Title :
A Swarm Intelligence Based Algorithm for Proteomic Pattern Detection of Ovarian Cancer
Author_Institution :
Dept. of Electr. & Comput. Eng., Stevens Inst. of Technol., Hoboken, NJ
Abstract :
The advanced protein profiling technologies can simultaneously resolve and analyze multiple proteins. Evaluating multiple proteins will be essential to establish signature proteomic patterns that distinguish cancer from non-cancer. It is desirable to have complex and intelligent analytical tools to detect the changes in protein expression and their correlation to diseases conditions. This paper proposed a swarming-agent based intelligence algorithm using a hybrid ant colony optimization/particle swarm optimization (ACO/PSO) algorithm to identify the diagnostic proteomic patterns of biomarkers for early detection of ovarian cancer. The experimental results demonstrated that the proposed system has high predictive accuracy and better diagnostic performance
Keywords :
artificial intelligence; cancer; medical diagnostic computing; particle swarm optimisation; pattern recognition; proteins; biomarkers; diagnostic performance; diagnostic proteomic patterns; hybrid ant colony optimization; ovarian cancer; particle swarm optimization; predictive accuracy; protein expression; protein profiling technology; proteomic pattern detection; signature proteomic patterns; swarm intelligence; swarming-agent based intelligence algorithm; Biomarkers; Cancer detection; Classification tree analysis; Decision trees; Diseases; Oncological surgery; Particle swarm optimization; Pattern analysis; Protein engineering; Proteomics;
Conference_Titel :
Computational Intelligence and Bioinformatics and Computational Biology, 2006. CIBCB '06. 2006 IEEE Symposium on
Conference_Location :
Toronto, Ont.
Print_ISBN :
1-4244-0624-2
Electronic_ISBN :
1-4244-0624-2
DOI :
10.1109/CIBCB.2006.331010
