GMDH2: Binary Classification via GMDH-Type Neural Network Algorithms-R Package and Web-Based Tool


DAĞ O., KARABULUT E., Alpar R.

INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS, cilt.12, sa.2, ss.649-660, 2019 (SCI-Expanded) identifier identifier

Özet

Group method of data handling (GMDH)-type neural network algorithms are the self-organizing algorithms for modeling complex systems. GMDH algorithms are used for different objectives; examples include regression, classification, clustering, forecasting, and so on. In this paper, we present GMDH2 package to perform binary classification via GMDH-type neural network algorithms. The package offers two main algorithms: GMDH algorithm and diverse classifiers ensemble based on GMDH (dce-GMDH) algorithm. GMDH algorithm performs binary classification and returns important variables. dce-GMDH algorithm performs binary classification by assembling classifiers based on GMDH algorithm. The package also provides a well-formatted table of descriptives in different format (R, LaTeX, HTML). Moreover, it produces confusion matrix and related statistics, and scatter plot (2D and 3D) with classification labels of binary classes to assess the prediction performance. Moreover, a user-friendly web-interface of the package is provided especially for non-R users. (c) 2019 The Authors. Published by Atlantis Press SARL.