Proceedings Article10.1109/IJCNN.1999.831089
Input variable selection using independent component analysis
Andrew D. Back,Thomas Trappenberg +1 more
- 10 Jul 1999
- Vol. 2, pp 989-992
TL;DR: This paper proposes a novel model-free algorithm for input variable selection using independent component analysis and higher order cross statistics that is capable of giving reliable performance and that it outperforms other approaches when the inputs are dependent.
read more
Abstract: The problem of input variable selection is well known in the task of modeling real world data. In this paper we propose a novel model-free algorithm for input variable selection using independent component analysis and higher order cross statistics. Experimental results are given which indicate that the method is capable of giving reliable performance and that it outperforms other approaches when the inputs are dependent.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Input determination for neural network models in water resources applications. Part 1—background and methodology
TL;DR: The input determination methodology is applied to a real-world case study in order to determine suitable model inputs for forecasting salinity in the River Murray, South Australia, 14 days in advance.
572
Independent component ordering in ICA time series analysis
Yiu-ming Cheung,Lei Xu +1 more
TL;DR: This paper proposes an alternative approach to order the components according to their joint contributions in data reconstruction, which naturally leads the component ordering to a typical combinatorial optimization problem, whereby the underlying optimum ordering can be found in an exhaustive way.
111
Feature Extraction Using ICA
Nojun Kwak,Chong-Ho Choi,Jin-Young Choi +2 more
- 21 Aug 2001
TL;DR: A new feature extraction algorithm using independent component analysis (ICA) for classification problems can be used in solving supervised classification problems to get new features which are made as independent from each other as possible and also convey the output information faithfully.
Artificial neural network in estimation of battery state of-charge (SOC) with nonconventional input variables selected by correlation analysis
Cheng-Hui Cai,Dong-Du,Zhi-Yu Liu,Hua Zhang +3 more
- 04 Nov 2002
TL;DR: In this article, a three-layer feed-forward backpropagation ANN is presented to estimate and predict the battery state-of-charge with nonconventional input variables selected, and the results obtained are compared.
40
The DNA of security return
TL;DR: Factor models can estimate the systematic risk, and there exist several methods to find out the number of factors in security returns, but factors in the aforementioned articles are not independent, and at best uncorrelated.
22
References
Dimension reduction by local principal component analysis
TL;DR: A local linear approach to dimension reduction that provides accurate representations and is fast to compute is developed and it is shown that the local linear techniques outperform neural network implementations.
788
•Book
Kendall's Advanced Theory of Statistics : Volume 1 Distribution Theory
Alan Stuart,J. Keith Ord,Maurice Kendall +2 more
- 15 Nov 1986
TL;DR: In this article, the authors present a guide to the kendall advanced theory of statistics volume 1 distribution theory, which can be used to obtain the book quickly and easily, if necessary.
561
•Proceedings Article
Fast Pruning Using Principal Components
Asriel U. Levin,Todd K. Leen,John Moody +2 more
- 29 Nov 1993
TL;DR: The method, "Principal Components Pruning (PCP)", is based on principal component analysis of the node activations of successive layers of the network and requires no network retraining and does not involve calculating the full Hessian of the cost function.
Blind separation of sources, Part 1: an adaptive algorithm based on neuromimetic architecture
Christian Jutten,Jeanny Hérault +1 more
TL;DR: A new concept, that of INdependent Components Analysis (INCA), more powerful than the classical Principal components Analysis (in decision tasks) emerges from this work.