16 results
Search Results
Now showing 1 - 10 of 16
Publication Metadata only Analysis of comparisons for forecasting gold price using neural network, radial basis function network and support vector regression(2014-01-01) Khanoksin Suranart; Supaporn Kiattisin; Adisorn Leelasantitham; Mahidol UniversityThis research is done to study and analyze the comparison for forecasting the gold price using Neural Network, Radial Basis Function Network, and Support Vector Regression. Which the neural network radial basis function network and support vectorPublication Metadata only Effectiveness of different spatial interpolators in estimating heavy metal contamination in shallow groundwater: a case study of arsenic contamination in Hanoi, Vietnam(2011-04) Pham Quy Giang; Kanchana Nakhapakorn; กาญจนา นาคะภากร; Achara Ussawarujikulchai; Mahidol University. Faculty of Environment and Resource Studiesin shallow groundwater, (2) generate risk map and compare effectiveness of different spatial interpolation approaches including Kriging, IDW and Radial Basis Function of Geographic Information System (GIS) in estimating arsenic concentrationPublication Metadata only Prediction of soil nitrogen content using E-nose and radial basis function(2019-01-18) Jigme Norbu; Theerapat Pobkrut; Treenet Thepudom; Thinley Namgyel; Teerayut Chaiyasit; Yu Thazin; Teerakiat Kerdcharoen; Mahidol University, e-nose coupled with Radial Basis Function (RBF) is employed to determine the amount of nitrogen (N) which is one of the main nutrients in the soil. The results demonstrate that not only does the e-nose clearly discriminate the odors of soilPublication Metadata only Monte Carlo simulations of a magnesium ion in liquid ammonia(1992-05-15) Supot Hannongbua; Bernd M. Rode; Mahidol University; University of InnsbruckAn infinitely dilute solution of Mg(II) in ammonia solution is studied by Monte Carlo simulations for two temperatures, using a newly developed Mg(II)-ammonia potential function based on ab initio calculations with a DZP basis set. The structure... of the solution is described by radial and angular distribution functions (RDF). The first shell coordination number of 8 remains constant upon increasing the temperature from 235 to 277 K. A small peak is observed in the Mg(II)-nitrogen RDF between the firstPublication Metadata only Bagging of Duo Output Neural Networks for Single Output Regression Problem(2010-01-01) Somkid Amornsamankul; Pawalai Kraipeerapun; Mahidol University; Ramkhamhaeng Universityneural networks, and the ensemble of support vector machine with linear, polynomial, and radial basis function kernels. © 2010 IEEE.Publication Metadata only Solving regression problem with complementary neural networks and an adjusted averaging technique(2010-12-01) Pawalai Kraipeerapun; Sathit Nakkrasae; Chun Che Fung; Somkid Amornsamankul; Ramkhamhaeng University; Murdoch University; Mahidol University; South Carolina Commission on Higher Educationindustry. We found that our proposed technique provides better performance when compared to the traditional CMTNN, backpropagation neural network, and support vector regression with linear, polynomial, and radial basis function kernels. © 2010 SpringerPublication Metadata only Applying duo output neural networks to solve single output regression problem(2009-12-01) Pawalai Kraipeerapun; Somkid Amornsamankul; Chun Che Fung; Sathit Nakkrasae; Ramkhamhaeng University; Mahidol University; Murdoch Universitywith linear, polynomial, and radial basis function kernels. © 2009 Springer-Verlag Berlin Heidelberg.Publication Metadata only Quantitative structure-property relationship study of spectral properties of green fluorescent protein with support vector machine(2013-01-05) Chanin Nantasenamat; Kakanand Srungboonmee; Saksiri Jamsak; Natta Tansila; Chartchalerm Isarankura-Na-Ayudhya; Virapong Prachayasittikul; Mahidol University; Prince of Songkla University. Such descriptors were mapped onto a higher dimensional space via kernel functions (e.g. linear, polynomial and radial basis function kernels) and learning is then performed using SVM. The predicted spectral properties were well correlated with their experimentalPublication Metadata only The hydration structure of 18-crown-6/K+complex as studied by Monte Carlo simulation using ab initio fitted potential(2006-09-01) Sriprajak Krongsuk; Teerakiat Kerdcharoen; Supot Hannongbua; Center for Nanoscience and Nanotechnology; Mahidol Universitythe structural properties of the complex in an aqueous solution using the Monte Carlo simulation method. The radial distribution function (RDF) centered at K+to the oxygen atom of water shows a sharp first peak at 2.88 Å. The corresponding coordination number...The intermolecular potential between a 18-crown-6/K+complex and a water molecule is derived from 1200 energy points obtained from quantum chemical calculations using the 6-31G** basis set. The ab initio fitted potential was then applied to studyPublication Metadata only Prediction of intracerebral hemorrhage following thrombolytic therapy for acute ischemic stroke using multiple artificial neural networks(2012-03-01) Permphan Dharmasaroja; Pornpatr A. Dharmasaroja; Mahidol University; Faculty of Medicine, Thammasat University, and imaging data using multiple ANN models. Methods: Models for radial basis function (RBF), multilayer perceptron (MLP), probabilistic neural network (PNN), and support vector machine (SVM) were generated to analyze 194 datasets with 29 predictive variables