|
| This Article | ||
| ||
| Share | ||
| Bibliographic References | ||
| Add to: | ||
 Digg  Furl  Spurl  Blink  Simpy  Google  Del.icio.us  Y!MyWeb | ||
| Search | ||
| ||
| ASCII Text | x | ||
| Zhiwei Wang, Gregory L. Durst, Russell C. Eberhart, Donald B. Boyd, Zina Ben Miled, "Particle Swarm Optimization and Neural Network Application for QSAR," Parallel and Distributed Processing Symposium, International, vol. 10, pp. 194, 18th International Parallel and Distributed Processing Symposium (IPDPS'04) - Workshop 9, 2004. | |||
| BibTex | x | ||
| @article{ 10.1109/IPDPS.2004.1303214, author = {Zhiwei Wang and Gregory L. Durst and Russell C. Eberhart and Donald B. Boyd and Zina Ben Miled}, title = {Particle Swarm Optimization and Neural Network Application for QSAR}, journal ={Parallel and Distributed Processing Symposium, International}, volume = {10}, year = {2004}, isbn = {0-7695-2132-0}, pages = {194}, doi = {http://doi.ieeecomputersociety.org/10.1109/IPDPS.2004.1303214}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, } | |||
| RefWorks Procite/RefMan/Endnote | x | ||
| TY - CONF JO - Parallel and Distributed Processing Symposium, International TI - Particle Swarm Optimization and Neural Network Application for QSAR SN - 0-7695-2132-0 SP EP A1 - Zhiwei Wang, A1 - Gregory L. Durst, A1 - Russell C. Eberhart, A1 - Donald B. Boyd, A1 - Zina Ben Miled, PY - 2004 KW - null VL - 10 JA - Parallel and Distributed Processing Symposium, International ER - | |||
A successful approach to building QSAR models was proposed by other researchers. It uses binary particle swarm optimization (BPSO) for feature selection in the first stage, and a back propagation neural network in the second stage to generate a QSAR model based on the features selected in the first stage.
This paper starts by re-establishing the results of this approach on an extended number of data sets. A new method is then proposed that addresses the limitation of back propagation. The new approach uses particle swarm optimization (PSO) in the second stage for training and bootstrap aggregation (Bagging) in order to overcome the instability of PSO. The proposed approach yields robust QSAR models, while reducing the variability due to the choice of the back propagation parameters.