Régression

Séparation des sources du signal, débruitage et récupération du signal

Utilisez les techniques de Deep Learning pour débruiter les signaux. Utilisez des transformées temps-fréquence différentiables pour reconstruire les signaux lorsqu’il manque des informations.

Fonctions

développer tout

Autoencodeurs

deepSignalAnomalyDetector Create signal anomaly detector (depuis R2023a)

Couches de traitement du signal

`cwtLayer`	Continuous wavelet transform (CWT) layer (depuis R2022b)
`modwtLayer`	Maximal overlap discrete wavelet transform (MODWT) layer (depuis R2022b)
`stftLayer`	Short-time Fourier transform layer (depuis R2021b)
`istftLayer`	Inverse short-time Fourier transform layer (depuis R2024a)

Extraction de caractéristiques

`cwtmag2sig`	Signal reconstruction from CWT magnitude (depuis R2023b)
`dlcwt`	Deep learning continuous wavelet transform (depuis R2022b)
`dlmodwt`	Deep learning maximal overlap discrete wavelet transform and multiresolution analysis (depuis R2022a)
`dlstft`	Deep learning short-time Fourier transform (depuis R2021a)
`dlistft`	Deep learning inverse short-time Fourier transform (depuis R2024a)
`cwtfilterbank`	Continuous wavelet transform filter bank
`findchangepts`	Find abrupt changes in signal
`findpeaks`	Find local maxima
`modwt`	Maximal overlap discrete wavelet transform
`risetime`	Rise time of positive-going bilevel waveform transitions
`stft`	Short-time Fourier transform
`stftmag2sig`	Signal reconstruction from STFT magnitude (depuis R2020b)
`signalFrequencyFeatureExtractor`	Streamline signal frequency feature extraction (depuis R2021b)
`signalTimeFeatureExtractor`	Streamline signal time feature extraction (depuis R2021a)
`waveletScattering`	Wavelet time scattering

Datastores et gestion des données

`edfheader`	Create header structure for EDF or EDF+ file (depuis R2021a)
`edfinfo`	Get information about EDF/EDF+ file (depuis R2020b)
`edfread`	Read data from EDF/EDF+ file (depuis R2020b)
`edfwrite`	Create or modify EDF or EDF+ file (depuis R2021a)
`paddata`	Pad data by adding elements (depuis R2023b)
`resize`	Resize data by adding or removing elements (depuis R2023b)
`trimdata`	Trim data by removing elements (depuis R2023b)
`signalDatastore`	Datastore for collection of signals (depuis R2020a)

Blocs

Wavelet Scattering

Model wavelet scattering network in Simulink (depuis R2022b)

Rubriques

Manage Data Sets for Machine Learning and Deep Learning Workflows (Signal Processing Toolbox)
Organize, access, and manage data sets for different AI applications.
Signal Recovery with Differentiable Scalograms and Spectrograms (Wavelet Toolbox)
Use differentiable time-frequency transforms and gradient descent to recover a time-domain signal without the need for phase information.
Signal Source Separation Using W-Net Architecture (Signal Processing Toolbox)
Use a deep learning network to separate two mixed signal sources.
Denoise EEG Signals Using Differentiable Signal Processing Layers (Signal Processing Toolbox)
Remove EOG noise from EEG signals using deep learning regression.

Exemples présentés

Anomaly Detection Using Convolutional Autoencoder with Wavelet Scattering Sequences

Detect anomalies in acoustic data using wavelet scattering with the deepSignalAnomalyDetector object.

Ouvrir le live script

Anomaly Detection Using Autoencoder and Wavelets

Use wavelet-extracted features and an autoencoder to detect arc signals in a DC system.

Ouvrir le live script

Detect Anomalies Using Wavelet Scattering with Autoencoders

Learn how to develop an alert system for predictive maintenance using wavelet scattering and deep learning.

Ouvrir le live script

Denoise Speech Using Deep Learning Networks

Denoise speech signals using deep learning networks. The example compares two types of networks applied to the same task: fully connected, and convolutional.

Ouvrir le live script