EDN

FFT convolution and the overlap-add method

This article presents two important DSP techniques, the overlap-add method, and FFT convolution. The overlap-add method is used to break long signals into smaller segments for easier processing. FFT ...
IEEE

Morphological Convolution Undecimated Wavelet: A Novel Frequency Demodulation Analysis Method for Bearing Fault Diagnosis

Abstract: The morphological undecimated wavelet (MUW) is an efficient feature extraction algorithm for bearing fault diagnosis. Currently, the researched MUW is mainly focused on background noise ...
IEEE

An Efficient Method For Generic Dsp Implementation Of Dilated Convolution

Abstract: Dilated convolution is a well-known technique used in neural networks algorithms in AI/ML applications to increase receptive-field under analysis. Dilated convolution layer has an inherent ...
Scientific Research Publishing

Plunger Pump Fault Diagnosis Method Based on Wavelet Convolution and Multi-Head Self-Attention Mechanism for Multi-Channel Feature Fusion ()

To address the issues of low accuracy, high dependence on prior knowledge, and poor adaptability in fusing multi-channel features in existing plunger pump fault diagnosis methods, a new method based ...
GitHub

LF-Disparity-Estimation-VS-Sub

LF disparity estimation dataset and view-selective convolution-based cost volume construction method We propose the TO-LF dataset, designed to address challenges in complex occlusion scenarios and ...