The week's pick
Random Articles
Reseach Article
Ranking of Classifiers based on Dataset Characteristics using Active Meta Learning
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 69 - Number 20 |
| Year of Publication: 2013 |
| Authors: Nikita Bhatt, Amit Thakkar, Amit Ganatra, Nirav Bhatt |
10.5120/12089-8269
|
Nikita Bhatt, Amit Thakkar, Amit Ganatra, Nirav Bhatt . Ranking of Classifiers based on Dataset Characteristics using Active Meta Learning. International Journal of Computer Applications. 69, 20 ( May 2013), 31-36. DOI=10.5120/12089-8269
Abstract
Classification is a machine learning technique which is used to categorize the different input patterns into different classes. To select the best classifier for a given dataset is one of the critical issues in Classification. Using cross-validation approach, it is possible to apply candidate algorithms on a given dataset and best classifier is selected by considering various evaluation measures of Classification. But computational cost is significant. Meta Learning automates this process by acquiring knowledge in form of Meta-features and performance information of candidate algorithm on datasets and creates a Meta Knowledge Base. Once Meta Knowledge Base is generated, system uses k-Nearest Neighbor as a Meta Learner that identifies the most similar datasets to new dataset. But generation of Meta Example is a costly process due to a large number of candidate algorithms and datasets with different characteristics involved. So Active Learning is incorporated into Meta Learning System that reduces generation of Meta example and at the same time maintaining performance of candidate algorithms. Once the training phase is completed based on Active Meta Learning approach, ranking is provided based on Success Rate Ratio (SRR) method that considers accuracy as a performance evaluation measure.
References
- Niklas Lavesson and Paul Davidsson, 2008, Analysis of Multi-Criteria Metrics for Classifier and Algorithm Evaluation, scientific commons.
- Iain Paterson, Helmut Barrer and Jorg Keller, 2002, The Focused Multi-Criteria Ranking Approach to Machine Learning Algorithm Selection - An Incremental Meta Learning Assistant for Data Mining Tasks, IDDM Institute for advanced studies, Austria, CiteSeer.
- Marcilio C. P. de Souto, Ricardo B. C. Prudencio, Rodrigo G. F. Soares, 2008, Ranking and Selecting Clustering Algorithms Using a Meta-Learning Approach.
- Christophe Giraud-Carrier, Chair, Dan Ventura, Yiu-Kai Dennis Ng Eric Mercer, Sean Warnick, 2011, Relationships among Learning Algorithms and Tasks, Proceedings of the International Conference on Machine Learning and Applications.
- Ajay Kumar Tanwari, Jamal Afridi, M. ZubairShafiq and Muddassar Farooq, 2009, Guidelines to Select Machine Learning Scheme for Classification of Biomedical
- Datasets, nexginrc, Evolutionary Computation, Machine Learning Scheme for Classification of Biomedical Datasets, Springer.
- Mykola Pechenizkiy, 2003, Data Mining Strategy Selection via Empirical and Constructive Induction, Finland.
- Stuart Moran,YulanHe, Kecheng Liu, 2009, An Empirical Framework for Automatically Selecting the Best Bayesian Classifier, Proceedings of the World Congress Engineering 2009 Vol I WCE 2009 London July 1-3,U. K.
- Silviu Cacoveanu, Camelia Vidrighin, Rodica Potolea, 2005, Evolution Meta-Learning Framework For automatic Classifier Selection.
- Shawkat Ali, Kate A. Smith, January 2006, On learning algorithm selection for classification, Applied Soft Computing Volume 6, Issue 2, 119-138.
- Ricardo B. C. Orudencio and Teresa B. Ludermir, 2008, Selective Generation of training examples in active meta-learning, International Journal of Hybrid Intelligent Systems.
- C. M. van der walt and E. Barnard, 2008, Data Characteristics that determines classifier performance.
- Myra Spiliopoulou, Alexis Kalousis, Lukas C. Faulstich and Theoharis, 2000, NOEMON: An Intelligent Assistant for Classifier Selection, Citeseer.
- Alexandros Kalousis And Melanie Hilario, 2002, Algorithm selection via meta learning.
- Ricardo Vilalta , Christophe Giraud-Carrier, Pavel Brazdil, Carlos Soares, 2004, Using Meta Learning to support Data Mining , 32-45.
- S. Appavu alias Balamurugan, Dr. R. Rajaram, G. Athiappan, M. Muthupandian, 2007, Data Mining Techniques for suspicious Email Detection: A Comparative Study, IADIS European Conference Data Ming, Madurai.
- C. Giraud-Carrier, R. Vilalta and P. Brazdil, 2004, Introduction to the special issue on meta-learning, Machine Learning 54, 187–193.
- Carlos Soares and Pavel B. Brazdil, 2002, Zoomed Ranking: Selection of Classification Algorithms Based on Relevant Performance Information, Principles of Data Mining and Knowledge Discovery, Springer Link.
- Ricardo B. C. Prudencio and Teresa B. Ludermin, 2009, Combining Uncertainty Sampling Methods for Active Meta Learning, Ninth International Conference on Intelligent Systems Design and Applications, 220-225.
- MihaGrcar, BlazFortun, Dunja Mladeni, 2002, k-NN Versus SVM in the Collaborative Filtering Framework, Data Science and Classification.
- Ricardo B. C. Prudencio and Teresa B. Ludermin, 2010, Active Meta-Learning with Uncertainty Sampling and Outlier Detection, IEEE World Congress on Computational Intelligence.
- D. Cohn, L. Atlas, and R. Ladner, 1994, Improving generalization with active learning, Machine Learning, vol. 15, pp. 201–221.
- G. Riccardi and D. Hakkani-Tur, 2005, Active learning: theory and applications to automatic speech recognition, IEEE Transactions on Speech and Audio Processing 13, 504–511.
- D. Angluin, 1998, Queries and concept learning, Machine Learning 2, 319–342.
- I. Muslea, S. Minton and C. Knobrock, 2006, Active learning with multiple views, Journal of Artificial Intelligence Research 27, 203–233.
- Ricardo B. C. Prudencio and Teresa B. Ludermin, 2011, Uncertainty Sampling Methods for Selecting Datasets in Active Meta Learning, Proceedings of International joint Conference on Neural Networks, San Jose, California, USA, July 31-August 5, 1082-1089.
- Pavel B. Brazdil, Carlos Soares, 2003, Ranking Learning Algorithms: Using IBL and Meta-Learning on Accuracy and Time Results.
Index Terms
Keywords