Preferred Language
Articles
/
alkej-355
Model Reference Adaptive Control based on a Self-Recurrent Wavelet Neural Network Utilizing Micro Artificial Immune Systems
...Show More Authors

Abstract 

This paper presents an intelligent model reference adaptive control (MRAC) utilizing a self-recurrent wavelet neural network (SRWNN) to control nonlinear systems. The proposed SRWNN is an improved version of a previously reported wavelet neural network (WNN). In particular, this improvement was achieved by adopting two modifications to the original WNN structure. These modifications include, firstly, the utilization of a specific initialization phase to improve the convergence to the optimal weight values, and secondly, the inclusion of self-feedback weights to the wavelons of the wavelet layer. Furthermore, an on-line training procedure was proposed to enhance the control performance of the SRWNN-based MRAC. As the training method, the recently developed modified micro artificial immune system (MMAIS) was used to optimize the parameters of the SRWNN. The effectiveness of this control approach was demonstrated by controlling several nonlinear dynamical systems. For each of these systems, several evaluation tests were conducted, including control performance tests, robustness tests, and generalization tests. From these tests, the SRWNN-based MRAC has exhibited its effectiveness regarding accurate control, disturbance rejection, and generalization ability. In addition, a comparative study was made with other related controllers, namely the original WNN, the artificial neural network (ANN), and the modified recurrent network (MRN). The results of these comparison tests indicated the superiority of the SRWNN controller over the other related controllers.

Keywords: Artificial neural network, micro artificial immune system, model reference adaptive control, self-recurrent wavelet neural network , Wavelet neural network.

Crossref
View Publication Preview PDF
Quick Preview PDF
Publication Date
Wed Jul 01 2026
Journal Name
Aip Conference Proceedings
Quantile fuzzy regression
...Show More Authors

Regression models are among the most important tools in scientific research and data analysis. Among these models, fuzzy regression models stand out as a modern form that addresses issues of uncertain data that do not conform to the assumptions of traditional models. In this study, we present fuzzy regression models with a focus on fuzzy linear quantitative models, in addition to fuzzy support vector machine (SVM) models. Generally, linear models are considered less effective compared to non-linear models, and to address this issue, hybrid models combining both types have been introduced. The concept of hybrid models has been generalized to fuzzy models in this paper, where we introduce a hybrid model that combines both linear and non-linea

... Show More
View Publication
Crossref
Publication Date
Tue Oct 01 2019
Journal Name
Journal Of Engineering
Evaluation of the Performance of Online GPS/GNSS Data Processing Services for Monitoring the Land Deformations and Movements
...Show More Authors

In recent years, the Global Navigation Satellite Services (GNSS) technology has been frequently employed for monitoring the Earth crust deformation and movement. Such applications necessitate high positional accuracy that can be achieved through processing GPS/GNSS data with scientific software such as BERENSE, GAMIT, and GIPSY-OSIS. Nevertheless, these scientific softwares are sophisticated and have not been published as free open source software. Therefore, this study has been conducted to evaluate an alternative solution, GNSS online processing services, which may obtain this privilege freely. In this study, eight years of GNSS raw data for TEHN station, which located in Iran, have been downloaded from UNAVCO website

... Show More
View Publication Preview PDF
Crossref (2)
Crossref
Publication Date
Mon Dec 10 2018
Journal Name
Aro-the Scientific Journal Of Koya University
Membrane Computing for Real Medical Image Segmentation
...Show More Authors

In this paper, membrane-based computing image segmentation, both region-based and edge-based, is proposed for medical images that involve two types of neighborhood relations between pixels. These neighborhood relations—namely, 4-adjacency and 8-adjacency of a membrane computing approach—construct a family of tissue-like P systems for segmenting actual 2D medical images in a constant number of steps; the two types of adjacency were compared using different hardware platforms. The process involves the generation of membrane-based segmentation rules for 2D medical images. The rules are written in the P-Lingua format and appended to the input image for visualization. The findings show that the neighborhood relations between pixels o

... Show More
View Publication Preview PDF
Crossref (2)
Crossref
Publication Date
Wed Dec 01 2021
Journal Name
Journal Of Economics And Administrative Sciences
Using Fuzzy Inference to Evaluation Suppliers in Diyala General Electric Industries Company
...Show More Authors

The research aims to evaluate the suppliers at Diyala general electric industries company conducted in an environment of uncertainty and fuzzy where there is no particular system followed by the company, and also aims to use the problem of traveling salesman problem in the process of transporting raw materials from suppliers to the company in a fuzzy environment. Therefore, a system based on mathematical methods and quantity was developed to evaluate the suppliers. Fuzzy inference system (FIS) and fuzzy set theory were used to solve this problem through (Matlab) and the problem of the traveling salesman in two stages was also solved by the first stage of eliminating the fuzzing of the environment using the rank function method, w

... Show More
View Publication Preview PDF
Crossref
Publication Date
Mon Jun 05 2023
Journal Name
Journal Of Engineering
Experimental Evaluation of the Performance of One-Axis Daily Tracking and Fixed PV Module in Baghdad, Iraq
...Show More Authors

An attempt was made to evaluate the PV performance of one-axis daily tracking and fixed system for Baghdad, Iraq. Two experimental simulations were conducted on a PV module for that purpose. Measurements included incident solar radiation, load voltage and load current. The first experiment was carried out for six months of winter half of year to simulate the one-axis daily tracking. The azimuth angle was due south while the tilt angle was being set to optimum according to each day of simulation. The second experiment was done at one day to simulate the PV module of fixed angles. It is found that there is a significant power gain of 29.6% for the tracking system in respect to the fixed one. The one-axis daily tracking was much more effect

... Show More
View Publication Preview PDF
Crossref (1)
Crossref
Publication Date
Mon Jul 01 2024
Journal Name
Journal Of Engineering
Efficient Intrusion Detection Through the Fusion of AI Algorithms and Feature Selection Methods
...Show More Authors

With the proliferation of both Internet access and data traffic, recent breaches have brought into sharp focus the need for Network Intrusion Detection Systems (NIDS) to protect networks from more complex cyberattacks. To differentiate between normal network processes and possible attacks, Intrusion Detection Systems (IDS) often employ pattern recognition and data mining techniques. Network and host system intrusions, assaults, and policy violations can be automatically detected and classified by an Intrusion Detection System (IDS). Using Python Scikit-Learn the results of this study show that Machine Learning (ML) techniques like Decision Tree (DT), Naïve Bayes (NB), and K-Nearest Neighbor (KNN) can enhance the effectiveness of an Intrusi

... Show More
View Publication Preview PDF
Scopus (5)
Crossref (1)
Scopus Crossref
Publication Date
Fri May 01 2026
Journal Name
2026 Xxix International Conference On Soft Computing And Measurements (scm)
Hierarchical Multi-Stage Intrusion Detection with Feature Inheritance and Prediction Verification
...Show More Authors

One of the challenges faced by traditional intrusion detection systems based on machine learning or deep learning is instability when dealing with unbalanced network traffic, leading to failure in detecting certain attacks (minority classifications). Additionally, they struggle with multi-stage attacks, resulting in an increase in false alarms. This paper presents a hierarchical intrusion detection system supported by a Prediction Verification Layer (PVL) and a Feature Inheritance Mechanism (FIM). Where PVL contributes to documenting the system’s final decision and increasing sensitivity to minority attacks, FIM also helps in inheriting features from previous layers and correcting errors as much as possible. Additionally, it allows for ad

... Show More
View Publication
Crossref
Publication Date
Mon Nov 06 2023
Journal Name
Al- Ustath Journal
INFINITIVAL AND GERUNDIAL CONSTRUCTIONS OF ASPECTUAL VERBS IN SELECTED BRITISH AND AMERICAN NOVELS
...Show More Authors

Abstract Infinitives and gerunds are non-finite verb forms which cannot be indicated by tense, number, or person. The construction of non-finite verbs is intricate because of their nature of meanings, forms, and functions. The major problem is that both infinitival and gerundial complements have identical functions and occupy identical positions in the sentences. Thus, there is a confusion in using an infinitival and gerundial forms after aspectual verbs. The selection of either one of these two forms as complements is controlled syntactically or semantically. Moreover, both forms can be used usually with similar predicate but with neat difference in meaning. In addition, there are problems with controlling the use of aspect, since aspectua

... Show More
Preview PDF
Publication Date
Thu Apr 01 2021
Journal Name
Neuroquantology
Finding Most Stable Isobar for Nuclides with Mass Number (165- 175) against Beta Decay
...Show More Authors

In the beta decay process, a neutron converts into a proton, or vice versa, so the atom in this process changes to a more stable isobar. Bethe-Weizsäcker used a quasi-experimental formula in the present study to find the most stable isobar for isobaric groups of mass nuclides (A=165-175). In a group of isobars, there are two methods of calculating the most stable isobar. The most stable isobar represents the lowest parabola value by calculating the binding energy value (B.E) for each nuclide in this family, and then drawing these binding energy values as a function of the atomic number (Z) in order to obtain the mass parabolas, the second method is by calculating the atomic number value of the most stable isobar (ZA). The results show

... Show More
Publication Date
Mon Jun 01 2015
Journal Name
Journal Of Engineering
Unity Sliding Mode Controller Design for Active Magnetic Bearings System
...Show More Authors

Active Magnetic Bearings (AMBs) are progressively being implemented in a wide variety of applications. Their exclusive appealing features make them suitable for solving traditional rotor-bearing problems using novel design approaches for rotating machinery.  In this paper, a linearized uncertain model of AMBs is utilized to develop a nonlinear sliding mode controller based on Lyapunov function for the electromechanical system. The controller requires measurements of the rotor displacements and their derivatives. Since the control law is discontinuous, the proposed controller can achieve a finite time regulation but with the drawback of the chattering problem. To reduce the effect of this problem, the gain of the uni

... Show More
View Publication Preview PDF