KI für DSP
DSP System Toolbox™ bietet Funktionen zur Extraktion von Signalstatistiken und zur Detektion von Signalanomalien mithilfe von Deep-Learning-Netzwerken in Simulink®.
Der Time Feature Extractor-Block extrahiert Zeitbereichseigenschaften des Signals wie Mittelwert, Effektivwert, Standardabweichung, SNR und SINAD.
Der Wavelet Scattering-Block erstellt ein Framework für Wavelet-Zeitstreuung in der Simulink-Umgebung. Verwenden Sie diesen Block, um Merkmale mit niedriger Varianz aus reellwertigen Daten abzuleiten und diese Merkmale dann in Machine-Learning- und Deep-Learning-Anwendungen zu verwenden. Weitere Informationen finden Sie unter Wavelet Scattering (Wavelet Toolbox). Der Wavelet Scattering-Block benötigt Wavelet Toolbox™.
Der Deep Signal Anomaly Detector-Block erkennt Echtzeit-Signalanomalien in Simulink mithilfe eines trainierten Deep-Learning-Netzwerkmodells mit LSTM-Autoencoder (long short-term memory). Sie müssen zunächst ein Detektorobjekt in MATLAB® mithilfe der deepSignalAnomalyDetector-Funktion erstellen und trainieren und daraufhin den Block zur Verwendung dieses Modells in Simulink konfigurieren. Der Deep Signal Anomaly Detector-Block benötigt Deep Learning Toolbox™.
Blöcke
Themen
- Wavelet Scattering (Wavelet Toolbox)
Derive low-variance features from real-valued time series and image data.
- Fault Detection Using Wavelet Scattering and Recurrent Deep Networks (Wavelet Toolbox)
Classify faults in acoustic recordings of air compressors using a wavelet scattering network paired with a recurrent neural network. (Seit R2021b)
- Deployment of Direction-of-Arrival Estimation Using Deep Learning
Generate and deploy code to estimate direction of arrival using deep learning techniques.
Enthaltene Beispiele
Deploy Direction of Arrival Estimation Using Deep Learning on Desktop
Integrate the trained network into Simulink for real-time inference on a desktop environment.
Deploy Direction of Arrival Estimation Using Deep Learning on Raspberry Pi
Deploy the trained model on Raspberry Pi® for resource-constrained applications.
Detect Air Compressor Sounds in Simulink Using Wavelet Scattering
Use the Wavelet Scattering block and a pretrained deep learning network to classify audio signals.
Deploy Wavelet Scattering and TensorFlow Lite Network on a Raspberry Pi Using Simulink
Generate and deploy Raspberry Pi code to detect air compressor sounds using the Wavelet Scattering Simulink block and a pretrained deep learning network.
Fault Detection and Localization in Three-Phase Power Transmission Using Deep Signal Anomaly Detector in Simulink
Detect faults in three-phase power transmission using the Deep Signal Anomaly Detector block.
Detect Anomalies in ECG Data Using Wavelet Scattering and LSTM Autoencoder in Simulink
Use wavelet scattering and deep learning network to detect anomalies in ECG signals.
Real-Time Noise Detection on Raspberry Pi Using Deep Signal Anomaly Detector
Detect the presence of noise on a Raspberry Pi device.
Detect Air Compressor Sounds Using Wavelet Scattering and TensorFlow Lite
Generate and deploy code to detect air compressor sounds using Wavelet Scattering and a TensorFlow Lite deep learning network.
