Lin, F.-S.F.-S.LinShen, C.-P.C.-P.ShenSung, H.-Y.H.-Y.SungLam, Y.-Y.Y.-Y.LamLin, J.-W.J.-W.LinFEI-PEI LAI2020-04-162020-04-162013https://scholars.lib.ntu.edu.tw/handle/123456789/484397Multiclass classification is an important technique to many complex bioinformatics problems. However, their performance is limited by the computation power. Based on the Apache Hadoop design framework, this study proposes a two layer architecture that exploits the inherent parallelism of GA-SVM classification to speed up the work. The performance evaluations on an mRNA benchmark cancer dataset have reduced 86.55% features and raised accuracy from 97.53% to 98.03%. With a user-friendly web interface, the system provides researchers an easy way to investigate the unrevealed secrets in the fast-growing repository of bioinformatics data. ? 2013 IEEE.[SDGs]SDG3[SDGs]SDG9Bioinformatics data; Cloud computing platforms; Computation power; Design frameworks; Inherent parallelism; Layer architectures; Multi-class classification; Web interface; Bioinformatics; Computer software; Computer aided diagnosis; messenger RNA; algorithm; biology; genetics; human; procedures; theoretical model; time; Algorithms; Computational Biology; Humans; Models, Theoretical; RNA, Messenger; Time Factorsconference paper10.1109/EMBC.2013.66097992-s2.0-84886580036https://www.scopus.com/inward/record.uri?eid=2-s2.0-84886580036&doi=10.1109%2fEMBC.2013.6609799&partnerID=40&md5=b910d2a21ed88e6771856d5be2d83b74