WASET
	@article{(Open Science Index):https://publications.waset.org/pdf/223,
	  title     = {Evaluation of the Impact of Dataset Characteristics for Classification Problems in Biological Applications},
	  author    = {Kanthida Kusonmano and  Michael Netzer and  Bernhard Pfeifer and  Christian Baumgartner and  Klaus R. Liedl and  Armin Graber},
	  country	= {},
	  institution	= {},
	  abstract     = {Availability of high dimensional biological datasets such as from gene expression, proteomic, and metabolic experiments can be leveraged for the diagnosis and prognosis of diseases. Many classification methods in this area have been studied to predict disease states and separate between predefined classes such as patients with a special disease versus healthy controls. However, most of the existing research only focuses on a specific dataset. There is a lack of generic comparison between classifiers, which might provide a guideline for biologists or bioinformaticians to select the proper algorithm for new datasets. In this study, we compare the performance of popular classifiers, which are Support Vector Machine (SVM), Logistic Regression, k-Nearest Neighbor (k-NN), Naive Bayes, Decision Tree, and Random Forest based on mock datasets. We mimic common biological scenarios simulating various proportions of real discriminating biomarkers and different effect sizes thereof. The result shows that SVM performs quite stable and reaches a higher AUC compared to other methods. This may be explained due to the ability of SVM to minimize the probability of error. Moreover, Decision Tree with its good applicability for diagnosis and prognosis shows good performance in our experimental setup. Logistic Regression and Random Forest, however, strongly depend on the ratio of discriminators and perform better when having a higher number of discriminators.
},
	    journal   = {International Journal of Biomedical and Biological Engineering},
	  volume    = {3},
	  number    = {10},
	  year      = {2009},
	  pages     = {309 - 313},
	  ee        = {https://publications.waset.org/pdf/223},
	  url   	= {https://publications.waset.org/vol/34},
	  bibsource = {https://publications.waset.org/},
	  issn  	= {eISSN: 1307-6892},
	  publisher = {World Academy of Science, Engineering and Technology},
	  index 	= {Open Science Index 34, 2009},
	}