K
Kevin McFall
Researcher at Kennesaw State University
Publications - 36
Citations - 392
Kevin McFall is an academic researcher from Kennesaw State University. The author has contributed to research in topics: Boundary value problem & Artificial neural network. The author has an hindex of 7, co-authored 36 publications receiving 268 citations. Previous affiliations of Kevin McFall include Pennsylvania State University & Southern Polytechnic State University.
Papers
More filters
Journal ArticleDOI
Artificial Neural Network Method for Solution of Boundary Value Problems With Exact Satisfaction of Arbitrary Boundary Conditions
Kevin McFall,J. R. Mahan +1 more
TL;DR: The approximate ANN solution automatically satisfies BCs at all stages of training, including before training commences, due to its unconstrained nature and because automatic satisfaction of Dirichlet BCs provides a good starting approximate solution for significant portions of the domain.
Journal ArticleDOI
A Blockchain and AutoML Approach for Open and Automated Customer Service
Zhi Li,Hanyang Guo,Wai Ming Wang,Yijiang Guan,Ali Vatankhah Barenji,George Q. Huang,Kevin McFall,Xin Chen +7 more
TL;DR: An open and automated customer service platform based on Internet of things, blockchain, and automated machine learning (AutoML) is proposed, which is adopted to automate the data analysis processes for reducing the reliance of costly experts.
Journal ArticleDOI
Automated design parameter selection for neural networks solving coupled partial differential equations with discontinuities
TL;DR: An automated design parameter selection process is developed to choose a single ANN from an ensemble comprising numerous combinations of design parameters and random starting weights and biases, which provides low error solutions for the three different thermal-fluid science example problems explored, including the Navier–Stokes equations.
Journal ArticleDOI
Software Effort Estimation Using a Neural Network Ensemble
TL;DR: Software effort estimation models using Artificial Neural Network (ANN) ensembles and regression analysis are developed based on data collected from 163 software development projects to achieve superior effort estimation results.
Journal ArticleDOI
Artificial Neural Networks in Radiation Heat Transfer Analysis
TL;DR: In this article, Artificial Neural Networks (ANNs) have been used to estimate the radiation distribution factor matrices and their subsequent use in radiation heat transfer calculations, without the need to perform a new ray trace for each value of emissivity.