Development Multiple Neuro-Fuzzy System Using Back-propagation Algorithm

Alshawi, Imad S.; Allamy, Haider Khalaf; Khan, Rafiqul Zaman

doi:10.24297/ijmit.v6i2.736

Cited by 5 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In most cases, fuzzy variables consist of more than one membership function related to them. As a result, the fuzzification process will produce several membership values for a single crisp input [22].…”

Section: System Designmentioning

confidence: 99%

A New Approach Based on Intelligent Method to Classify Quality of Service

Altmemi

Abdulzahra

Alshawi

2022

IJCAI

View full text Add to dashboard Cite

Computer networks are used more frequently for time-sensitive applications like voice over internet protocol and other communications. In computer networks, quality of service (QoS) can be crucial since it makes it easier to assess a network's performance and offers mechanisms for enhancing its performance. As a result, understanding the QoS provided by networks is essential for both network users and service providers to assess how well the transmission requirements of different applications are satisfied and to implement improvements to network performance. Next-generation monitoring systems must not only detect network performance deterioration instantly but also pinpoint the underlying cause of quality of service problems to achieve strict network standards. A brand-new fuzzy logic-based algorithm is suggested as a solution to this issue. Thus, the proposed approach was evaluated and compared with probabilistic neural networks (PNN) and Bayesian classification, as well as network performance measurement, latency, jitter, and packet loss. All approaches correctly classified the QoS categories, although generally, the fuzzy approach outperformed PNN and Bayesian. An improved comprehension of the network performance is acquired by precisely determining its QoS.Povzetek: Razvit je nov algoritem za odkrivanje vzroka za poslabšano kvaliteto storive v omrežjih.

show abstract

Section: System Designmentioning

confidence: 99%

A New Approach Based on Intelligent Method to Classify Quality of Service

Altmemi

Abdulzahra

Alshawi

2022

IJCAI

View full text Add to dashboard Cite

show abstract

“…In ANN, since hidden neurons and layers are the main units, initially, determination of ANN architecture, depth and width, is the most important issue that should be considered before initialization of any other hyperparameters [9,10]. Furthermore, during the training process, majority of other hyperparameters can be modified accurately with less computational complexity if the architecture of ANN were initialized ideally.…”

Section: Introductionmentioning

confidence: 99%

Using Persistence Barcode to Show the Impact of Data Complexity on the Neural Network Architecture

Alhelfi

Ali

2022

eijs

View full text Add to dashboard Cite

It is so much noticeable that initialization of architectural parameters has a great impact on whole learnability stream so that knowing mathematical properties of dataset results in providing neural network architecture a better expressivity and capacity. In this paper, five random samples of the Volve field dataset were taken. Then a training set was specified and the persistent homology of the dataset was calculated to show impact of data complexity on selection of multilayer perceptron regressor (MLPR) architecture. By using the proposed method that provides a well-rounded strategy to compute data complexity. Our method is a compound algorithm composed of the t-SNE method, alpha-complexity algorithm, and a persistence barcode reading method to extract the Betti number of a dataset. After that, MLPR were trained using that dataset using a single hidden layer with increased hidden neurons. Then, increased both hidden layers and hidden neurons. Our empirical analysis has shown that the training efficiency of MLPR severely depends on its architecture’s ability to express the homology of the dataset.

show abstract

“…Such models are called classifiers which predict categorical (discrete, unordered) class labels [6], [7]. Many classification methods have been proposed by researchers in ML, like the DT classifier [8], [9] and Neural Network classifier [10], [11]. In this paper, the researchers propose to create e-government from three government departments (Military, Social Welfare, and Statistics_ planning) by applying ML for five classifiers (SVM, DT, KNN, RF, and NB), using the ECR data, and choosing the algorithm with the highest accuracy for all government departments.…”

Section: Introductionmentioning

confidence: 99%

Big Data in E-government: Classification and Prediction using Machine Learning Algorithms

Altamimi¹

2022

IJICI

View full text Add to dashboard Cite

Many countries have used big data to develop their institutions, such as Estonia in policing, India in health care, and the development of agriculture in the United Kingdom, etc. Data is very important as it is no longer oil that is the most valuable resource in the world, but data. This research examines ways to develop the Iraqi state institutions by using the big data of one of its institutions (electronic civil registry) (ECR) using the mining and analysis of this data. The pre-processing and analysis of this data are carried out depending on the needs of each institution and then using Machine Learning (ML) techniques. Its use has shown remarkable results in many areas, especially in data analysis, classification and forecasting. We applied five ML algorithms that are Support Vector Machine (SVM), Decision Tree (DT), K-Nearest Neighbor (KNN), Random Forest (RF), and Naive Bayes (NB) carried out in the Orange Data Mining tool. According to the simulation results of the proposed system, the accuracy of the classifications was around 100%, 99%, and 100% for the military department by the SVM classifier, the social welfare department by the RF classifier, and the statistics-planning department by the SVM classifier, respectively.

show abstract

Development Multiple Neuro-Fuzzy System Using Back-propagation Algorithm

Cited by 5 publications

References 11 publications

A New Approach Based on Intelligent Method to Classify Quality of Service

A New Approach Based on Intelligent Method to Classify Quality of Service

Using Persistence Barcode to Show the Impact of Data Complexity on the Neural Network Architecture

Big Data in E-government: Classification and Prediction using Machine Learning Algorithms

Contact Info

Product

Resources

About