scholarly journals Self-Supervised Voltage Sag Source Identification Method Based on CNN

Energies ◽  
2019 ◽  
Vol 12 (6) ◽  
pp. 1059 ◽  
Author(s):  
Danqi Li ◽  
Fei Mei ◽  
Chenyu Zhang ◽  
Haoyuan Sha ◽  
Jianyong Zheng
Keyword(s):  
Neural Network ◽  
Source Identification ◽  
The Self ◽  
Convolution Neural Network ◽  
Voltage Sag ◽  
Training Process ◽  
Identification Method ◽  
Network Training ◽  
Three Phase

A self-supervised voltage sag source identification method based on a convolution neural network is proposed in this study. In addition, a self-supervised CNN (Convolutional Neural Networks) voltage sag source identification model is constructed on the basis of the convolution neural network and AutoEncoder. The convolution layer and pool layer in CNN are used to extract the voltage sag characteristics, and the self-supervised network training process is realized based on the principle of AE. In the constructed mode, features which reflect the data characteristics are used rather than artificial features, thus improving the accuracy of practical application. It is unnecessary to input a lot of correct labels before the self-supervised training process. The model can meet the requirements of sag source identification on timeliness, practicability, diversity, and versatility in the context of modern big data. In this study, three-phase asymmetric sag sources in sag sources are classified into more detailed categories according to different fault phases. Therefore, the proposed method can not only identify the voltage sag source, but also accurately determine the specific fault phase. Finally, the optimal parameters of the model are recognized through a case study, and a self-supervised CNN model is established based on the data type of voltage sag. This model extracts features and identifies sag sources through the measured sag data. The superiority of the proposed method is verified by a comparison.

scholarly journals A Functionally Separate Autoencoder

2020 ◽  
Author(s):  
Jinxin Wei
Keyword(s):  
Neural Network ◽  
Supervised Learning ◽  
Negative Feedback ◽  
Learning Process ◽  
Inverse Function ◽  
Convolution Neural Network ◽  
Training Process ◽  
New Knowledge

<p><b>According to kids’ learning process, an auto</b><b>-</b><b>encoder</b><b> is designed</b><b> which can be split into two parts. The two parts can work well separately.The top half is an abstract network which is trained by supervised learning and can be used to classify and regress. The bottom half is a concrete network which is accomplished by inverse function and trained by self-supervised learning. It can generate the input of abstract network from concept or label. The network can achieve its intended functionality through testing by mnist dataset and convolution neural network.</b><b> R</b><b>ound function</b><b> is added between the abstract network and concrete network in order</b><b> to get the the representative generation of class.</b><b> T</b><b>he generation ability </b><b> can be increased </b><b>by adding jump connection and negative feedback. At last, the characteristics of </b><b>the</b><b> network</b><b> is discussed</b><b>. </b><b>T</b><b>he input can </b><b>be </b><b>change</b><b>d </b><b>to any form by encoder and then change it back by decoder through inverse function. The concrete network can be seen as the memory stored by the parameters.</b><b> </b><b>Lethe is that when new knowledge input,</b><b> </b><b>the training process make</b><b>s</b><b> the parameter</b><b>s</b><b> change.</b><b></b></p>

scholarly journals MATHEMATICAL MODELS AND RECOGNITION METHODS FOR MOBILE SUBSCRIBERS MUTUAL PLACEMENT

T-Comm ◽  
2021 ◽  
Vol 15 (4) ◽  
pp. 49-56
Author(s):  
Vadim V. Ziyadinov ◽  
◽  
Maxim V. Tereshonok ◽  
Keyword(s):  
Neural Network ◽  
Mathematical Model ◽  
Mobile Networks ◽  
Convolution Neural Network ◽  
Mass Action ◽  
Validation Dataset ◽  
Neural Network Training ◽  
Processing Application ◽  
Network Training ◽  
Placement Types

The challenge of mobile subscribers’ groups and crowd’s behavior prediction during the mass events is now increasingly important. Operative methods application of this task solution is difficult; accordingly, development and application of technical methods is necessary. The method of this problem solution consists of subscribers’ telephone conversations recording in a zone of mass action, and the following speech recognition, the semantic analysis and statistical processing application. However, there is a tendency demand decrease for mobile systems voice services with simultaneous demand growth for data traffic nowadays. The purpose of this paper is to create a mathematical model of mobile networks subscribers’ mutual placement types, applicable for automatization of the subscribers’ activities nature prediction systems. The research method consists of mathematical simulation model development for pseudo-random examples generation of subscribers’ mutual placement types set, creation of training dataset, convolution neural network training and usage of training results to recognize the new examples. The results obtained. A mathematical model is proposed allowing to create a representative training and validation dataset of mobile networks subscribers’ mutual placement types for neural network training and testing. The convolution neural network trained using these samples has shown high classification accuracy results with a wide class of subscribers’ mutual placement types.

scholarly journals A Functionally Separate Autoencoder

2021 ◽  
Author(s):  
Jinxin Wei
Keyword(s):  
Neural Network ◽  
Supervised Learning ◽  
Negative Feedback ◽  
Learning Process ◽  
Inverse Function ◽  
Convolution Neural Network ◽  
Training Process ◽  
New Knowledge

<p><b>According to kids’ learning process, an auto</b><b>-</b><b>encoder</b><b> is designed</b><b> which can be split into two parts. The two parts can work well separately.The top half is an abstract network which is trained by supervised learning and can be used to classify and regress. The bottom half is a concrete network which is accomplished by inverse function and trained by self-supervised learning. It can generate the input of abstract network from concept or label. The network can achieve its intended functionality through testing by mnist dataset and convolution neural network.</b><b> R</b><b>ound function</b><b> is added between the abstract network and concrete network in order</b><b> to get the the representative generation of class.</b><b> T</b><b>he generation ability </b><b> can be increased </b><b>by adding jump connection and negative feedback. At last, the characteristics of </b><b>the</b><b> network</b><b> is discussed</b><b>. </b><b>T</b><b>he input can </b><b>be </b><b>change</b><b>d </b><b>to any form by encoder and then change it back by decoder through inverse function. The concrete network can be seen as the memory stored by the parameters.</b><b> </b><b>Lethe is that when new knowledge input,</b><b> </b><b>the training process make</b><b>s</b><b> the parameter</b><b>s</b><b> change.</b><b></b></p>

A comparative case study of neural network training by using frame-level cost functions for automatic speech recognition purposes in Spanish

2020 ◽  
Vol 79 (27-28) ◽  
pp. 19669-19715
Author(s):  
Aldonso Becerra ◽  
J. Ismael de la Rosa ◽  
Efrén González ◽  
A. David Pedroza ◽  
N. Iracemi Escalante ◽  
...  
Keyword(s):  
Neural Network ◽  
Speech Recognition ◽  
Automatic Speech Recognition ◽  
Cost Functions ◽  
Comparative Case Study ◽  
Neural Network Training ◽  
Network Training

A VISUALIZATION AND DESIGN TOOL (AVID) FOR DATA MINING WITH THE SELF-ORGANIZING FEATURE MAP

2000 ◽  
Vol 09 (03) ◽  
pp. 369-375
Author(s):  
SUSAN E. GEORGE
Keyword(s):  
Neural Network ◽  
Data Mining ◽  
Software Tool ◽  
Design Tool ◽  
The Self ◽  
Training Data ◽  
Feature Map ◽  
Network Training ◽  
Som Network ◽  
Selection Of

This paper presents a software tool called AVID (A VIsualization and Design) which is particularly useful for data mining with an artificial neural network known as the self-organising feature map (SOM). AVID supports network training in both the i) selection of network inputs and ii) visualisation of the trained SOM. Both these features are novel aids to SOM network training and are particularly important when consideration is given to using the SOM for data mining. Once trained the SOM produces a 2-dimensional topological ordering of the input training data and it is particularly useful for representing the relationships within multi-dimensional data. The main classes within the data can be identified from the output map. AVID is an important software tool which enables data mining with the SOM by the selection of network inputs and the subsequent visualisation of the classes within these input vectors.

Sign in / Sign up

Export Citation Format

Share Document