Aim and Scope
Data mining and knowledge discovery are crucial techniques across manyÂ scientific disciplines. Recent developments such as the Genome ProjectÂ (and its successors) or the construction of the Large Hadron ColliderÂ have provided the scientific community with vast amounts of data.Â Metaheuristics and other evolutionary algorithms have been successfullyÂ applied to a large variety of data mining tasks. CompetitiveÂ metaheuristic approaches are able to deal with rule, tree and prototypeÂ induction, neural networks synthesis, fuzzy logic learning, and kernelÂ machines–to mention but a few. Moreover, the inherent parallel natureÂ of some metaheuristics (e.g. evolutionary approaches, particle swarms,Â ant colonies, etc) makes them perfect candidates for approaching veryÂ large-scale data mining problems.
Although a number of recent techniques have applied these methods toÂ complex data mining domains, we are still far from having a deep andÂ principled understanding of how to scale them to datasets of terascale,Â petascale or even larger scale. In order to achieve and maintain aÂ relevant role in large scale data mining, metaheuristics need, amongÂ other features, to have the capacity of processing vast amounts of dataÂ in a reasonable time frame, to use efficiently the unprecedentedÂ computer power available nowadays due to advances in high performanceÂ computing and to produce when possible- human understandable outputs.
Several research topics impinge on the applicability of metaheuristicsÂ for data mining techniques: (1) proper scalable learning paradigms andÂ knowledge representations, (2) better understanding of the relationshipÂ between the learning paradigms/representations and the nature of theÂ problems to be solved, (3) efficiency enhancement techniques, and (4)Â visualization tools that expose as much insight as possible to theÂ domain experts based on the learned knowledge.
We would like to invite researchers to submit contributions on the areaÂ of large-scale data mining using metaheuristics. Potentially viableÂ research themes are:
- Learning paradigms based on metaheuristics, evolutionary algorithms,Â learning classifier systems, particle swarm, ant colonies, tabu search,Â simulated annealing, etc
- Hybridization with other kinds of machine learning techniquesÂ including exact and approximation algorithms
- Knowledge representations for large-scale data mining
- Advanced techniques for enhanced prediction (classification,Â regression/function approximation, clustering, etc.) when dealing withÂ large data sets
- Efficiency enhancement techniques
- Parallelization techniques
- Hardware acceleration techniques (vectorial instuctions, GPUs, etc.)
- Theoretical models of the scalability limits of the learningÂ paradigms/representations
- Principled methodologies for experiment design (choosing methods,Â adjusting parameters, etc.)
- Explanatory power and visualization of generated solutions
- Data complexity analysis and measures
- Ensemble methods
- Online data mining and data streams
- Examples of real-world successful applications
Instructions for authors
Papers should have approximately 20 pages (but certainly not more than 24 pages). The papers must follow the format of the Memetic ComputingÂ journal:
Papers should be submitted following the Memetic Computing journalÂ guidelines. When submitting the paper please select this special issue as the article type.
- Manuscript submission: May 31st, 2009
- Notification of acceptance: July 31st, 2009
- Submission of camera-ready version: Sep 30th, 2009
School of Computer Science and School of Biosciences
University of Nottingham
National Center for Supercomputing Applications
University of Illinois at Urbana-Champaign