Measurements and Feature Extraction
Signal Processing Toolbox™ provides functions that let you measure common distinctive features of a signal. Locate signal peaks and determine their height, width, and distance to neighbors. Measure time-domain features such as peak-to-peak amplitudes and signal envelopes. Measure pulse metrics such as overshoot and duty cycle.
In the frequency domain, measure fundamental, mean, median, and harmonic frequencies, channel bandwidth, and power in a frequency band. Characterize systems by measuring spurious free dynamic range (SFDR), signal-to-noise ratio (SNR), total harmonic distortion (THD), signal to noise and distortion ratio (SINAD), and third-order intercept (TOI).
Extract signal features to enhance key characteristics and reduce data variability and dimensionality when training AI models.
Categories
- Descriptive Statistics
Peaks, RMS level, peak-to-peak amplitude, crest factor, dynamic time warping, CUSUM control chart, edit distance
- Pulse and Transition Metrics
Rise time, fall time, slew rate, overshoot, undershoot, settling time, pulse width, duty cycle
- Spectral Measurements
Channel power, bandwidth, mean frequency, median frequency, harmonic distortion
Related Information
Featured Examples
Classify ECG Signals Using Long Short-Term Memory Networks
Classify heartbeat electrocardiogram data using deep learning and signal processing.
Human Activity Recognition Using Signal Feature Extraction and Machine Learning
Extract features from smartphone sensor signals and use them to classify human activity.
Waveform Segmentation Using Deep Learning
Segment human electrocardiogram signals using time-frequency analysis and deep learning.
Distortion Measurements
Generate 2048 samples of a sinusoid of frequency 2.5 kHz sampled at 50 kHz. Add white Gaussian noise such that the signal-to-noise ratio (SNR) is 80 dB.
Determine Peak Widths
Create a signal that consists of a sum of bell curves. Specify the location, height, and width of each curve.
