Artificial Neural Network Mixed-Signal Prototype System for Model Parameter Identification

1998 ◽  
pp. 97-102
Author(s):  
Andrzej Materka ◽  
Pawel Pełczynski ◽  
Michał Strzelecki
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Parameter Identification ◽  
Prototype System ◽  
Mixed Signal ◽  
Model Parameter ◽  
Artificial Neural ◽  
Model Parameter Identification

scholarly journals Transceiver error reduction by design prototype system based on neural network analysis method

2020 ◽  
Vol 18 (3) ◽  
pp. 1244
Author(s):  
Muthna Jasim Fadhil ◽  
Maitham Ali Naji ◽  
Ghalib Ahmed Salman
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Code Word ◽  
Prototype System ◽  
Spiking Neural Network ◽  
Analysis Method ◽  
Neural Network Structure ◽  
Artificial Neural ◽  
Source Dimension ◽  
Proper Condition

<p><span>Code words traditional can be decoding when applied in artificial neural network. Nevertheless, explored rarely for encoding of artificial neural network so that it proposed encoder for artificial neural network forward with major structure built by Self Organizing Feature Map (SOFM). According to number of bits codeword and bits source mentioned the dimension of forward neural network at first then sets weight of distribution proposal choosing after that algorithm appropriate using for sets weight initializing and finally sets code word uniqueness check so that matching with existing. The spiking neural network (SNN) using as decoder of neural network for processing of decoding where depending on numbers of bits codeword and bits source dimension the spiking neural network structure built at first then generated sets codeword by network neural forward using for train spiking neural network after that when whole error reached minimum the process training stop and at last sets code word decode accepted. In tests simulation appear that feasible decoding and encoding neural network while performance better for structure network neural forward a proper condition is achieved with γ node output degree. The methods of mathematical traditional can not using for decoding generated Sets codeword by encoder network of neural so it is prospect good for communication security. </span></p>

Research of WBS Construction Technology for Large Aircraft Based on Artificial Neural Network

2012 ◽  
Vol 220-223 ◽  
pp. 812-818 ◽  
Author(s):  
Kun Fei Wang ◽  
Guang Rong Yan ◽  
Wei Wang
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Prototype System ◽  
Construction Technology ◽  
Work Breakdown Structure ◽  
Relational Work ◽  
Artificial Neural ◽  
Set Up ◽  
Control Work ◽  
Large Aircraft

To ensure development work breakdown comprehensive and thorough for large aircraft product, this paper put forward a WBS decomposition technique based on artificial neural network. On the basis of analysis of the neural network model and work breakdown structure (WBS), project control work breakdown structure (PCWBS), functional work breakdown structure (FWBS), relational work breakdown structure (RWBS), I set up a model which could get PCWBS, FWBS, RWBS and then get WBS according to the knowledge of the similar aircraft development WBS decomposition, so as to realize the automatic acquisition of WBS by input the general project attribute, which replaced the traditional state of depends on the personnel’s experience, and improve efficiency. Based on this, a prototype system is developed, and has been validated by a large aircraft WBS’s generation.

Cole-Cole Model Parameter Estimation from Multi-frequency Complex Resistivity Spectrum Based on the Artificial Neural Network

2021 ◽  
Vol 26 (1) ◽  
pp. 71-77
Author(s):  
Weiqiang Liu ◽  
Rujun Chen ◽  
Liangyong Yang
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Parameter Estimation ◽  
Model Parameters ◽  
Near Surface ◽  
Complex Resistivity ◽  
Model Parameter ◽  
Model Parameter Estimation ◽  
Artificial Neural ◽  
Cole Model

In near surface electrical exploration, it is often necessary to estimate the Cole-Cole model parameters according to the measured multi-frequency complex resistivity spectrum of ore and rock samples in advance. Parameter estimation is a nonlinear optimization problem, and the common method is least square fitting. The disadvantage of this method is that it relies on initial value and the result is unstable when data is confronted with noise interference. To further improve the accuracy of parameter estimation, this paper applied artificial neural network (ANN) method to the Cole-Cole model estimation. Firstly, a large number of forward models are generated as samples to train the neural network and when the data fitting error is lower than the error threshold, the training ends. The trained neural network is directly used to efficiently estimate the parameters of vast amounts of new data. The efficiency of the artificial neural network is analyzed by using simulated and measured spectral induced polarization data. The results show that artificial neural network method has a faster computing speed and higher accuracy in Cole-Cole model parameter estimation.

Sign in / Sign up

Export Citation Format

Share Document