Effects of hidden nodes on network structure inference

Stress will definitely be experienced by every human being and the level of stress experienced by each individual is different. Stress experienced by students certainly will disturb their study if it is not handled quickly and appropriately. Therefore we have created an expert system using a neural network backpropagation algorithm to help counselors to predict the stress level of students. The network structure of the experiment consists of 26 input nodes, 5 hidden nodes, and 2 the output nodes, learning rate of 0.1, momentum of 0.1, and epoch of 5000, with a 100% accuracy rate. Index Terms - Stress on study, expert system, neural network, Stress Prediction

Download Full-text

A Power Transformer Fault Diagnosis Method Based on Random Vector Functional-Link Neural Network

Mathematical Problems in Engineering ◽

10.1155/2021/6656061 ◽

2021 ◽

Vol 2021 ◽

pp. 1-18

Author(s):

Qian Wang ◽

Shinan Wang ◽

Rong Shi ◽

Yong Li

Keyword(s):

Neural Network ◽

Fault Diagnosis ◽

Network Model ◽

Random Vector ◽

Network Structure ◽

Theoretical Basis ◽

Parameter Selection ◽

Functional Link ◽

Transformer Fault ◽

Hidden Nodes

The random vector functional link (RVFL) network is suitable for solving nonlinear problems from transformer fault symptoms and different fault types due to its simple structure and strong generalization ability. However, the RVFL network has a disadvantage in that the network structure, and parameters are basically determined by experiences. In this paper, we proposed a method to improve the RVFL neural network algorithm by introducing the concept of hidden node sensitivity, classify each hidden layer node, and remove nodes with low sensitivity. The simplified network structure could avoid interfering nodes and improve the global search capability. The five characteristic gases produced by transformer faults are divided into two groups. A fault diagnosis model of three layers with four classifiers was built. We also investigated the effects of the number of hidden nodes and scale factors on RVFL network learning ability. Simulation results show that the number of implicit layer nodes has a large impact on the network model when the number of input dimensions is small. The network requires a higher number of implicit layer neurons and a smaller threshold range. The size of the scale factor has significant influence on the network model with larger input dimension. This paper describes the theoretical basis for parameter selection in RVFL neural networks. The theoretical basis for the selection of the number of hidden nodes, and the scale factor is derived. The importance of parameter selection for the improvement of diagnostic accuracy is verified through simulation experiments in transformer fault diagnosis.

Download Full-text

An alter-centric perspective on employee innovation: The importance of alters’ creative self-efficacy and network structure.

Journal of Applied Psychology ◽

10.1037/apl0000220 ◽

2017 ◽

Vol 102 (9) ◽

pp. 1360-1374 ◽

Cited By ~ 20

Author(s):

Travis J. Grosser ◽

Vijaya Venkataramani ◽

Giuseppe (Joe) Labianca

Keyword(s):

Network Structure ◽

Self Efficacy ◽

Creative Self

Download Full-text

Türkiye'de iller arası göçlerin nodexl ile sosyal ağ analizi

GÖÇ DERGİSİ ◽

10.33182/gd.v4i1.573 ◽

2017 ◽

Vol 4 (1) ◽

pp. 82-109 ◽

Cited By ~ 1

Author(s):

Mustafa Yakar ◽

Fatma Sert Eteman

Keyword(s):

Network Structure ◽

Population Data ◽

Single Mode ◽

Turkish Population ◽

Place Of Birth ◽

Place Of Residence ◽

Migration Flow ◽

Population Structures ◽

The Republic ◽

Provincial Scale

Türkiye'de 20.yy'ın ortasından itibaren başlayan iç göçler zamanla kurulan göçmen ağları ile süreklilik kazanmış ve ülke içinde nüfusun kır-kent dağılımını değiştirecek boyutlara erişmiştir. Araştırma, göçün doğum yeri verisinden hareketle ikamet edilen yerdeki nüfus miktarına göre alınan ve verilen göç akışının büyüklüğünü iller ölçeğinde yönlü ağlar kullanılarak analiz edilmesini amaçlamaktadır. Araştırmada, TÜİK tarafından yayınlanmış olan 2015 yılına ait, iller ölçeğinde doğum yerine göre ikamet yeri verisi kullanılmıştır. Göçün kaynak ve hedef sahaları arasındaki akışını incelemek için NodeXL ile oluşturulan tek modlu, yönlü ve ağırlıklandırılmış göç ağının istatistiksel olarak tam ağ yapısına sahip olduğu görülmüştür. Ağ grafiklerinden ve istatistiklerinden göç hareketinin doğudan batıya doğru gerçekleştiği ve İstanbul’ un ülkenin tamamına hâkim bir görünüme sahip olduğu anlaşılmaktadır. Türkiye nüfusunun cumhuriyet tarihi içinde geçirdiği iç göç süreçleriyle birlikte ülke içinde kurulmuş ve oldukça karmaşık bir görünüme sahip ağ yapısının olduğu ileri sürülebilir. Kurulan ağlar göçlerin devamını sağladığı gibi, göçün yöneldiği merkezlerde daha heterojen nüfus yapılarının ortaya çıkmasına yol açmıştır.ABSTRACT IN ENGLISHSocial Network Analysis of Migration Inter Provinces In Turkey with Nodexl The internal migrations which started in Turkey in the middle of the 20th century have gained permanency with the migration networks that were established at the time and reached dimensions which have the potential to change the rural-urban distribution of the population within the country. The study aims to analyze the magnitude of the incoming and outgoing migration flow at the provincial scale based on the population data for place of birth according to place of residence by using directional networks. Place of residence according to place of birth at the provincial scale data for 2015 published by TÜİK was used in the study. A single mode, directional and weighted migration network created with NodeXL to examine the migration flows between the source and target has a statistically complete network structure. The network graphs and statistics show that the migrations have taken place from east to west and Istanbul has a view as dominant of the country. It can be argued that internal network structure of Turkish population has a very complex view because of internal migration in the history of the republic. The established networks have enabled the continuation of migration and have manifested as the emergence of more heterogeneous population structures in centers where migration had been directed.

Download Full-text

Application of Fractal Methods to Ensure the Cyber-Resilience of Self-Organizing Networks

Nonlinear Phenomena in Complex Systems ◽

10.33581/1561-4085-2019-22-4-336-341 ◽

2019 ◽

Vol 22 (4) ◽

pp. 336-341

Author(s):

D. V. Ivanov ◽

D. A. Moskvin

Keyword(s):

Information Security ◽

Network Structure ◽

Self Regulation ◽

Security Threats ◽

Self Organizing Networks ◽

Self Organizing ◽

Fractal Methods

In the article the approach and methods of ensuring the security of VANET-networks based on automated counteraction to information security threats through self-regulation of the network structure using the theory of fractal graphs is provided.

Download Full-text