Application of back propagation model to evaluate Chinese grain logistics parks

Author(s):  
Xin Shen
2019 ◽  
Vol 38 (2) ◽  
pp. 342-352
Author(s):  
Saeid Maknouni Gilani ◽  
Mohammad Zare ◽  
Ezzatollah Raeisi

1998 ◽  
Vol 08 (03) ◽  
pp. 297-306 ◽  
Author(s):  
Tzung-Pei Hong ◽  
Jyh-Jong Lee

The back-propagation model is applied mainly to multiple layers of neurons with feed-forward connections. It applies the generalized delta learning rule to derive appropriate weights on connections from a set of training instances. In the past, a parallel back-propagation learning algorithm on a bus-based architecture with an infinite number of processors was proposed to speed up the learning of weights. In this paper, the parallel back-propagation learning algorithm is modified, so that it is applicable to any number of processors. The given training instances are equally partitioned and put on these processors. When learning starts, each processor searches its own training subset to update the weight matrix and to broadcast the new result. Both analytical and experimental results show that the average speed-up can reach nearly O(r) by r processors if r is much less than the number of training instances.


Manual Signatures are used in authentication worldwide. But they are still not used in VANETs and in ad hoc networks for security. In our research we try to use manual signature in place of Digital Signatures for the security of message and stimulated the same by pattern recalling mechanism of Artificial Neural Network using Elman Back Propagation Algorithm to create pseudo digital signature. These pseudo digital signatures are now used as the identity of message sender in communication. We also maintained the speed of manual signature recognition and verification to stop the delay in identification of the sender.


2010 ◽  
Vol 168-170 ◽  
pp. 404-407 ◽  
Author(s):  
Qing Yang ◽  
Yong Ju Hu ◽  
Liang Xue

This study simulated the nanofiltration (NF) process of contamination removing by back-propagation neural network (BPNN), according to the test values of DK membrane pre-treating Imidacloprid pesticide wastewater. The real time nanofiltration (NF) separation model was presented for effective controlling of DK NF separation. The research showed the simulation precision met the application demands, with the correlation coefficient between the simulation and test rejection of COD and salt over 0.99, and absoluteness error below ±4%. In order to test the prediction of this BPNN simulation model, further NF experiments were carried out. Under the same multifactor condition, the predictions for the NF process performances were found to be in good agreement with the experimental results. This BP simulation model for NF process could be used to test the stability and effectively of NF system, and support the membrane technology well.


Sign in / Sign up

Export Citation Format

Share Document