Prognostic Prediction of Lymphoma by Gene Expression Profiling Using FNN

摘要: Despite recent progress in clinical study and biological technology of cancer, the prognostic prediction patients still remains difficult inaccurate. Since DNA microarrays permits a simultaneous analysis multiple genes, it has been used to profile gene expression which can categorize cancers into subgroups [1]. To analyze data, many statistical techniques have used, but there would be relationships among genes that cannot expressed statistically. Therefore, artificial neural network (ANN) fuzzy (FNN) are useful for finding with high accuracy [2]. However, immensity data makes us spend much computational time construct ANN or FNN model. In this paper, we applied combined SWEEP operator method accelerate calculation speed about 30 times faster than modeling using back propagation leaning algorithm. The constructed models achieve prognosis patients. results were evaluated compared those Multiple Regression Analysis (MRA).