This research study proposes a novel method for automatic fault prediction from foundry data introducing the so-called Meta Prediction Function (MPF). Kernel Principal Component Analysis (KPCA) is used for dimension reduction. Different algorithms are used for building the MPF such as Multiple Linear Regression (MLR), Adaptive Neuro Fuzzy Inference System (ANFIS), Support Vector Machine (SVM) and Neural Network (NN). We used classical machine learning methods such as ANFIS, SVM and NN for comparison with our proposed MPF. Our empirical results show that the MPF consistently outperform the classical methods.
%0 Journal Article
%1 saadbashiralvi2017efficient
%A Saad Bashir Alvi, Robert Martin
%A Gottschling, Johannes
%D 2017
%E et al, Dhinaharan Nagamalai
%J Computer Science & Information Technology (CS & IT)
%K ANFIS, Fuzzy Inference KPCA Machine, Network, Neural Support System, Vector
%N 7
%P 29-43
%R 10.5121/csit.2017.70703
%T Efficient Use of Hybrid Adaptive Neuro-Fuzzy Inference System Combined with Nonlinear Dimension Reduction Method in Production Processes
%U http://airccse.org/csit/V7N69.html
%V 7
%X This research study proposes a novel method for automatic fault prediction from foundry data introducing the so-called Meta Prediction Function (MPF). Kernel Principal Component Analysis (KPCA) is used for dimension reduction. Different algorithms are used for building the MPF such as Multiple Linear Regression (MLR), Adaptive Neuro Fuzzy Inference System (ANFIS), Support Vector Machine (SVM) and Neural Network (NN). We used classical machine learning methods such as ANFIS, SVM and NN for comparison with our proposed MPF. Our empirical results show that the MPF consistently outperform the classical methods.
%@ 978-1-921987-67-0
@article{saadbashiralvi2017efficient,
abstract = {This research study proposes a novel method for automatic fault prediction from foundry data introducing the so-called Meta Prediction Function (MPF). Kernel Principal Component Analysis (KPCA) is used for dimension reduction. Different algorithms are used for building the MPF such as Multiple Linear Regression (MLR), Adaptive Neuro Fuzzy Inference System (ANFIS), Support Vector Machine (SVM) and Neural Network (NN). We used classical machine learning methods such as ANFIS, SVM and NN for comparison with our proposed MPF. Our empirical results show that the MPF consistently outperform the classical methods.},
added-at = {2017-06-19T03:28:54.000+0200},
author = {Saad Bashir Alvi, Robert Martin and Gottschling, Johannes},
biburl = {https://www.bibsonomy.org/bibtex/23ed1e3a7fe6a88de9d7aaccb3a481239/laimbee},
doi = {10.5121/csit.2017.70703},
editor = {et al, Dhinaharan Nagamalai},
interhash = {45f3a2996b3bcf965d8e75e872057666},
intrahash = {3ed1e3a7fe6a88de9d7aaccb3a481239},
isbn = {978-1-921987-67-0},
issn = {2231 - 5403},
journal = {Computer Science & Information Technology (CS & IT)},
keywords = {ANFIS, Fuzzy Inference KPCA Machine, Network, Neural Support System, Vector},
language = {English},
month = may,
number = 7,
pages = {29-43},
timestamp = {2017-06-19T03:28:54.000+0200},
title = {Efficient Use of Hybrid Adaptive Neuro-Fuzzy Inference System Combined with Nonlinear Dimension Reduction Method in Production Processes },
url = {http://airccse.org/csit/V7N69.html},
volume = 7,
year = 2017
}