Application of elitist multi-objective genetic algorithm for classification rule generation
Applied Soft ComputingPublished 24 March 2007
Satchidananda Dehuri, Srikanta Patnaik, Ashish Ghosh, Raghvendra Mall
Citations82
SJR quartileQ1
SJR score1.51
SNIP1.97
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
An elitist multi-objective genetic algorithm (EMOGA) for mining classification rules from large databases with a hybrid crossover operator for optimizing these objectives simultaneously with a clear edge over simple genetic algorithm.
Abstract
We present an elitist multi-objective genetic algorithm (EMOGA) for mining classification rules from large databases. We emphasize on predictive accuracy, comprehensibility and interestingness of the rules. However, predictive accuracy, comprehensibility and interestingness of the rules often conflict with each other. This makes it a multi-objective optimization problem that is very difficult to solve efficiently. We have proposed a multi-objective genetic algorithm with a hybrid crossover operator for optimizing these objectives simultaneously. We have compared our rule discovery procedure with simple genetic algorithm with a weighted sum of all these objectives. The experimental result confirms that our rule discovery algorithm has a clear edge over simple genetic algorithm.
Keywords
Computer Science
IEEE Transactions on Evolutionary ComputationA fast and elitist multiobjective genetic algorithm: NSGA-II
47,759 Citations2002Kalyanmoy Deb, Amrit Pratap +2 more
This paper suggests a non-dominated sorting-based MOEA, called NSGA-II (Non-dominated Sorting Genetic Algorithm II), which alleviates all of the above three difficulties, and modify the definition of dominance in order to solve constrained multi-objective problems efficiently.
Elements of Information Theory
37,533 Citations2001Thomas M. Cover, Joy A. Thomas
Multi-Objective Optimization Using Evolutionary Algorithms
15,017 Citations2001Kalyanmoy Deb, Deb Kalyanmoy
This text provides an excellent introduction to the use of evolutionary algorithms in multi-objective optimization, allowing use as a graduate course text or for self-study.
IEEE Transactions on Evolutionary ComputationMultiobjective evolutionary algorithms: a comparative case study and the strength Pareto approach
8,605 Citations1999Eckart Zitzler, Lothar Thiele
The proof-of-principle results obtained on two artificial problems as well as a larger problem, the synthesis of a digital hardware-software multiprocessor system, suggest that SPEA can be very effective in sampling from along the entire Pareto-optimal front and distributing the generated solutions over the tradeoff surface.
Medical Entomology and ZoologyMultiple Attribute Decision Making: Methods and Applications
8,268 Citations1981Shu-Jen J. Chen, C. L. Hwang +2 more
Lecture notes in economics and mathematical systemsMultiple Attribute Decision Making
8,145 Citations1981Ching-Lai Hwang, Kwangsun Yoon
Handbook of Genetic Algorithms
7,308 Citations1991Lawrence Davis
Evolutionary Algorithms for Solving Multi-Objective Problems
5,697 Citations2007Gary B. Lamont
Birkhäuser Basel eBooksElements of Information Theory
2,908 Citations1992Konrad Jacobs
For information theory, messages are elements of a set, and when they are handled, their sole concern is to keep distinct messages distinct, i.e. to make the mappings resulting from the authors' manipulations injective (= one-to-one).
Genetic algorithms and evolutionary computationEvolutionary Algorithms for Solving Multi-Objective Problems
2,650 Citations2002Carlos A. Coello Coello, David A. Van Veldhuizen +1 more
This paper presents a meta-anatomy of the multi-Criteria Decision Making process, which aims to provide a scaffolding for the future development of multi-criteria decision-making systems.
A niched Pareto genetic algorithm for multiobjective optimization
2,423 Citations2002Jeffrey Horn, N. Nafpliotis +1 more
The Niched Pareto GA is introduced as an algorithm for finding the Pare to optimal set and its ability to find and maintain a diverse "Pareto optimal population" on two artificial problems and an open problem in hydrosystems is demonstrated.
international conference on Genetic algorithmsGenetic algorithms with sharing for multimodal function optimization
1,890 Citations1987David E. Goldberg, Jon T. Richardson
MIT Press eBooksKnowledge Discovery in Databases
1,758 Citations1991Gregory Piateski, William Frawley
ACM SIGART BulletinBook review: Genetic Algorithms + Data Structures = Evolution Programs by Zbigniew Michalewicz (Springer-Verlag, 1992)
1,091 Citations1993Michael de la Maza
Natural computing seriesData Mining and Knowledge Discovery with Evolutionary Algorithms
768 Citations2002Alex A. Freitas
This book integrates two areas of computer science, namely data mining and evolutionary algorithms, and emphasizes the importance of discovering comprehensible, interesting knowledge, which is potentially useful for intelligent decision making.
TechnometricsConstruction and Assessment of Classification Rules
625 Citations1999Mark R. Wade, David J. Hand
Basic Ideas Introduction Constructing Rules Fisher's LDA and Other Methods Based on Covariance Matrices Recursive Partitioning Methods Nonparametric Smoothing Methods Practical Issues Some Special Problems Some Illustrative Applications.
Natural computing seriesA Survey of Evolutionary Algorithms for Data Mining and Knowledge Discovery
424 Citations2003Alex A. Freitas
This chapter discusses the use of evolutionary algorithms, particularly genetic algorithms and genetic programming, in data mining and knowledge discovery, and discusses some preprocessing and postprocessing steps of the knowledge discovery process, focusing on attribute selection and pruning of an ensemble of classifiers.
Machine LearningA knowledge-intensive genetic algorithm for supervised learning
247 Citations1994Cezary Z. Janikow
The method of abstracting the genetic algorithm to the problem level, described here for the supervised inductive learning, can be also extended to other domains and tasks, since it provides a framework for combining recently popular genetic algorithm methods with traditional problem-solving methodologies.
Knowledge-Based SystemsOn rule interestingness measures
236 Citations1999Alex A. Freitas
This article aims at drawing attention to several factors related to rule interestingness that have been somewhat neglected in the literature, and introducing a new criterion to measure attribute surprisingness, as a factor influencing the interestingness of discovered rules.
Using general impressions to analyze discovered classification rules
217 Citations1997Bing Liu, Wynne Hsu +1 more
This paper proposes a technique that analyzes the discovered rules against a specific type of existing knowledge, which is called general impressions, to help the user identify interesting rules.
Advances in Soft Computing: Engineering Design and Manufacturing
206 Citations1998Rinku Roy, 武 古橋 +1 more
Discovering comprehensible classification rules with a genetic algorithm
188 Citations2002M.V. Fidelis, Heitor Silvério Lopes +1 more
A classification algorithm based on genetic algorithms (GAs) that discovers comprehensible IF-THEN rules, in the spirit of data mining is presented.
Lecture notes in computer scienceA spatial predator-prey approach to multi-objective optimization: A preliminary study
171 Citations1998Marco Laumanns, Günter Rudolph +1 more
The main objective of this preliminary study is the answer to the question whether the predator-prey approach to multi-objective optimization works at all, which is examined under several step-size adaptation rules.
Machine LearningA Knowledge-Intensive Genetic Algorithm for Supervised Learning
150 Citations1993Cezary Z. Janikow
The method of abstracting the genetic algorithm to the problem level, described here for the supervised inductive learning, provides a framework for combining recently popular genetic algorithm methods with traditional problem-solving methodologies.
Lecture notes in computer scienceOn objective measures of rule surprisingness
137 Citations1998Alex A. Freitas
This paper has a twofold goal: showing that it is indeed possible to define objective (rather than subjective) measures of discovered rule surprisingness, and proposing new ideas and methods for defining objectiveRule surprisingness measures.
Discovering interesting prediction rules with a genetic algorithm
133 Citations2003Edgar Noda, Alex A. Freitas +1 more
This work presents a genetic algorithm designed from the scratch to discover interesting rules that addresses the dependence modelling task, where different rules can predict different goal attributes.
IEEE Intelligent Systems and their ApplicationsKnowledge discovery from data?
128 Citations2000Michael J. Pazzani
The knowledge discovery and data mining field draws on findings from statistics, databases, and artificial intelligence to construct tools that let users gain insight from massive data sets by paying attention to the cognitive factors that make the resulting models coherent, credible, easy to use, and easy to communicate to others.
Some experiments in machine learning using vector evaluated genetic algorithms (artificial intelligence, optimization, adaptation, pattern recognition)
121 Citations1984James David Schaffer
The VEGA approach has demonstrated the efficacy of extending the previously demonstrated power of genetic algorithms to vector-valued problems and thereby provides a new approach to machine learning.
Applied Soft ComputingOn the combination of evolutionary algorithms and stratified strategies for training set selection in data mining
93 Citations2005José-Ramón Cano, Francisco Herrera +1 more
The study shows that the stratified evolutionary instance selection consistently outperforms the non-evolutionary ones and has the main advantages: high instance reduction rates, high classification accuracy and models with high interpretability.
Kent Academic Repository (University of Kent)A Genetic Programming Framework for Two Data Mining Tasks: Classification and Generalized Rule Induction
91 Citations1997Alex A. Freitas
This paper proposes a genetic programming framework for two major data mining tasks, namely classification and generalized rule induction, which emphasizes the integration between a GP algorithm and relational database systems.
Knowledge-Based SystemsPredictive and comprehensible rule discovery using a multi-objective genetic algorithm
80 Citations2006Satchidananda Dehuri, Raghvendra Mall
A multi-objective evolutionary algorithm called improved niched Pareto genetic algorithm (INPGA) is proposed for mining highly predictive and comprehensible classification rules from large databases and has a clear edge over SGA and NPGA.
Evolutionary algorithms in data mining
57 Citations2000Siddhartha Bhattacharyya
This paper proposes the use of evolutionary computation based procedures for obtaining a set of non- dominated models with respect to multiple stated objectives, and results from a real-world problem illustrate the benefits of the proposed approach.
Advances in soft computingA Genetic Algorithm for Generalized Rule Induction
50 Citations1999Alex A. Freitas
This paper presents a new genetic algorithm designed for discovering a few interesting, high-level prediction rules from databases, rather than discovering classification knowledge as usual in the literature.
Lecture notes in computer scienceDiscovery of decision rules from databases: An evolutionary approach
31 Citations1998Wojciech Kwedlo, Marek Krętowski
An EA-based system called EDRL, which for each class label sequentially generates a disjunctive set of decision rules in propositional form, which is evaluated by comparing its classification accuracy with that of C4.5 learning algorithm on six datasets from UCI repository.
The worth of the uniform [uniform crossover]
26 Citations2003Emanuel Falkenauer
It is argued that on problems with even a mild degree of difficulty, disruption is indeed harmful, and UC appears to perform worse than the classic 2-point crossover fitted with inversion, and essentially the same as a simple copy-and-mutate operator.
Series in machine perception and artificial intelligenceSoft Computing Approach to Pattern Recognition and Image Processing
23 Citations2002Ashish Ghosh, Sankar K. Pal
Part I: multiple classifier systems, J. Kittler building decision trees from the Fourier spectrum of a tree ensemble, H. Kargupta clustering large data sets, and autoassociative neural network models for pattern recognition tasks in speech and image.