Input Variable Selection Using Independent Component Analysis and Higher Order Statistics

نویسندگان

  • Andrew D. Back
  • Andrzej Cichocki
چکیده

In real world problems of nonlinear model building there may be a number of inputs available for use. However, a common problem is that we do not know which inputs are necessary for the model. Previous methods have difficulties in coping with dependent inputs. In this paper, we propose a novel method of input variable selection based on independent component analysis and higher order cross statistics. Experimental results indicate that the method is capable of giving reliable performance with dependent inputs to nonlinear models.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Selecting inputs for modeling using normalized higher order statistics and independent component analysis

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 w...

متن کامل

Input variable selection using independent component analysis

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 w...

متن کامل

Efficiency Measurement of Clinical Units Using Integrated Independent Component Analysis-DEA Model under Fuzzy Conditions

Background and Objectives: Evaluating the performance of clinical units is critical for effective management of health settings. Certain assessment of clinical variables for performance analysis is not always possible, calling for use of uncertainty theory. This study aimed to develop and evaluate an integrated independent component analysis-fuzzy-data envelopment analysis approach to accurate ...

متن کامل

Selection of multinomial logit models via association rules analysis

In this research, we propose a novel approach for a multinomial logit model selection procedure: specifically, we apply association rules analysis to identifying potential interactions for multinomial logit modeling. Interaction effects are very common in reality, but conventional multinomial logit model selection methods typically ignore them. This is especially true for higher-order interacti...

متن کامل

Bootstrap feature selection in support vector machines for ventricular fibrillation detection

Support Vector Machines (SVM) for classification are being paid special attention in a number of practical applications. When using nonlinear Mercer kernels, the mapping of the input space to a highdimensional feature space makes the input feature selection a difficult task to be addressed. In this paper, we propose the use of nonparametric bootstrap resampling technique to provide with a stati...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1998