scholarly journals THE RESEARCH OF THE INFLUENCE OF THE STRUCTURAL PARAMETERS OF THE ARTIFICIAL NEURAL NETWORK AND THE NUMBER OF TRAINING SAMPLES ON THE AVERAGE OF THE AVERAGE-SQUARE ERROR OF THE OBTAINED RESULT. THE RECOMMENDATIONS ON SELECTING PARAMETERS AND TRAINING OF THE NETWORK

2017 ◽  
Vol 7 (4) ◽  
pp. 112-114
Author(s):  
N.I. Voitekhov ◽  
◽  
D.A. Chernyshev ◽  
A.N. Lykov ◽  
◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Structural Parameters ◽  
Training Samples ◽  
Artificial Neural ◽  
And Training

scholarly journals ANNETT-O: an ontology for describing artificial neural network evaluation, topology and training

2019 ◽  
Vol 13 (3) ◽  
pp. 179
Author(s):  
Iraklis A. Klampanos ◽  
Athanasios Davvetas ◽  
Antonis Koukourikos ◽  
Vangelis Karkaletsis
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Artificial Neural ◽  
Network Evaluation ◽  
And Training

Offline Signature Verification and Forgery Detection Based on Computer Vision and Fuzzy Logic

2014 ◽  
Vol 3 (4) ◽  
pp. 156
Author(s):  
Gautam S. Prakash ◽  
Shanu Sharma
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Fuzzy Logic ◽  
Detection System ◽  
Structural Parameters ◽  
Signature Verification ◽  
Width Ratio ◽  
Forgery Detection ◽  
Offline Signature Verification ◽  
Artificial Neural

<p>Automated signature verification and forgery detection has many applications in the field of Bank-cheque processing,document  authentication, ATM access etc. Handwritten signatures have proved to be important in authenticating a person's identity, who is signing the document. In this paper a Fuzzy Logic and Artificial Neural Network Based Off-line Signature Verification and Forgery Detection System is presented. As there are unique and important variations in the feature elements of each signature, so in order to match a particular signature with the database, the structural parameters of the signatures along with the local variations in the signature characteristics are used. These characteristics have been used to train the artificial neural network. The system uses the features extracted from the signatures such as centroid, height – width ratio, total area, I<sup>st</sup> and II<sup>nd</sup> order derivatives, quadrant areas etc. After the verification of the signature the angle features are used in fuzzy logic based system for forgery detection.</p>

Parametric Analysis of the Cathode Catalyst Layer of Proton Exchange Membrane Fuel Cells Using Artificial Neural Network

2011 ◽  
Author(s):  
N. Khajeh-Hosseini-Dalasm ◽  
S. Ahadian ◽  
K. Fushinobu ◽  
K. Okazaki
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Proton Exchange Membrane ◽  
Structural Parameters ◽  
Catalyst Layer ◽  
Proton Exchange ◽  
Cathode Catalyst ◽  
Cathode Catalyst Layer ◽  
Artificial Neural ◽  
Exchange Membrane

A mathematical model was developed to study the cathode catalyst layer (CL) performance of a proton exchange membrane fuel cell (PEMFC). A number of CL parameters affecting its performance are implemented into the CL agglomerate model. These parameters are: saturation and eight structural parameters, i.e., ionomer film thickness covering the agglomerate, agglomerate radius, platinum and carbon loading, membrane content, gas diffusion layer penetration content and CL thickness. An artificial neural network (ANN) approach along with statistical methods was used for modeling, prediction, and analysis of the CL performance, which is determined by activation over-potential. The ANN was constructed to develop a relationship between the named (input) parameters and activation overpotential. An statistical analysis, namely, analysis of means (ANOM) was performed on the data obtained by the trained ANN and resulted in the main effect of each input parameter, sensitivity factors of structural parameters and their mutual combination.

An Artificial Neural Network Recognition Method for Single-Phase Earth Fault of Ultra-High Voltage Power Grid

2013 ◽  
Vol 333-335 ◽  
pp. 1659-1662
Author(s):  
Hai Wei Lu ◽  
Gang Wu ◽  
Chao Xiong
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Single Phase ◽  
Training Sample ◽  
Normal Operation ◽  
Recognition Method ◽  
Time Motion ◽  
Training Samples ◽  
Artificial Neural ◽  
Network Diagnosis

Fault diagnosis is very important to make the system return to normal operation quickly after an accident. This paper diagnoses the specific component failure and failure area when the real-time motion information of inputting protection and switch transferred to a trained artificial neural network model by building an artificial neural network diagnosis model of components such as transmission line, bus bar and transformer, training the artificial neural network through taking the failure rule which is found by the historic fault data as a training sample. This method has obvious advantages in the accuracy and speed of diagnosis compared with the previous artificial neural network and overcomes the shortcomings of the incompletion of training samples and not well dealing with the heuristic knowledge.

Predictions of vertical train-bridge response using artificial neural network-based surrogate model

2019 ◽  
Vol 22 (12) ◽  
pp. 2712-2723 ◽  
Author(s):  
Xu Han ◽  
Huoyue Xiang ◽  
Yongle Li ◽  
Yichao Wang
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Dynamic Systems ◽  
Artificial Neural Network Model ◽  
Stochastic Excitations ◽  
Training Samples ◽  
Artificial Neural ◽  
Nonlinear Autoregressive

To improve the efficiency of reliability calculations for vehicle-bridge systems, we present a surrogate modeling method based on a nonlinear autoregressive with exogenous input artificial neural network model and an important sample, which can forecast responses of dynamic systems, such as vehicle-bridge systems, subjected to stochastic excitations. We also propose a process to analyze the method. A quarter-vehicle model is used to verify the proposed method’s precision, and the nonlinear autoregressive with exogenous input artificial neural network model is used to predict responses of vertical vehicle-bridge systems. The results show that, compared to other training samples, the nonlinear autoregressive with exogenous input artificial neural network model has better prediction accuracy when the sample with the maximum response is considered as an important sample and is used to train the nonlinear autoregressive with exogenous input artificial neural network model, and it requires only two-time numerical simulation (or Monte Carlo simulation) at most, which is used in the training of the nonlinear autoregressive with exogenous input artificial neural network model.

Fault Diagnosis of Valve Train of Internal Combustion Engine Based on the Artificial Neural Network and Support Vector Machine

2012 ◽  
Vol 605-607 ◽  
pp. 729-733
Author(s):  
Feng Rong Bi ◽  
Zhen Song
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Support Vector Machine ◽  
Fault Diagnosis ◽  
Combustion Engine ◽  
Valve Train ◽  
Support Vector ◽  
Valve Mechanism ◽  
Training Samples ◽  
Artificial Neural

The theory of artificial neural network and support vector machine has been introduced. According to the characteristics of vibration signal for the valve mechanism, fault diagnosis has been proposed for abnormal valve clearance based on artificial neural network (ANN) and support vector machine (SVM). Two kinds of intelligent technology have been compared in fault identification by changing the number of training samples. The diagnosis has indicated that at small number of training samples SVM has high generalization ability, and at large number of training samples, ANN has exact recognition when it comes to diagnosing valve train.

Sign in / Sign up

Export Citation Format

Share Document