Dual-path AI framework spots hidden anomalies in industrial time series data
Researchers at Guangdong University of Technology have developed DP-MVAD, a dual-path multi-view framework that disentangles trends from perturbations and fuses ...
Researchers at Guangdong University of Technology have developed DP-MVAD, a dual-path multi-view framework that disentangles trends from perturbations and fuses ...
Researchers at Saudi Electronic University have developed XCardioPulmoNet, an explainable deep learning framework that classifies heart and lung sounds with ...
A new simulation study compares Fourier, wavelet, and direct time-domain fitting methods for analyzing short and non-stationary NMR signals, revealing ...
A new multi-stream deep learning framework called MS-AtroNet combines convolutional, state-space, wavelet, and evidential components to classify Alzheimer's MRI slices ...
Researchers at Linyi University have combined wavelet decomposition with denoising diffusion models to forecast urban traffic flow more accurately across ...
Researchers in China have developed WEM-Mamba, a wavelet-enhanced state space model that classifies rotator cuff tears from plain shoulder X-rays ...
A new deep learning and ensemble learning framework reaches up to 93.04% accuracy in estimating aboveground biomass across three contrasting ...
Researchers in Chongqing have developed a wavelet-guided deep learning framework that coordinates frequency-domain and spatial cues to sharply localize changes ...
Researchers have developed an empirical model that predicts the destructive velocity pulses of near-fault ground motion from earthquake magnitude, distance, ...
Researchers have built a WaveNet-CNN framework that fuses spatial and frequency-domain features with a dual moth flame optimization algorithm to ...
© 2025 Scienmag - Science Magazine
© 2025 Scienmag - Science Magazine