A matheuristic for binary classification of data sets using hyperboxes

Date

2018-07-08

Author

Akbulut, Derya
İyigün, Cem
Özdemirel, Nur Evin

Metadata

Show full item record

Item Usage Stats

341
views

0
downloads

In this study, an optimization approach is proposed for the binary classification problem. A Mixed Integer Programming (MIP) model formulation is used to construct hyperboxes as classifiers, minimizing the number of misclassified and unclassified samples as well as overlapping of hyperboxes. The hyperboxes are determined by some lower and upper bounds on the feature values, and overlapping of these hyperboxes is allowed to keep a balance between misclassification and overfitting. A matheuristic, namely Iterative Classification procedure for Binary classes (ICB) is developed based on the MIP formulation. In each iteration of the ICB algorithm, a fixed number of hyperboxes are generated using the MIP model, and then a trimming algorithm is used to adjust the hyperboxes in a way to eliminate the misclassified samples. Some trimmed hyperboxes and sample assignments are then fixed, reducing the unclassified sample size left for the next iteration. ICB controls the number of hyperboxes in a greedy manner, but provides an overall hyperbox configuration with no misclassification by the end of the training phase. For the test phase, distance-based heuristic algorithms are also developed to classify the uncovered and overlap samples that are not classified by the hyperboxes.

URI

https://hdl.handle.net/11511/86765

Conference Name

EURO 2018 - 29th European Conference on Operational Research, July 8-11 2018

Collections

Department of Industrial Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

A Modified Parallel Learning Vector Quantization Algorithm for Real-Time Hardware Applications Alkim, Erdem; AKLEYLEK, SEDAT; KILIÇ, ERDAL (2017-10-01) In this study a modified learning vector quantization (LVQ) algorithm is proposed. For this purpose, relevance LVQ (RLVQ) algorithm is effciently combined with a reinforcement mechanism. In this mechanism, it is shown that the proposed algorithm is not affected constantly by both relevance-irrelevance input dimensions and the winning of the same neuron. Hardware design of the proposed scheme is also given to illustrate the performance of the algorithm. The proposed algorithm is compared to the corresponding...
An fMRI segmentation method under markov random fields for brain decoding Aksan, Emre; Yarman Vural, Fatoş Tunay; Department of Computer Engineering (2015) In this study, a specially tailored segmentation method for partitioning the fMRI data into a set of "homogenous" regions with respect to a predefined cost function is proposed. The proposed method, referred as f-MRF, employs univariate and multivariate fMRI data analysis techniques under Markov Random Fields to estimate the segments by resolving a mixture density. The univariate approach helps identifying activation pattern of a voxel independently from other voxels. In order to capture local interactions ...
A generative model for multi class object recognition and detection Ulusoy, İlkay (2006-01-01) In this study, a generative type probabilistic model is proposed for object recognition. This model is trained by weakly labelled images and performs classification and detection at the same time. When test on highly challenging data sets, the model performs good for both tasks (classification and detection).
A Probabilistic approach to sparse multi scale phase based stereo ULUSOY PARNAS, İLKAY; Halıcı, Uğur; HANCOCK, EDWIN (2004-04-30) In this study, a multi-scale phase based sparse disparity algorithm and a probabilistic model for matching are proposed. The disparity algorithm and the probabilistic approach are verified on various stereo image pairs.
A genetic algorithm for TSP with backhauls based on conventional heuristics Önder, İlter; Özdemirel, Nur Evin; Department of Information Systems (2007) A genetic algorithm using conventional heuristics as operators is considered in this study for the traveling salesman problem with backhauls (TSPB). Properties of a crossover operator (Nearest Neighbor Crossover, NNX) based on the nearest neighbor heuristic and the idea of using more than two parents are investigated in a series of experiments. Different parent selection and replacement strategies and generation of multiple children are tried as well. Conventional improvement heuristics are also used as mut...

Citation Formats

D. Akbulut, C. İyigün, and N. E. Özdemirel, “A matheuristic for binary classification of data sets using hyperboxes,” presented at the EURO 2018 - 29th European Conference on Operational Research, July 8-11 2018, Valencia, Spain, 2018, Accessed: 00, 2021. [Online]. Available: https://hdl.handle.net/11511/86765.