La traducción de esta página aún no se ha actualizado a la versión más reciente. Haga clic aquí para ver la última versión en inglés.

Machine learning y deep learning para señales

Etiquetado de señales, ingeniería de características, generación de conjuntos de datos

Signal Processing Toolbox™ proporciona funcionalidades para realizar el etiquetado de señales, la ingeniería de características y la generación de conjuntos de datos en los flujos de trabajo de machine learning y deep learning.

Apps

Signal Analyzer	Visualizar y comparar múltiples señales y espectros
Signal Labeler	Etiquete atributos de señal, regiones y puntos de interés y extraiga características
EDF File Analyzer	Visualizar archivos EDF o EDF+

Funciones

expandir todo

Etiquetado de señales

`labeledSignalSet`	Create labeled signal set
`signalLabelDefinition`	Create signal label definition
`countlabels`	Count number of unique labels
`filenames2labels`	Get list of labels from filenames
`folders2labels`	Get list of labels from folder names
`splitlabels`	Find indices to split labels according to specified proportions
`signalMask`	Modify and convert signal masks and extract signal regions of interest
`binmask2sigroi`	Convert binary mask to matrix of ROI limits
`extendsigroi`	Extend signal regions of interest to left and right
`extractsigroi`	Extract signal regions of interest
`mergesigroi`	Merge signal regions of interest
`removesigroi`	Remove signal regions of interest
`shortensigroi`	Shorten signal regions of interest from left and right
`sigroi2binmask`	Convert matrix of ROI limits to binary mask

Importación de datos y almacenes de datos

`edfinfo`	Get information about EDF/EDF+ file
`edfwrite`	Create or modify EDF or EDF+ file
`edfheader`	Create header structure for EDF or EDF+ file
`edfread`	Leer datos del archivo EDF/EDF+
`signalDatastore`	Datastore for collection of signals

Extracción de características

`dlstft`	Deep learning short-time Fourier transform
`stftLayer`	Short-time Fourier transform layer
`findchangepts`	Find abrupt changes in signal
`findpeaks`	Encontrar los máximos locales
`findsignal`	Find signal location using similarity search
`fsst`	Fourier synchrosqueezed transform
`instbw`	Estimate instantaneous bandwidth
`instfreq`	Estimate instantaneous frequency
`pentropy`	Spectral entropy of signal
`periodogram`	Estimación de la densidad espectral de potencia de un periodograma
`pkurtosis`	Spectral kurtosis from signal or spectrogram
`powerbw`	Power bandwidth
`pspectrum`	Analizar señales en los dominios de frecuencia y de tiempo-frecuencia
`pwelch`	Estimación de densidad espectral de potencia de Welch
`signalFrequencyFeatureExtractor`	Streamline signal frequency feature extraction
`signalTimeFeatureExtractor`	Streamline signal time feature extraction
`zerocrossrate`	Zero-crossing rate

Temas

Manage Data Sets for Machine Learning and Deep Learning Workflows
Organize, access, and manage data sets for different AI applications.
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, Signal Labeler, or Medical Image Labeler.
Radar and Communications Waveform Classification Using Deep Learning (Phased Array System Toolbox)
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 deep learning and time-frequency analysis.
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.
Denoise Speech Using Deep Learning Networks
Denoise speech signals using fully connected and convolutional neural networks.

Información relacionada

Deep Learning in MATLAB (Deep Learning Toolbox)
Clasificación de secuencias mediante deep learning (Deep Learning Toolbox)

Ejemplos destacados

Classify ECG Signals Using Long Short-Term Memory Networks

Classify heartbeat electrocardiogram data using deep learning and signal processing.

Abrir script en vivo

Waveform Segmentation Using Deep Learning

Segment human electrocardiogram signals using time-frequency analysis and deep learning.

Abrir script en vivo

Create Labeled Signal Sets Iteratively with Reduced Human Effort

Use deep learning to decrease the human effort required to label signals.

Abrir script en vivo

Generate Synthetic Signals Using Conditional GAN

Use a conditional generative adversarial network to produce synthetic signals.

Abrir script en vivo

Spoken Digit Recognition with Custom Log Spectrogram Layer and Deep Learning

Classify spoken digits using a deep convolutional neural network and a custom spectrogram layer.

Abrir script en vivo

Signal Recovery with Differentiable Scalograms and Spectrograms

Use differentiable time-frequency transforms to recover a time-domain signal without the need for phase information or transform inversion.

Abrir script en vivo

Human Health Monitoring Using Continuous Wave Radar and Deep Learning

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

Abrir script en vivo

Label Signal Attributes, Regions of Interest, and Points

Use Signal Labeler to label attributes, regions, and points of interest in a set of whale songs.

Abrir script en vivo

Automate Signal Labeling with Custom Functions

Use Signal Labeler to locate and label QRS complexes and R peaks of ECG signals.

Abrir script en vivo

Label Spoken Words in Audio Signals

Use Signal Labeler to label spoken words in an audio signal.

Abrir script en vivo

Classify Time Series Using Wavelet Analysis and Deep Learning

Classify ECG signals using the continuous wavelet transform and a deep convolutional neural network.

Abrir script en vivo

Deploy Signal Segmentation Deep Network on Raspberry Pi

Generate a MEX function and a standalone executable to perform waveform segmentation on a Raspberry Pi^®.

Abrir script en vivo

Learn Pre-Emphasis Filter Using Deep Learning

Use a convolutional deep network to learn a pre-emphasis filter for speech recognition.

Abrir script en vivo

Denoise EEG Signals Using Deep Learning Regression with GPU Acceleration

Remove EOG noise from EEG signals using deep learning regression.

Abrir script en vivo

Denoise Signals with Adversarial Learning Denoiser Model

Use an adversarial learning denoiser model to denoise signals.

Abrir script en vivo

Hand Gesture Classification Using Radar Signals and Deep Learning

Classify ultra-wideband impulse radar signal data using a MISO convolutional neural network.

Abrir script en vivo

Human Activity Recognition Using Signal Feature Extraction and Machine Learning

Extract features from smartphone sensor signals and use them to classify human activity.

Abrir script en vivo

Anomaly Detection Using Autoencoder and Wavelets

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

Abrir script en vivo

Classify Arm Motions Using EMG Signals and Deep Learning

Classify arm motions using labeled EMG signals and a long short-term memory network.

Abrir script en vivo

Signal Source Separation Using W-Net Architecture

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

Abrir script en vivo