An online isotonic separation with cascade architecture for binary classification

[Display omitted] •Cascade Isotonic separation is an online algorithm to construct model on large data.•It provides an exact solution for the large scale LPP.•The data chunk are divided into partitions based on dominance property and trained using cascade structure.•Results prove that cascade-IS out...

Full description

Saved in:
Bibliographic Details
Published in:Expert systems with applications 2020-11, Vol.157, p.113466, Article 113466
Main Authors: Malar, B., Nadarajan, R.
Format: Article
Language:English
Subjects:
Algorithms
Cascade Isotonic separation
Cascading
Classification
Computing time
Datasets
Isotonic separation
Linear programming
Partitions
Separation
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:[Display omitted] •Cascade Isotonic separation is an online algorithm to construct model on large data.•It provides an exact solution for the large scale LPP.•The data chunk are divided into partitions based on dominance property and trained using cascade structure.•Results prove that cascade-IS outperforms its counterparts in terms of model, training time and performance measures. Isotonic separation (IS) is a non-parametric classification technique which constructs an isotonic function from ordered data. The rationale is to convert partially isotonic data into isotonic using a linear programming problem (LPP) and partition the input space into isotonic and non-isotonic regions to make predictions easier. Despite the widespread applications of IS in diverse domains where monotonicity exists, it has certain limitations: Firstly, computing time and the constraints of the LPP in isotonic separation increase polynomially as size of the data increases and it is highly complex to solve the LPP and obtain the model on large data sets. In order to support dynamic stream data and address the computational overhead and size of the LPP issues, this paper proposes an online isotonic separation algorithm called Cascade-IS (CIS) for binary classification. The rationale behind CIS is that it splits the data set into a sequence of partitions and models are obtained and combined in cascade. Statistical and experimental analysis are done on datasets with isotonic properties and the results prove that CIS is superior to its variants in terms of training time, performance measures and number of constraints in the LPP.
ISSN:0957-4174
1873-6793
DOI:10.1016/j.eswa.2020.113466