Regression

Signal denoising, phase recovery, and source separation

Apply deep learning techniques to denoise signals. Use differentiable time-frequency transforms to reconstruct signals when there is missing information.

Apps

Regression LearnerTrain regression models to predict data using supervised machine learning
Experiment Manager Design and run experiments to train and compare deep learning networks

Functions

expand all

audioDatastoreDatastore for collection of audio files
arrayDatastoreDatastore for in-memory data (Since R2020b)
signalDatastoreDatastore for collection of signals
imageDatastoreDatastore for image data
waveletScatteringWavelet time scattering
signalTimeFeatureExtractorStreamline signal time feature extraction (Since R2021a)
signalFrequencyFeatureExtractorStreamline signal frequency feature extraction (Since R2021b)
signalTimeFrequencyFeatureExtractorStreamline signal time-frequency feature extraction (Since R2024a)
stftLayerShort-time Fourier transform layer (Since R2021b)
istftLayerInverse short-time Fourier transform layer (Since R2024a)
cwtLayerContinuous wavelet transform layer (Since R2022b)
icwtLayerInverse continuous wavelet transform layer (Since R2024b)
modwtLayerMaximal overlap discrete wavelet transform layer (Since R2022b)

Blocks

Wavelet ScatteringModel wavelet scattering network in Simulink (Since R2022b)

Related Information

Topics

Featured Examples

New
CBRS Band Radar Parameter Estimation Using YOLOX

CBRS Band Radar Parameter Estimation Using YOLOX

Detect radar pulses in noise and estimates the pulse parameters using a combination of time-frequency maps and a deep-learning object detector.

Denoise Signals with Generative Adversarial Networks

Denoise Signals with Generative Adversarial Networks

Use autoencoders and generative adversarial networks to denoise signals.

Signal Source Separation Using W-Net Architecture

Signal Source Separation Using W-Net Architecture

Use a deep learning network to separate two mixed signal sources.

(Signal Processing Toolbox)

  • Since R2022b
Denoise EEG Signals Using Differentiable Signal Processing Layers

Denoise EEG Signals Using Differentiable Signal Processing Layers

Remove EOG noise from EEG signals using deep learning regression.

(Signal Processing Toolbox)

  • Since R2021b
Human Health Monitoring Using Continuous Wave Radar and Deep Learning

Human Health Monitoring Using Continuous Wave Radar and Deep Learning

Use a deep learning network to reconstruct electrocardiograms from continuous-wave radar signals.

(Signal Processing Toolbox)

  • Since R2022b
Denoise Speech Using Deep Learning Networks

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.

Denoise Signals with Adversarial Learning Denoiser Model

Denoise Signals with Adversarial Learning Denoiser Model

Use an adversarial learning denoiser model to denoise signals.

Signal Recovery with Differentiable Scalograms and Spectrograms

Signal Recovery with Differentiable Scalograms and Spectrograms

Use differentiable time-frequency transforms and gradient descent to recover a time-domain signal without the need for phase information.

(Wavelet Toolbox)

  • Since R2022b