期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2013
卷号：56
期号：2
出版社：Journal of Theoretical and Applied
摘要：World Health Organization (WHO) reports that worldwide 7.6 million deaths are caused by cancer each year. Uncontrollable cell development in the tissues of the lung is called as lung cancer. These uncontrollable cells restrict the growth of healthy lung tissues. If not treated, this growth can spread beyond the lung in the nearby tissue called metastasis and, form tumors. In order to preserve the life of the people who are suffered by the lung cancer disease, it should be pre-diagonized. So there is a need of pre diagnosis system for lung cancer disease which should provide better results. The proposed lung cancer prediagnosis technique is the combination of FFBNN and ABC. By using the Artificial Bee Colony (ABC) algorithm, the dimensionality of the dataset is reduced in order to reduce the computation complexity. Then the risk factors and the symptoms from the dimensional reduced dataset are given to the FFBNN to accomplish the training process. In order to get higher accuracy in the prediagnosis process, the FFBNN parameters are optimized using ABC algorithm. In the testing process, more data are given to well trained FFBNN-ABC to validate whether the given testing data predict the lung disease perfectly or not.
关键词：Artificial Bee Colony (ABC) Algorithm; Feed Forward Back Propagation Neural Network (FFBNN); Risk factor and symptoms; Dimensionality reduction
