嵌入式 AI 系统

基于 ARM^® 的设备和嵌入式 NVIDIA^® GPU 上的深度学习

在硬件上执行和部署深度学习解决方案。

函数

`cwtLayer`	Continuous wavelet transform (CWT) layer （自 R2022b 起）
`modwtLayer`	Maximal overlap discrete wavelet transform (MODWT) layer （自 R2022b 起）
`stftLayer`	Short-time Fourier transform layer （自 R2021b 起）

`dlcwt`	Deep learning continuous wavelet transform （自 R2022b 起）
`dlmodwt`	Deep learning maximal overlap discrete wavelet transform and multiresolution analysis （自 R2022a 起）
`dlstft`	Deep learning short-time Fourier transform （自 R2021a 起）
`cwtfilterbank`	Continuous wavelet transform filter bank
`findchangepts`	Find abrupt changes in signal
`findpeaks`	Find local maxima
`modwt`	Maximal overlap discrete wavelet transform
`risetime`	Rise time of positive-going bilevel waveform transitions
`stft`	Short-time Fourier transform （自 R2019a 起）
`signalFrequencyFeatureExtractor`	Streamline signal frequency feature extraction （自 R2021b 起）
`signalTimeFeatureExtractor`	Streamline signal time feature extraction （自 R2021a 起）
`waveletScattering`	Wavelet time scattering

Deep Learning Code Generation on ARM for Fault Detection Using Wavelet Scattering and Recurrent Neural Networks (Wavelet Toolbox)
Perform acoustic-based fault detection on a Raspberry Pi^® using wavelet scattering and recurrent neural networks.

Use wavelets to classify waveforms on a NVIDIA Jetson^®.

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

Classify human electrocardiogram (ECG) signals by deploying a trained directed acyclic graph (DAG) network.

Generate and deploy a CUDA^® executable to classify electrocardiogram signals using wavelet-derived features.

Create and deploy a Simulink^® model for signal classification using wavelet-based features.

Classify human electrocardiogram signals on a Raspberry Pi using scalograms and a deep convolutional neural network.