Results 51 to 60 of about 78,334 (302)

Parameter optimization of support vector machine based on improved cuckoo search algorithm

Xi'an Gongcheng Daxue xuebao, 2022
To solve the problem of difficult selection of penalty factor and kernel function parameters of Support Vector Machine (SVM), an improved cuckoo search algorithm (GFCS) was proposed to optimize SVM parameter model (GFCS-SVM) . The GFCS algorithm improves
GU Jiaxin, HE Xingshi, LIU Qing
doaj   +1 more source

A Permutation Approach for Selecting the Penalty Parameter in Penalized Model Selection [PDF]

Biometrics, 2015
Summary We describe a simple, computationally efficient, permutation-based procedure for selecting the penalty parameter in LASSO-penalized regression. The procedure, permutation selection, is intended for applications where variable selection is the primary focus, and can be applied in a variety of structural settings, including that of
Sabourin, Jeremy A., Valdar, William, Nobel, Andrew B.   +2 more
openaire   +3 more sources

Compact and stable discontinuous Galerkin methods for convection-diffusion problems [PDF]

, 2012
We present a new scheme, the compact discontinuous Galerkin 2 (CDG2) method, for solving nonlinear convection-diffusion problems together with a detailed comparison to other well-accepted DG methods.
Dedner, A., Dedner, Andreas, Klöfkorn, R., Brdar, S.   +3 more
core   +1 more source

Impact of Asymptomatic Intracranial Hemorrhage on Outcome After Endovascular Stroke Treatment

Annals of Clinical and Translational Neurology, EarlyView.
ABSTRACT Background Endovascular treatment (EVT) achieves high rates of recanalization in acute large‐vessel occlusion (LVO) stroke, but functional recovery remains heterogeneous. While symptomatic intracranial hemorrhage (sICH) has been well studied, the prognostic impact of asymptomatic intracranial hemorrhage (aICH) after EVT is less certain ...
Shihai Yang, Chengsong Yue, Zhuang Li, Xiaolei Shi, Haoxuan Zhu, Jie Yang, Linyu Li, Jiaxing Song, Shitao Fan, Gaoming Li, Wenzhe Sun, Zhixian Ye, Jiacheng Huang, Dahong Yang, Jinfu Ma, Xu Xu, Zhixi Wang, Lilan Wang, Guojian Liu, Fengli Li, Changwei Guo, Li Qi, Wenjie Zi   +22 more
wiley   +1 more source

Manifold learning via Multi-Penalty Regularization [PDF]

, 2018
Manifold regularization is an approach which exploits the geometry of the marginal distribution. The main goal of this paper is to analyze the convergence issues of such regularization algorithms in learning theory.
geroge patton (4780518)
core   +3 more sources

Distributed power supply restoration method for distribution network based on improved ADMM

Diance yu yibiao
In order to speed up the solving efficiency of the power supply restoration method of distribution network after failure, this paper presents a multi-period distributed power supply restoration method for distribution network based on improved ...
HAI Di, ZHANG Ruiying, CHENG Jiangdong, DUAN Yu, WANG Yingzi, LIN Lin   +5 more
doaj   +1 more source

2DNMR data inversion using locally adapted multi-penalty regularization [PDF]

, 2021
Geologists and Reservoir Engineers routinely use time-domain nuclear magnetic resonance (NMR) to learn about the porous structure of rocks that hold underground fluids.
Bortolotti V., Landi G., Zama F.
core   +1 more source

Paramagnetic Rim Lesions Are Associated With Trans‐Synaptic Degeneration of the Visual Pathway in Multiple Sclerosis

Annals of Clinical and Translational Neurology, EarlyView.
ABSTRACT Objectives Retrograde trans‐synaptic degeneration (rTSD) from posterior visual pathway lesions in multiple sclerosis (MS) is characterized by hemi‐macular ganglion cell‐inner plexiform layer (GCIPL) thinning and contralateral visual field loss.
Abdul Jaber Tayem, Angel Liu, Sargis Manukyan, Mustafa Subhi, Elaina Luskin, Bryan Quah, Sreekanth Madhusoodhanan Nair, Arzu C. Has Silemek, Gabriela Zabala, Yujie Cui, Laura Locke, Paula Barreras, Marwa Kaisey, Vinicius Calsavara, Daniel S. Reich, Nancy L. Sicotte, Pascal Sati, Omar Al‐Louzi   +17 more
wiley   +1 more source

Completely Smooth Lower-Order Penalty Approach for Solving Second-Order Cone Mixed Complementarity Problems

Mathematics
In this paper, a completely smooth lower-order penalty method for solving a second-order cone mixed complementarity problem (SOCMCP) is studied. Four distinct types of smoothing functions are taken into account.
Qiong Wu, Zijun Hao
doaj   +1 more source

Embedding negative structures to model holes and cut-outs [PDF]

, 2009
It has now been established that geometric boundary conditions and continuity conditions can be modelled by using either positive or negative stiffness or inertia type penalty term [1-5].
Ilanko, Sinniah
core