT filter tensor to filter bank matrix (Da R2022b)
cwtfilterbankContinuous wavelet transform filter bank
cwtfilters2arrayConvert CWT filter bank to reduced-weight tensor for deep learning (Da R2022b)
dlcwtDeep learning continuous wavelet transform (Da R2022b)
dlmodwtDeep learning maximal overlap discrete wavelet transform and multiresolution analysis (Da R2022a)
dlstftDeep learning short-time Fourier transform (Da R2021a)
lwt1-D lifting wavelet transform (Da R2021a)
melSpectrogramMel spectrogram
modwptMaximal overlap discrete wavelet packet transform
modwtMaximal overlap discrete wavelet transform
waveletScatteringWavelet time scattering
wentropyWavelet entropy
wvdWigner-Ville distribution and smoothed pseudo Wigner-Ville distribution
audioDatastoreDatastore for collection of audio files
augmentedImageDatastoreTrasformare i batch per aumentare i dati dell’immagine
imageDatastoreDatastore for image data
signalDatastoreDatastore for collection of signals (Da R2020a)
labeledSignalSetCreate labeled signal set
signalLabelDefinitionCreate signal label definition