Vorverarbeitung und Merkmalsextraktion

Extrahieren von Signalmerkmalen in der Zeit-, Frequenz- und Zeit-Frequenz-Domäne

Extrahieren Sie bedeutsame Signalmerkmale zur Verwendung in Machine-Learning-Modellen mithilfe von Befehlszeilenfunktionen oder der Signal Feature Extractor-App.

Apps

EDF File Analyzer	View EDF or EDF+ files (Seit R2021a)
Signal Analyzer	Visualize and compare multiple signals and spectra
Signal Labeler	Label signal attributes, regions, and points of interest
Signal Feature Extractor	Extract and analyze signal features (Seit R2025a)

Funktionen

alle erweitern

Signalentrauschung und -Rekonstruktion

`detrend`	Remove polynomial trend
`envelope`	Signal envelope
`lowpass`	Lowpass-filter signals
`smoothdata`	Smooth noisy data
`cwtmag2sig`	Signal reconstruction from CWT magnitude (Seit R2023b)
`stftmag2sig`	Signal reconstruction from STFT magnitude

Signal- und Wavelet-Merkmale

`cwtfilterbank`	Continuous wavelet transform filter bank
`findpeaks`	Find local maxima
`findchangepts`	Find abrupt changes in signal
`modwt`	Maximal overlap discrete wavelet transform
`risetime`	Rise time of positive-going bilevel waveform transitions
`stft`	Short-time Fourier transform
`signalTimeFeatureExtractor`	Streamline signal time feature extraction (Seit R2021a)
`signalFrequencyFeatureExtractor`	Streamline signal frequency feature extraction (Seit R2021b)
`signalTimeFrequencyFeatureExtractor`	Streamline signal time-frequency feature extraction (Seit R2024a)
`timeFrequencyScattering`	Joint time-frequency scattering (Seit R2024b)
`waveletScattering`	Wavelet time scattering

Datastores und Datenverwaltung

`audioDatastore`	Datastore for collection of audio files
`arrayDatastore`	Datastore for in-memory data
`imageDatastore`	Datastore for image data
`signalDatastore`	Datastore for collection of signals
`edfheader`	Create header structure for EDF or EDF+ file (Seit R2021a)
`edfinfo`	Get information about EDF/EDF+ file
`edfread`	Read data from EDF/EDF+ file
`edfwrite`	Create or modify EDF or EDF+ file (Seit R2021a)
`paddata`	Pad data by adding elements (Seit R2023b)
`resize`	Resize data by adding or removing elements (Seit R2023b)
`trimdata`	Trim data by removing elements (Seit R2023b)

Differenzierbare Signalverarbeitung

`dlcwt`	Deep learning continuous wavelet transform (Seit R2022b)
`dlicwt`	Deep learning inverse continuous 1-D wavelet transform (Seit R2024b)
`dldwt`	Differentiable discrete wavelet transform (Seit R2025a)
`dlidwt`	Differentiable inverse discrete wavelet transform (Seit R2025a)
`dlmodwt`	Deep learning maximal overlap discrete wavelet transform and multiresolution analysis (Seit R2022a)
`dlstft`	Deep learning short-time Fourier transform (Seit R2021a)
`dlistft`	Deep learning inverse short-time Fourier transform (Seit R2024a)
`cwtLayer`	Continuous wavelet transform layer (Seit R2022b)
`icwtLayer`	Inverse continuous wavelet transform layer (Seit R2024b)
`modwtLayer`	Maximal overlap discrete wavelet transform layer (Seit R2022b)
`stftLayer`	Short-time Fourier transform layer (Seit R2021b)
`istftLayer`	Inverse short-time Fourier transform layer (Seit R2024a)

Themen

View, Preprocess, and Write EDF File (Signal Processing Toolbox)
View and preprocess data stored in an EDF file.
Manage Data Sets for Machine Learning and Deep Learning Workflows (Signal Processing Toolbox)
Organize, access, and manage data sets for different AI applications.
Accelerate Signal Feature Extraction and Classification Using a Parallel Pool of Workers (Signal Processing Toolbox)
Use parallel computing to extract signal multidomain features for bearing fault detection. (Seit R2024b)
Accelerate Signal Feature Extraction and Classification Using a GPU (Signal Processing Toolbox)
Use a graphical processing unit (GPU) to extract signal multidomain features for bearing fault detection. (Seit R2024b)

Enthaltene Beispiele

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.

Live Script öffnen

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.

Live Script öffnen

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)

Seit R2021b

Time-Frequency Feature Embedding with Deep Metric Learning

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

Live Script öffnen

Signal Classification Using Wavelet-Based Features and Support Vector Machines

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

(Wavelet Toolbox)