Preprocessing and Feature Extraction

Extract signal features in time, frequency, and time-frequency domains

Extract meaningful signal features using command-line functions or the Feature Extractor app to use in machine learning models.

Apps

EDF File AnalyzerView EDF or EDF+ files (Since R2021a)
Signal AnalyzerVisualize and compare multiple signals and spectra
Signal LabelerLabel signal attributes, regions, and points of interest
Signal Feature ExtractorExtract and analyze signal features (Since R2025a)

Functions

expand all

detrendRemove polynomial trend
envelopeSignal envelope
lowpassLowpass-filter signals
smoothdataSmooth noisy data
cwtmag2sigSignal reconstruction from CWT magnitude (Since R2023b)
stftmag2sigSignal reconstruction from STFT magnitude (Since R2020b)
cwtfilterbankContinuous wavelet transform filter bank
findpeaksFind local maxima
findchangeptsFind abrupt changes in signal
modwtMaximal overlap discrete wavelet transform
risetime Rise time of positive-going bilevel waveform transitions
stftShort-time Fourier transform
signalTimeFeatureExtractorStreamline signal time feature extraction (Since R2021a)
signalFrequencyFeatureExtractorStreamline signal frequency feature extraction (Since R2021b)
signalTimeFrequencyFeatureExtractorStreamline signal time-frequency feature extraction (Since R2024a)
timeFrequencyScatteringJoint time-frequency scattering (Since R2024b)
waveletScatteringWavelet time scattering
audioDatastoreDatastore for collection of audio files
arrayDatastoreDatastore for in-memory data (Since R2020b)
imageDatastoreDatastore for image data
signalDatastoreDatastore for collection of signals
edfheaderCreate header structure for EDF or EDF+ file (Since R2021a)
edfinfoGet information about EDF/EDF+ file (Since R2020b)
edfreadRead data from EDF/EDF+ file (Since R2020b)
edfwriteCreate or modify EDF or EDF+ file (Since R2021a)
paddataPad data by adding elements (Since R2023b)
resizeResize data by adding or removing elements (Since R2023b)
trimdataTrim data by removing elements (Since R2023b)
dlcwtDeep learning continuous wavelet transform (Since R2022b)
dlicwtDeep learning inverse continuous 1-D wavelet transform (Since R2024b)
dldwtDifferentiable discrete wavelet transform (Since R2025a)
dlidwtDifferentiable inverse discrete wavelet transform (Since R2025a)
dlmodwtDeep learning maximal overlap discrete wavelet transform and multiresolution analysis (Since R2022a)
dlstftDeep learning short-time Fourier transform (Since R2021a)
dlistftDeep learning inverse short-time Fourier transform (Since R2024a)
cwtLayerContinuous wavelet transform layer (Since R2022b)
icwtLayerInverse continuous wavelet transform layer (Since R2024b)
modwtLayerMaximal overlap discrete wavelet transform layer (Since R2022b)
stftLayerShort-time Fourier transform layer (Since R2021b)
istftLayerInverse short-time Fourier transform layer (Since R2024a)

Related Information

Topics

Featured Examples

Machine Learning and Deep Learning Classification Using Signal Feature Extraction Objects

Machine Learning and Deep Learning Classification Using Signal Feature Extraction Objects

Use signal feature extraction objects and AI-based classification to identify faulty bearing signals in mechanical systems.

Feature Selection Based on Deep Learning Interpretability for Signal Classification Applications

Feature Selection Based on Deep Learning Interpretability for Signal Classification Applications

Use the locally interpretable model-agnostic explanation technique to interpret decision-making processes of a deep learning network.

Human Activity Recognition Using Signal Feature Extraction and Machine Learning

Human Activity Recognition Using Signal Feature Extraction and Machine Learning

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

(Signal Processing Toolbox)

  • Since R2021b
Time-Frequency Feature Embedding with Deep Metric Learning

Time-Frequency Feature Embedding with Deep Metric Learning

Construct wavelet-based feature embeddings to classify EEG signals from persons with and without epilepsy.

Signal Classification Using Wavelet-Based Features and Support Vector Machines

Signal Classification Using Wavelet-Based Features and Support Vector Machines

Classify electrocardiogram signals using features derived from wavelets and an autoregressive model.

(Wavelet Toolbox)