@article{(Open Science Index):https://publications.waset.org/pdf/3329,
	  title     = {Latent Topic Based Medical Data Classification},
	  author    = {Jian-hua Yeh and  Shi-yi Kuo},
	  country	= {},
	  institution	= {},
	  abstract     = {This paper discusses the classification process for medical data. In this paper, we use the data from ACM KDDCup 2008 to demonstrate our classification process based on latent topic discovery. In this data set, the target set and outliers are quite different in their nature: target set is only 0.6% size in total, while the outliers consist of 99.4% of the data set. We use this data set as an example to show how we dealt with this extremely biased data set with latent topic discovery and noise reduction techniques. Our experiment faces two major challenge: (1) extremely distributed outliers, and (2) positive samples are far smaller than negative ones. We try to propose a suitable process flow to deal with these issues and get a best AUC result of 0.98.
},
	    journal   = {International Journal of Computer and Information Engineering},
	  volume    = {5},
	  number    = {5},
	  year      = {2011},
	  pages     = {476 - 480},
	  ee        = {https://publications.waset.org/pdf/3329},
	  url   	= {https://publications.waset.org/vol/53},
	  bibsource = {https://publications.waset.org/},
	  issn  	= {eISSN: 1307-6892},
	  publisher = {World Academy of Science, Engineering and Technology},
	  index 	= {Open Science Index 53, 2011},
	}