Results 51 to 60 of about 708 (167)

A Self‐Attention Autoformer With Period–Trend Decoupling for Power Grid Call Volume Forecasting

Digital Twins and Applications, Volume 3, Issue 1, January/December 2026.
This paper proposes a period–trend decoupled self‐attention Autoformer model for power grid call volume forecasting, in which the seasonal–trend decomposition mechanism of Autoformer is introduced to decompose the original sequence into short‐term seasonal components and long‐term trend components, and the L1 loss is employed to reduce the negative ...
Hao Qin, Kaidong Lin, Shuzhao Xu, Shijian Zhang, Siyuan Peng   +4 more
wiley   +1 more source

Correntropy-Based Constructive One Hidden Layer Neural Network

Algorithms
One of the main disadvantages of the traditional mean square error (MSE)-based constructive networks is their poor performance in the presence of non-Gaussian noises.
Mojtaba Nayyeri, Modjtaba Rouhani, Hadi Sadoghi Yazdi, Marko M. Mäkelä, Alaleh Maskooki, Yury Nikulin   +5 more
doaj   +1 more source

L₁-Norm Robust Regularized Extreme Learning Machine with Asymmetric C-Loss for Regression

Axioms, 2023
Extreme learning machines (ELMs) have recently attracted significant attention due to their fast training speeds and good prediction effect. However, ELMs ignore the inherent distribution of the original samples, and they are prone to overfitting, which ...
Qing Wu, Fan Wang, Yu An, Ke Li
doaj   +1 more source

Robust Sub‐Filter Based APA With Parametric Welsch Function for Acoustic Echo Cancellation Under Impulsive Noise

Electronics Letters, Volume 62, Issue 1, January/December 2026.
Acoustic echo cancellation (AEC) in actual communication systems is challenging due to highly correlated inputs, impulsive disturbances, and computational limitations. The traditional Affine Projection Algorithm (APA) is better than the Normalised Least Mean Square method, although it involves matrix inversion complexity and is susceptible to outliers (
Gagandeep Singh, Asutosh Kar, Vasundhara, Monorama Swain, Jesper Rindom Jensen, Mads Græsbøll Christensen   +5 more
wiley   +1 more source

Deep Robust Nonnegative Matrix Factorization for Hierarchical Data Representation

IET Image Processing, Volume 20, Issue 1, January/December 2026.
1. A hierarchical nonnegative matrix factorization method is proposed, which expands the single‐layer data representation to multiple layers, helping to explore the data's structure. 2. The L21 norm increases the robustness of the model, making the algorithm insensitive to noise. 3.
Song Yang, Li Sun, Dezhou Kong, Yun Wang
wiley   +1 more source

Complex Correntropy Applied to a Compressive Sensing Problem in an Impulsive Noise Environment

IEEE Access, 2019
Correntropy is a similarity function capable of extracting high-order statistical information from data. It has been used in different kinds of applications as a cost function to overcome traditional methods in non-Gaussian noise environments. One of the
Joao P. F. Guimaraes, Felipe B. Da Silva, Aluisio I. R. Fontes, Ricardo Von Borries, Allan De M. Martins   +4 more
doaj   +1 more source

A Cooperative Adaptive Kalman Filter for Robust Terrain‐Referenced Navigation in Complex Environments

IET Radar, Sonar &Navigation, Volume 20, Issue 1, January/December 2026.
This paper introduces a Cooperative Adaptive Kalman Filter (CAKF) to prevent filter divergence in a Terrain‐Aided Navigation system by synergistically adapting its process noise (Q), measurement noise (R), and state covariance (P) based on vehicle manoeuvres and terrain quality.
Liyue Liang, Daojie Yu, Jianping Du, Yijie Bai, Tao Li, Jiale Zhou   +5 more
wiley   +1 more source

A TC‐Based Multicomponent LFM Signal Characterization Method Under Impulsive Noise and Its Application

IET Signal Processing, Volume 2026, Issue 1, 2026.
The burst‐like and high‐amplitude characteristics of impulsive noise, which markedly differ from those of Gaussian noise, render methods based on the Gaussian assumption unable to accurately characterize signals under impulsive noise. Moreover, when dealing with multicomponent signal, existing impulsive noise suppression methods inevitably introduce ...
Weiwei Shang, Yong Guo, Lidong Yang, Tianyuan Liu   +3 more
wiley   +1 more source

Imagined Chinese Speech Decoding Based on Initials and Finals From EEG Activity

IET Signal Processing, Volume 2026, Issue 1, 2026.
Brain‐computer interface (BCI) plays an important role in various fields, such as neuroscience, rehabilitation, and machine learning. The silent BCI, which can reconstruct inner speech from neural activity, holds great promise for aphasia patients. In this paper, we design an imagined Chinese speech experimental paradigm based on initials and finals ...
Jingyu Gu, Jiuchuan Jiang, Qian Cai, Haixian Wang, Chao Zhai   +4 more
wiley   +1 more source

Generalized Complex Correntropy: Application to Adaptive Filtering of Complex Data

IEEE Access, 2018
Adaptive filtering for complex data has received more attentions recently. As a similarity measure for the complex random variables, complex correntropy has been shown robustness in the design of adaptive filter.
Guobing Qian, Shiyuan Wang
doaj   +1 more source