Results 131 to 140 of about 65,893 (254)

Spectral methods for Neural Integral Equations. [PDF]

Ric Mat
Zappala E.
europepmc   +1 more source

A Hybrid Fuzzy–Support Vector Machine Framework for Real‐Time Dust Detection and Thermal Mapping in Photovoltaic Panels

Energy Science &Engineering, EarlyView.
A hybrid Fuzzy–SVM framework for real‐time dust detection and thermal mapping in PV panels. ABSTRACT Dust accumulation significantly degrades the energy output of photovoltaic (PV) panels, particularly in arid and semi‐arid regions. While existing studies have separately explored image‐based dust detection, environmental modeling, and machine learning (
Debasish Sarker, S. M. Rezaul Karim, MD. Shouquat Hossain, Md. Moshaddek Hossain, Md. Monirul Kabir   +4 more
wiley   +1 more source

Diabetic retinopathy severity detection using an improved Whale optimization algorithm and convolutional Kolmogorov-Arnold network. [PDF]

Front Med (Lausanne)
Dutta AK, Aljarallah NA, Sait ARW.
europepmc   +1 more source

Ensemble Deep Learning–Based Wind Power Forecasting With Self‐Adaptive Osprey Optimization Algorithm

Energy Science &Engineering, EarlyView.
Design of Self‐Adaptive Osprey (SAO) algorithm: The novel SAO algorithm is designed by integrating the exploration capability of the conventional Osprey algorithm by including the self‐adaptiveness for enhancing the convergence rate. Ensemble Deep Learning for wind power forecasting: The wind forecasting is employed using the proposed Ensemble learning
Johncy Bai Johnson, Sivarani Thankamony Saradha Devi, Kumar Chandrasekaran, Sourav Barua   +3 more
wiley   +1 more source

Fractional-order neural network for detecting process deviations in optical fiber cable manufacturing. [PDF]

Sci Rep
Gomolka Z, Zeslawska E, Olbrot L.
europepmc   +1 more source

Machine Learning‐Driven Classification and Production Capacity Prediction of Tight Sandstone Reservoirs: A Case Study of the Taiyuan Formation, Ordos Basin

Energy Science &Engineering, EarlyView.
On the basis of core and log data, a Bayesian‐Optimized Random Forest model achieved 92.76% accuracy in classifying tight sandstone reservoirs. A gray relational analysis‐derived evaluation index shows > 80% consistency with actual gas zones. ABSTRACT Tight sandstone gas (TSG), an unconventional oil–gas resource, has heterogeneous reservoirs ...
Yin Yuan, Haijiao Fu, Detian Yan, Gang Wang, Shuguang Yang, Mengmeng Liu, Qingling Jiang, Xiaoming Wang, Wei Wang   +8 more
wiley   +1 more source

SimpleKANSleepNet: a Kolmogorov-Arnold network based sleep stage classification method. [PDF]

Front Bioinform
Ji X, Wang L, Zhou Y.
europepmc   +1 more source

A Deep Learning Framework for Forecasting Medium‐Term Covariance in Multiasset Portfolios

Journal of Forecasting, EarlyView.
ABSTRACT Forecasting the covariance matrix of asset returns is central to portfolio construction, risk management, and asset pricing. However, most existing models struggle at medium‐term horizons, several weeks to months, where shifting market regimes and slower dynamics prevail.
Pedro Reis, Ana Paula Serra, João Gama
wiley   +1 more source

Kolmogorov GAM Networks Are All You Need! [PDF]

Entropy (Basel)
Polson S, Sokolov V.
europepmc   +1 more source

Electricity Price Prediction Using Multikernel Gaussian Process Regression Combined With Kernel‐Based Support Vector Regression

Journal of Forecasting, EarlyView.
ABSTRACT This paper presents a new hybrid model for predicting German electricity prices. The algorithm is based on a combination of Gaussian process regression (GPR) and support vector regression (SVR). Although GPR is a competent model for learning stochastic patterns within data and for interpolation, its performance for out‐of‐sample data is not ...
Abhinav Das, Stephan Schlüter, Lorenz Schneider   +2 more
wiley   +1 more source