A proactive metaheuristic model for optimizing weights of artificial neural network

Alsaeedi, Ali Hakem; Aljanabi, Ali Hussein; Manna, Mehdi Ebady; Albukhnefis, Adil L.

doi:10.11591/ijeecs.v20.i2.pp976-984

Cited by 16 publications

(13 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Firstly we propose the betweenness centrality algorithm which evaluates The frequency of each node acts or performs as a connecter or a bridge over the shortest route connecting two more nodes [17]. Being between implies that a vertex can affect the flow of information between several network nodes.…”

Section: Methodsmentioning

confidence: 99%

Complex networks analysis: centrality measures

Saber¹,

Hamid²

2023

IJEECS

View full text Add to dashboard Cite

<span lang="EN-US">The centrality of an edge in a graph is proposed to be the degree of sensitivity of a graph distance function to the weight of the edge under consideration. Many centrality metrics are available in network analysis and are effectively used in the investigation of social network properties. Node position is one of them. In this paper, we propose a novel importance of nodes showing how to locate the most essential nodes in a network and to construct a centrality measure for each node in the network, sort the nodes by centralities, and focus on the top ranked nodes, which are the most relevant in terms of this centrality measure. Our research aims to explain how to identify the most important nodes in networks. A centrality metric should be established for each node in the network, and then the nodes based on their centralities, focusing on the top-ranked nodes, which in light of this importance, might be regarded as the most pertinent measure.</span>

show abstract

Section: Methodsmentioning

confidence: 99%

Complex networks analysis: centrality measures

Saber¹,

Hamid²

2023

IJEECS

View full text Add to dashboard Cite

show abstract

“…Along with the fact that it is necessary to assess possible changes as a result of such impacts, it is necessary to simulate the state of the information system (Startup) and determine the predicted states of its parameters. This can be done thanks to a trained neural network [25], which is based on data from the initial stages of creating and developing a startup. In accordance with the assessment of the state of effectiveness of such a project, a decision is made whether to make such changes to the parameters of the Information System or not.…”

Section: Methodsmentioning

confidence: 99%

Development of a model for evaluating the effectiveness of innovative startups based on information cycles and using neural networks

Morozov

Kolomiiets²,

Olga³

2021

IJEECS

View full text Add to dashboard Cite

An integrated approach to the creation and development of innovative startup projects in the field of information technology is considered. To conduct research, the authors proposed a model of information cycles of startup projects based on the creation of an information model of such projects. At the same time there are dynamic processes of changes in the parameters of the model, which are turbulent in nature and require the use of tools and methods of artificial intelligence for research. The key areas of knowledge of such influence are defined. The mathematical model of processes of management of development of IT startups on the basis of creation and development of a difficult IT product, taking into account influences of environments of the project is constructed, the basic characteristics are allocated and parameters are defined. To do this, the construction of predictive models is proposed to be carried out by modified Demarc trends, the method of self-organization and the neural network. The modeling of the main objective functions of the mathematical model of these processes is performed. The analysis of the received results is carried out and the conclusions are made.

show abstract

“…Customer behavior changes in line with the defined business use case. Customizing each prediction model costs redundant time and effort for each case [7]. Herein, data scientists automate the data modelling process, so it generalizes the modelling process and offers it as a service [8].…”

Section: Introductionmentioning

confidence: 99%

Smart evaluation for deep learning model: churn prediction as a product case study

Elgohary¹,

Galal

Mosa

et al. 2023

Bulletin EEI

View full text Add to dashboard Cite

Customer churn prediction recently is one of the vital issues that confronts diverse business industries to sustain the customers base and profits. On the other hand, data scientists employ gigantic customer data to automate the data modelling process to offer these models as a generally portable service. This research has two main contributions: deep learning customer churn prediction model and smart evaluation prediction model service. So, this service harnesses any customer data to automate building, evaluation, and deployment of the churn prediction model. The research consists of three main parts. Firstly, it illustrates the dataset labelling which annotates customers data into churn or non-churn. Secondly, the deep learning churn prediction framework using convolutional neural network (CNN) algorithm. Finally, a case study is presented to show how churn prediction service is automatically trained and generated based on real customer data, where CNN parameters are adapted to achieve the most reliable performance in line with customers' behavior. The applied case study achieves accuracy 0.77, area under the curve (AUC) 0.84 and f1 score 0.83.

show abstract

A proactive metaheuristic model for optimizing weights of artificial neural network

Cited by 16 publications

References 17 publications

Complex networks analysis: centrality measures

Complex networks analysis: centrality measures

Development of a model for evaluating the effectiveness of innovative startups based on information cycles and using neural networks

Smart evaluation for deep learning model: churn prediction as a product case study

Contact Info

Product

Resources

About