Document Detail


Multi-category classification using an Extreme Learning Machine for microarray gene expression cancer diagnosis.
MedLine Citation:
PMID:  17666768     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
In this paper, the recently developed Extreme Learning Machine (ELM) is used for direct multicategory classification problems in the cancer diagnosis area. ELM avoids problems like local minima, improper learning rate and overfitting commonly faced by iterative learning methods and completes the training very fast. We have evaluated the multi-category classification performance of ELM on three benchmark microarray datasets for cancer diagnosis, namely, the GCM dataset, the Lung dataset and the Lymphoma dataset. The results indicate that ELM produces comparable or better classification accuracies with reduced training time and implementation complexity compared to artificial neural networks methods like conventional back-propagation ANN, Linder's SANN, and Support Vector Machine methods like SVM-OVO and Ramaswamy's SVM-OVA. ELM also achieves better accuracies for classification of individual categories.
Authors:
Runxuan Zhang; Guang-Bin Huang; Narasimhan Sundararajan; P Saratchandran
Related Documents :
867758 - Transmissible gastroenteritis in pigs: some observations on laboratory aids to diagnosis.
3758008 - Barium swallow as an aid to the diagnosis of grass sickness.
21355648 - Neighborhood disadvantage as a moderator of the association between harsh parenting and...
15926028 - The role of the ear, nose and throat specialist in diagnosing headaches.
21490508 - Descriptions of community by people with spinal cord injuries: concepts to inform commu...
15563278 - Bounding analysis as an inadequately specified methodology.
Publication Detail:
Type:  Journal Article    
Journal Detail:
Title:  IEEE/ACM transactions on computational biology and bioinformatics / IEEE, ACM     Volume:  4     ISSN:  1545-5963     ISO Abbreviation:  IEEE/ACM Trans Comput Biol Bioinform     Publication Date:    2007 Jul-Sep
Date Detail:
Created Date:  2007-08-01     Completed Date:  2007-10-19     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  101196755     Medline TA:  IEEE/ACM Trans Comput Biol Bioinform     Country:  United States    
Other Details:
Languages:  eng     Pagination:  485-95     Citation Subset:  IM    
Affiliation:
Systems Biology Unit, Department of Genomes and Genetics, Institut Pasteur, France. rzhang@pasteur.fr
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Algorithms
Artificial Intelligence*
Diagnosis, Computer-Assisted / methods
Gene Expression Profiling / methods*
Humans
Neoplasm Proteins / metabolism*
Neoplasms / diagnosis,  metabolism*
Oligonucleotide Array Sequence Analysis / methods*
Pattern Recognition, Automated / methods*
Tumor Markers, Biological / metabolism*
Chemical
Reg. No./Substance:
0/Neoplasm Proteins; 0/Tumor Markers, Biological

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  High-throughput ligand screening via preclustering and evolved neural networks.
Next Document:  Superiority of spaced seeds for homology search.