Tuning a multiple classifier system for side effect discovery using genetic algorithms

In previous work, a novel supervised framework implementing a binary classifier was presented that obtained excellent results for side effect discovery. Interestingly, unique side effects were identified when different binary classifiers were used within the framework, prompting the investigation of...

Full description

Bibliographic Details
Main Authors: Reps, Jenna M., Aickelin, Uwe, Garibaldi, Jonathan M.
Format: Conference or Workshop Item
Published: IEEE 2014
Subjects:
Online Access:https://eprints.nottingham.ac.uk/3354/
_version_ 1848791021854392320
author Reps, Jenna M.
Aickelin, Uwe
Garibaldi, Jonathan M.
author_facet Reps, Jenna M.
Aickelin, Uwe
Garibaldi, Jonathan M.
author_sort Reps, Jenna M.
building Nottingham Research Data Repository
collection Online Access
description In previous work, a novel supervised framework implementing a binary classifier was presented that obtained excellent results for side effect discovery. Interestingly, unique side effects were identified when different binary classifiers were used within the framework, prompting the investigation of applying a multiple classifier system. In this paper we investigate tuning a side effect multiple classifying system using genetic algorithms. The results of this research show that the novel framework implementing a multiple classifying system trained using genetic algorithms can obtain a higher partial area under the receiver operating characteristic curve than implementing a single classifier. Furthermore, the framework is able to detect side effects efficiently and obtains a low false positive rate.
first_indexed 2025-11-14T18:21:53Z
format Conference or Workshop Item
id nottingham-3354
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T18:21:53Z
publishDate 2014
publisher IEEE
recordtype eprints
repository_type Digital Repository
spelling nottingham-33542020-05-04T20:14:05Z https://eprints.nottingham.ac.uk/3354/ Tuning a multiple classifier system for side effect discovery using genetic algorithms Reps, Jenna M. Aickelin, Uwe Garibaldi, Jonathan M. In previous work, a novel supervised framework implementing a binary classifier was presented that obtained excellent results for side effect discovery. Interestingly, unique side effects were identified when different binary classifiers were used within the framework, prompting the investigation of applying a multiple classifier system. In this paper we investigate tuning a side effect multiple classifying system using genetic algorithms. The results of this research show that the novel framework implementing a multiple classifying system trained using genetic algorithms can obtain a higher partial area under the receiver operating characteristic curve than implementing a single classifier. Furthermore, the framework is able to detect side effects efficiently and obtains a low false positive rate. IEEE 2014-07 Conference or Workshop Item PeerReviewed Reps, Jenna M., Aickelin, Uwe and Garibaldi, Jonathan M. (2014) Tuning a multiple classifier system for side effect discovery using genetic algorithms. In: 2014 IEEE Congress on Evolutionary Computation (CEC), 6-11 July 2014, Beijing, China. adr Biomedical Informatics bradford hill ensemble http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6900328
spellingShingle adr
Biomedical Informatics
bradford hill
ensemble
Reps, Jenna M.
Aickelin, Uwe
Garibaldi, Jonathan M.
Tuning a multiple classifier system for side effect discovery using genetic algorithms
title Tuning a multiple classifier system for side effect discovery using genetic algorithms
title_full Tuning a multiple classifier system for side effect discovery using genetic algorithms
title_fullStr Tuning a multiple classifier system for side effect discovery using genetic algorithms
title_full_unstemmed Tuning a multiple classifier system for side effect discovery using genetic algorithms
title_short Tuning a multiple classifier system for side effect discovery using genetic algorithms
title_sort tuning a multiple classifier system for side effect discovery using genetic algorithms
topic adr
Biomedical Informatics
bradford hill
ensemble
url https://eprints.nottingham.ac.uk/3354/
https://eprints.nottingham.ac.uk/3354/