Results 71 to 80 of about 50,949 (199)
IET Control Theory &Applications, Volume 19, Issue 1, January/December 2025.This work addresses the issue of rejection delay due to DoS attacks triggered by historical measurements during the transmission of a large amount of measurement data in WECS‐based networked microgrids. We propose a novel robust SRCKF method, designated as MCC‐SRCKF, which incorporates MCC into the SRCKF structure of DSE.
Xiao Hu +4 more
wiley +1 more source
EntropyAiming at the problem that sparse channel estimation in underwater acoustic communication is susceptible to complex multipath propagation, non-Gaussian impulsive noise, and channel time variations, this paper proposes a bidirectional proportionate ...
Xiao-Chen Chen +3 more
doaj +1 more source
KLMS‐Net: Deep unrolling for kernel least mean square algorithm
Electronics Letters, Volume 61, Issue 1, January/December 2025.This letter proposes a novel network framework based on the deep unrolling of kernel least mean square (KLMS‐Net). KLMS‐Net transforms the iterative process of KLMS into the forward propagation of deep neural networks, which learn the implicit feature mappings in a model‐driven manner, providing deep neural networks with explicit interpretability ...
Yu Tang +5 more
wiley +1 more source
Robust Capsule Network Based on Maximum Correntropy Criterion for Hyperspectral Image Classification
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020 Recently, deep learning-based algorithms have been widely used for classification of hyperspectral images (HSIs) by extracting invariant and abstract features.
Heng-Chao Li +5 more
doaj +1 more source
IET Electric Power Applications, Volume 19, Issue 1, January/December 2025.This paper proposes an attention‐guided semi‐supervised model for transformer fault diagnosis using vibration‐acoustic data fusion. The model employs multilevel attention and a consistency learning strategy to enhance diagnostic accuracy under limited labelled data.
Yanfei Sun +3 more
wiley +1 more source
A Student's T Distribution‐Based Filter Design for SINS/GNSS With Heavy‐Tailed Noise
IET Electric Power Applications, Volume 19, Issue 1, January/December 2025.To reduce the affection of outliers caused by heavy‐tailed noise, the noise model is constructed by the Student's T distribution rather than the Gaussian distribution, and the related probability density functions (PDF) are adaptively modelled as student's T PDFs with different DoF parameters.
Menghao Qian, Wei Chen, Ruisheng Sun
wiley +1 more source
IEEE Access, 2020 This paper focuses on the problem of distributed adaptive estimation over dynamic multi-task networks, where a set of nodes is required to collectively estimate some parameters of interest from noisy measurements.
Qing Shi +3 more
doaj +1 more source
IET Generation, Transmission &Distribution, Volume 19, Issue 1, January/December 2025.This paper proposes a robust, user‐type‐specific anomaly detection method for electricity usage. First, after data cleaning and preprocessing, a correntropy‐based K‐means clustering method is proposed to perform robust clustering, effectively separating users with non‐Gaussian noisy data.
Teng Zhang +4 more
wiley +1 more source
Quaternion Recurrent Neural Network with Real-Time Recurrent Learning and Maximum Correntropy Criterion [PDF]
IEEE International Joint Conference on Neural NetworkWe develop a robust quaternion recurrent neural network (QRNN) for real-time processing of 3D and 4D data with outliers. This is achieved by combining the real-time recurrent learning (RTRL) algorithm and the maximum correntropy criterion (MCC) as a loss
Pauline Bourigault +2 more
semanticscholar +1 more source
Regularized Maximum Correntropy Criterion Kalman Filter for Uncalibrated Visual Servoing in the Presence of Non-Gaussian Feature Tracking Noise. [PDF]
Sensors (Basel), 2023 Leite GR, Araújo ÍBQ, Martins AM.
europepmc +1 more source