Title :
Report about VOCs dataset´s analysis based on randomForests method
Author :
Huaizhong, Zhang ; Hamprecht, Fred ; Amann, Anton
Author_Institution :
Sch. of Math. & Comput. Sci., Nanjing Normal Univ.
Abstract :
Volatile organic compounds (VOCs) play an important role in diagnosis and therapy of various diseases. We compare several main classifiers for data classification and point out the advantages of randomForests on supervising learning. So, in this project, we take the randomForests approach to analyze and appraise the VOCs data originally coming from the medical test. According to actual situation, combining the unsupervising and supervising methods, the important components and outliers are given. The evaluation for the classifying results has been acquired due to the cross-validation sampling methods
Keywords :
classification; data analysis; diseases; learning (artificial intelligence); medical computing; patient diagnosis; sampling methods; VOC datasets analysis; cross-validation sampling methods; data classification; disease diagnosis; disease therapy; randomForests method; supervising learning; unsupervising learning; volatile organic compounds; Data analysis; Decision theory; Diseases; Gas detectors; Humans; Mathematics; Medical diagnostic imaging; Medical treatment; Pattern analysis; Volatile organic compounds;
Conference_Titel :
High-Performance Computing in Asia-Pacific Region, 2005. Proceedings. Eighth International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7695-2486-9
DOI :
10.1109/HPCASIA.2005.85
