On the Optimization of Keyword Clustering Using Evolutionary Algorithms

Viktoria Dorfer

On the Optimization of Keyword Clustering Using Evolutionary Algorithms

Research Center Hagenberg

Publikation: Typen von Abschlussarbeiten › Masterarbeit / Diplomarbeit

Abstract

Im Bereich der Life Sciences liegt der Großteil der Informationen und Erkenntnisse als Klartext vor. Umso schwieriger gestaltet sich daher die Suche nach relevanten Informationen. Vor allem PubMed-Suchen liefern oft nicht nur eine große Anzahl an Publikationen, sondern auch viele für das eigentliche Interessensgebiet irrelevante Ergebnisse. Um dieses Problem zu behandeln, bieten Methoden des Information Retrieval verschiedenste Ansätze an. Darunter fällt auch die so genannte "Query Extension", bei der die Suchabfrage um gewisse, passende Wörter erweitert wird. Die Auswahl dieser Wörter wird mit Hilfe von Dokumenten-Clustern oder Keyword-Clustern getroffen. In dieser Masterarbeit wird ein neuer Ansatz vorgestellt, der mit Hilfe von evolutionären Algorithmen Keyword-Cluster erzeugt. Sie ist eine Sammlung von drei Publikationen zu dieser Aufgabenstellung. "Optimization of Keyword Grouping in Biomedical Information Retrieval Using Evolutionary Algorithms", publiziert in "Proceedings of the 22nd European Modeling and Simulation Symposium, EMSS 2010, Marokko" und verfasst von Viktoria Dorfer, Stephan M. Winkler, Thomas Kern, Gerald Petz und Patrizia Faschang, beschreibt die zugrundeliegende Problematik und die Grundlagen des neuen Ansatzes. In "On the Performance of Evolutionary Algorithms in Biomedical Keyword Clustering", publiziert in "Proceedings of the Genetic and Evolutionary Computation Conference, MedGEC 2011, Dublin" und verfasst von Viktoria Dorfer, Stephan M. Winkler, Thomas Kern, Sophie A. Blank, Gerald Petz und Patrizia Faschang, wird die Methode intensiv mit verschiedensten evolutionären Algorithmen und unterschiedlichen Parametereinstellungen getestet. Abschließend wird in "Analysis of Single-Objective and Multi-Objective Evolutionary Algorithms in Keyword Cluster Optimization", publiziert in "Proceedings of the International Conference on Computer Aided Systems Theory, EUROCAST 2011, Las Palmas" und verfasst von Viktoria Dorfer, Stephan M. Winkler, Thomas Kern, Gerald Petz,und Patrizia Faschang, für eine Auswahl von Algorithmen und Parametereinstellungen eine Analyse der Populationsdiversität durchgeführt.

Originalsprache	Englisch
Publikationsstatus	Veröffentlicht - 2011

Zitieren

@mastersthesis{8ab4c6ac0b3f4fb7a6bdd188334d99ce,

title = "On the Optimization of Keyword Clustering Using Evolutionary Algorithms",

abstract = "Most of the information in the eld of life sciences is available only in plaintext, leading to an often difficult search for the appropriate information. Especially when performing a PubMed query, not only lots of publications are presented to the user, but also a huge amount of irrelevant references. To solve this kind of problem, biomedical information retrieval provides various approaches, including query extension. Here, user queries are extended with appropriate additional words, selected from previously generated document or keyword clusters. In this master thesis a new approach is presented, where keyword clusters are generated using evolutionary algorithms. It is a collection of three publications on this scope. {"}Optimization of Keyword Grouping in Biomedical Information Retrieval Using Evolutionary Algorithms, published in {"}Proceedings of the 22nd European Modeling and Simulation Symposium, EMSS 2010, Morocco{"} and written by Viktoria Dorfer, Stephan M. Winkler, Thomas Kern, Gerald Petz, and Patrizia Faschang, describes the underlying problem and the principles of the new approach. In {"}On the Performance of Evolutionary Algorithms in Biomedical Keyword Clustering{"}, published in {"}Proceedings of the Genetic and Evolutionary Computation Conference, MedGEC 2011, Dublin{"} and written by Viktoria Dorfer, Stephan M. Winkler, Thomas Kern, Sophie A. Blank, Gerald Petz, and Patrizia Faschang, the method is intensively tested with various evolutionary algorithms and different parameter settings. Finally, a population diversity analysis is performed on the most promising algorithms in {"}Analysis of Single-Objective and Multi-Objective Evolutionary Algorithms in Keyword Cluster Optimization{"}, published in {"}Proceedings of the International Conference on Computer Aided Systems Theory, EUROCAST 2011, Las Palmas{"} and written by Viktoria Dorfer, Stephan M. Winkler, Thomas Kern, Gerald Petz, and Patrizia Faschang.",

author = "Viktoria Dorfer",

year = "2011",

language = "English",

}

TY - THES

T1 - On the Optimization of Keyword Clustering Using Evolutionary Algorithms

AU - Dorfer, Viktoria

PY - 2011

Y1 - 2011

N2 - Most of the information in the eld of life sciences is available only in plaintext, leading to an often difficult search for the appropriate information. Especially when performing a PubMed query, not only lots of publications are presented to the user, but also a huge amount of irrelevant references. To solve this kind of problem, biomedical information retrieval provides various approaches, including query extension. Here, user queries are extended with appropriate additional words, selected from previously generated document or keyword clusters. In this master thesis a new approach is presented, where keyword clusters are generated using evolutionary algorithms. It is a collection of three publications on this scope. "Optimization of Keyword Grouping in Biomedical Information Retrieval Using Evolutionary Algorithms, published in "Proceedings of the 22nd European Modeling and Simulation Symposium, EMSS 2010, Morocco" and written by Viktoria Dorfer, Stephan M. Winkler, Thomas Kern, Gerald Petz, and Patrizia Faschang, describes the underlying problem and the principles of the new approach. In "On the Performance of Evolutionary Algorithms in Biomedical Keyword Clustering", published in "Proceedings of the Genetic and Evolutionary Computation Conference, MedGEC 2011, Dublin" and written by Viktoria Dorfer, Stephan M. Winkler, Thomas Kern, Sophie A. Blank, Gerald Petz, and Patrizia Faschang, the method is intensively tested with various evolutionary algorithms and different parameter settings. Finally, a population diversity analysis is performed on the most promising algorithms in "Analysis of Single-Objective and Multi-Objective Evolutionary Algorithms in Keyword Cluster Optimization", published in "Proceedings of the International Conference on Computer Aided Systems Theory, EUROCAST 2011, Las Palmas" and written by Viktoria Dorfer, Stephan M. Winkler, Thomas Kern, Gerald Petz, and Patrizia Faschang.

AB - Most of the information in the eld of life sciences is available only in plaintext, leading to an often difficult search for the appropriate information. Especially when performing a PubMed query, not only lots of publications are presented to the user, but also a huge amount of irrelevant references. To solve this kind of problem, biomedical information retrieval provides various approaches, including query extension. Here, user queries are extended with appropriate additional words, selected from previously generated document or keyword clusters. In this master thesis a new approach is presented, where keyword clusters are generated using evolutionary algorithms. It is a collection of three publications on this scope. "Optimization of Keyword Grouping in Biomedical Information Retrieval Using Evolutionary Algorithms, published in "Proceedings of the 22nd European Modeling and Simulation Symposium, EMSS 2010, Morocco" and written by Viktoria Dorfer, Stephan M. Winkler, Thomas Kern, Gerald Petz, and Patrizia Faschang, describes the underlying problem and the principles of the new approach. In "On the Performance of Evolutionary Algorithms in Biomedical Keyword Clustering", published in "Proceedings of the Genetic and Evolutionary Computation Conference, MedGEC 2011, Dublin" and written by Viktoria Dorfer, Stephan M. Winkler, Thomas Kern, Sophie A. Blank, Gerald Petz, and Patrizia Faschang, the method is intensively tested with various evolutionary algorithms and different parameter settings. Finally, a population diversity analysis is performed on the most promising algorithms in "Analysis of Single-Objective and Multi-Objective Evolutionary Algorithms in Keyword Cluster Optimization", published in "Proceedings of the International Conference on Computer Aided Systems Theory, EUROCAST 2011, Las Palmas" and written by Viktoria Dorfer, Stephan M. Winkler, Thomas Kern, Gerald Petz, and Patrizia Faschang.

M3 - Master's Thesis / Diploma Thesis

ER -

On the Optimization of Keyword Clustering Using Evolutionary Algorithms

Abstract

Fingerprint

Zitieren