Journal of Chemical and Pharmaceutical Research (ISSN : 0975-7384)

Reach Us reach to JOCPR whatsapp-JOCPR +44 1625708989
All submissions of the EM system will be redirected to Online Manuscript Submission System. Authors are requested to submit articles directly to Online Manuscript Submission System of respective journal.

Original Articles: 2014 Vol: 6 Issue: 5

Innovation capability prediction on complex pharmaceutical product based on algorithm compiled RBFNN with simulated annealing arithmetic


A new neural network in the field of innovation capability prediction arithmetic on complex pharmaceutical product based on RBFNN and simulated annealing arithmetic is discussed in detail. Radial basis function neural network (RBFNN) has been designed, and simulated annealing arithmetic is adopted in adjusting the network weights. MATLAB program is compiled here, innovation capability prediction analysis on 29 listed pharmaceutical companies have been done employing the algorithm. The experiments have shown that the arithmetic can efficiently approach the precision with 10-4 error, also the learning speed is quick and analysis results are ideal. Experiments have been done with other kind networks in comparison. Back-propagation (BP) learning algorithm network does not converge until 3500 iterative procedure, and exactness design RBFNN is time-consuming and has big error. The arithmetic based on RBFNN and simulated annealing arithmetic can keep the network away from the partial minimum.