An Agent-Based Hybrid System for Microarray Data Analysis

This article reports our experience in agent-based hybrid construction for microarray data analysis. The contributions are twofold: We demonstrate that agent-based approaches are suitable for building hybrid systems in general, and that a genetic ensemble system is appropriate for microarray data analysis in particular. Created using an agent-based framework, this genetic ensemble system for microarray data analysis excels in both sample classification accuracy and gene selection reproducibility.

Authors

• Zili Zhang
• Pengyi Yang
• Xindong Wu
• Chengqi Zhang Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University

Keywords

• Data analysis
• Bioinformatics
• Hybrid intelligent systems
• Intelligent agent
• Genetic algorithms
• Australia
• Reproducibility of results
• System testing
• Multiagent systems
• Algorithm design and analysis
• Microarray Data
• Hybrid System
• Classification Accuracy
• Gene Selection
• Subset Of Genes
• Fitness Function
• Classification Of Samples
• New Combinations
• Multi-agent Systems
• Filtering Algorithm
• Combination Of Algorithms
• Multi-objective Genetic Algorithm
• Agent-based Approach
• Bioinformatics Problems
• Pearson Correlation
• Training Set
• Training Data
• Decision Tree
• Classification Results
• Microarray Datasets
• High Classification Accuracy
• Independent Run
• Majority Voting
• Gain Ratio
• Biological Importance
• Feature Subset
• Unseen Data
• Ranking Results
• Classification Power
• Hybridization Solution
• data mining
• intelligent agents
• hybrid systems
• microarray