PMID- 24212037 OWN - NLM STAT- MEDLINE DCOM- 20140623 LR - 20131111 IS - 1878-3619 (Electronic) IS - 0959-2989 (Linking) VI - 24 IP - 1 DP - 2014 TI - Tumor classification based on orthogonal linear discriminant analysis. PG - 1399-405 LID - 10.3233/BME-130944 [doi] AB - Gene expression profiles have great potential for accurate tumor diagnosis. It is expected to enable us to diagnose tumors precisely and systematically, and also bring the researchers of machine learning two challenges, the curse of dimensionality and the small sample size problems. We propose a manifold learning based dimensional reduction algorithm named orthogonal local discriminant embedding (O-LDE) and apply it to tumor classification. Comparing with the classical local discriminant embedding (LDE), O-LDE aims to obtain an orthogonal linear projection matrix by solving an optimization problem. After being projected into a low-dimensional subspace by O-LDE, the data points of the same class maintain their intrinsic neighbor relations, whereas the neighboring points of the different classes are far from each other. Experimental results on a public tumor dataset validate the effectiveness and feasibility of the proposed algorithm. FAU - Wang, Huiya AU - Wang H AD - Department of Mathematics, Northwest University, Xi'an 710069, China. FAU - Zhang, Shanwen AU - Zhang S LA - eng PT - Journal Article PT - Research Support, Non-U.S. Gov't PL - Netherlands TA - Biomed Mater Eng JT - Bio-medical materials and engineering JID - 9104021 SB - IM MH - Algorithms MH - Artificial Intelligence MH - Computer Simulation MH - Databases, Factual MH - *Discriminant Analysis MH - Gene Expression Profiling MH - Gene Expression Regulation, Neoplastic MH - Humans MH - Leukemia/classification/*diagnosis MH - Models, Theoretical MH - Neoplasms/classification/*diagnosis/*genetics OTO - NOTNLM OT - Tumor classification OT - local discriminant embedding (LDE) OT - orthogonal local discriminant embedding (O-LDE) EDAT- 2013/11/12 06:00 MHDA- 2014/06/24 06:00 CRDT- 2013/11/12 06:00 PHST- 2013/11/12 06:00 [entrez] PHST- 2013/11/12 06:00 [pubmed] PHST- 2014/06/24 06:00 [medline] AID - Q866H7141TJ82016 [pii] AID - 10.3233/BME-130944 [doi] PST - ppublish SO - Biomed Mater Eng. 2014;24(1):1399-405. doi: 10.3233/BME-130944.