Preferred Language
Articles
/
jih-1335
Density and Approximation by Using Feed Forward Artificial Neural Networks
...Show More Authors

I n  this  paper ,we 'viii  consider  the density  questions  associC;lted with  the single  hidden layer feed forward  model. We proved  that a FFNN   with   one   hidden   layer  can   uniformly   approximate   any continuous  function  in C(k)(where k is a compact set in R11 ) to any required accuracy.

 

However, if the set of basis function is dense then the ANN's can has al most one hidden layer. But if the set of basis function  non-dense, then we  need more  hidden layers. Also, we have shown  that there exist  localized functions and that there is no theoretical lower bound on    the   degree   of    a pproximation    common    to   all    acti vation functions(contrary to the si tuation in the single hidden layer model).

View Publication Preview PDF
Quick Preview PDF
Publication Date
Tue Apr 02 2024
Journal Name
Engineering, Technology & Applied Science Research
Two Proposed Models for Face Recognition: Achieving High Accuracy and Speed with Artificial Intelligence
...Show More Authors

In light of the development in computer science and modern technologies, the impersonation crime rate has increased. Consequently, face recognition technology and biometric systems have been employed for security purposes in a variety of applications including human-computer interaction, surveillance systems, etc. Building an advanced sophisticated model to tackle impersonation-related crimes is essential. This study proposes classification Machine Learning (ML) and Deep Learning (DL) models, utilizing Viola-Jones, Linear Discriminant Analysis (LDA), Mutual Information (MI), and Analysis of Variance (ANOVA) techniques. The two proposed facial classification systems are J48 with LDA feature extraction method as input, and a one-dimen

... Show More
View Publication Preview PDF
Scopus (9)
Crossref (10)
Scopus Clarivate Crossref
Publication Date
Wed Feb 01 2023
Journal Name
Mathematical Models And Computer Simulations
Function Approximation Technique (FAT)-Based Adaptive Feedback Linearization Control for Nonlinear Aeroelastic Wing Models Considering Different Actuation Scenarios
...Show More Authors

View Publication
Crossref (1)
Crossref
Publication Date
Fri Oct 01 2021
Journal Name
International Journal Of Mechanical Engineering And Robotics Research
Proportional-Derivative PD Vibration Control with Adaptive Approximation Compensator for a Nonlinear Smart Thin Beam Interacting with Fluid
...Show More Authors

This work is concerned with the vibration attenuation of a smart beam interacting with fluid using proportional-derivative PD control and adaptive approximation compensator AAC. The role of the AAC is to improve the PD performance by compensating for unmodelled dynamics using the concept of function approximation technique FAT. The key idea is to represent the unknown parameters using the weighting coefficient and basis function matrices/vectors. The weighting coefficient vector is updated using Lyapunov theory. This controller is applied to a flexible beam provided with surface bonded piezo-patches while the vibrating beam system is submerged in a fluid. Two main effects are considered: 1) axial stretching of the vibrating beam that leads

... Show More
View Publication Preview PDF
Crossref (3)
Crossref
Publication Date
Tue Nov 13 2018
Journal Name
Ibn Al-haitham Journal For Pure And Applied Sciences
The Approximation Solution of a Nonlinear Parabolic Boundary Value Problem Via Galerkin Finite Elements Method with Crank-Nicolson
...Show More Authors

    This paper deals with finding the approximation solution of a nonlinear parabolic boundary value problem (NLPBVP) by using the Galekin finite element method (GFEM) in space and Crank Nicolson (CN) scheme in time, the problem then reduce to solve a Galerkin nonlinear algebraic system(GNLAS). The predictor and the corrector technique (PCT) is applied here to solve the GNLAS, by transforms it to a Galerkin linear algebraic system (GLAS). This GLAS is solved once using the Cholesky method (CHM) as it appear in the matlab package and once again using the Cholesky reduction order technique (CHROT) which we employ it here to save a massive time. The results, for CHROT are given by tables and figures and show

... Show More
View Publication Preview PDF
Crossref (1)
Crossref
Publication Date
Sun Oct 01 2017
Journal Name
Al–bahith Al–a'alami
Social Media Networks and Freedom of Expression of Individual Rights and Social Diversity: Facebook is a Sample
...Show More Authors

We are, today, facing a torrent of information, ideas, images and videos due to advances of communication technology and electronic publishing. In addition to the proliferation of social networking sites that allow individuals to use them and participate in their channels without any restrictions limiting their freedom in publishing. Due to these sites many terms have emerged like alternative media which use internet and its various techniques to serve its objectives notably the freedom of expression without restrictions. This research studies the phenomenon of interactive media i.e. alternative media through Facebook along with the freedom that makes it spreading in the society and the relation of individual freedom with social diversit

... Show More
View Publication Preview PDF
Crossref (1)
Crossref
Publication Date
Thu Dec 08 2022
Journal Name
International Journal Of Interactive Mobile Technologies (ijim)
Implementation of RWP and Gauss Markov Mobility Model for Multi-UAV Networks in Search and Rescue Environment
...Show More Authors

Future generations of wireless networks are expected to heavily rely on unmanned aerial vehicles (UAVs). UAV networks have extraordinary features like high mobility, frequent topology change, tolerance to link failure, and extending the coverage area by adding external UAVs. UAV network provides several advantages for civilian, commercial, search and rescue applications. A realistic mobility model must be used to assess the dependability and effectiveness of UAV protocols and algorithms.  In this research paper, the performance of the Gauss Markov (GM) and Random Waypoint (RWP) mobility models in multi-UAV networks for a search and rescue scenario is analyzed and evaluated. Additionally, the two mobility models GM and RWP are descr

... Show More
View Publication
Crossref (14)
Crossref
Publication Date
Fri Dec 01 2017
Journal Name
International Journal Of Electrical And Computer Engineering (ijece)
Performance Evaluation of UDP, DCCP, SCTP and TFRC for Different Traffic Flow in Wired Networks
...Show More Authors

<p>The demand for internet applications has increased rapidly.  Providing quality of service (QoS) requirements for varied internet application is a challenging task. One important factor that is significantly affected on the QoS service is the transport layer. The transport layer provides end-to-end data transmission across a network. Currently, the most common transport protocols used by internet application are TCP (Transmission Control Protocol) and UDP (User Datagram Protocol). Also, there are recent transport protocols such as DCCP (data congestion control protocol), SCTP (stream congestion transmission protocol), and TFRC (TCP-friendly rate control), which are in the standardization process of Internet Engineering Task

... Show More
View Publication Preview PDF
Crossref (2)
Crossref
Publication Date
Thu Jan 30 2020
Journal Name
Telecommunication Systems
Nature-inspired optimization algorithms for community detection in complex networks: a review and future trends
...Show More Authors

View Publication
Scopus (28)
Crossref (23)
Scopus Clarivate Crossref
Publication Date
Thu Nov 21 2019
Journal Name
Journal Of Engineering
Simple 2D chaotic remapping scheme for securing optical communication networks
...Show More Authors

In this work, a simple and new method is proposed to simultaneously improve the physical layer security and the transmission performance of the optical orthogonal frequency division multiplexing system, by combining orthogonal frequency division multiplexing technique with chaotic theory principles. In the system, a 2-D chaotic map is employed. The introduced system replaces complex operations such as matrix multiplication with simple operations such as multiplexing and inverting. The system performance in terms of bit error rate (BER) and peak to average ratio (PAPR) is enhanced. The system is simulated using Optisystem15 with a MATLAB2016 and for different constellations. The simulation results showed that the  BE

... Show More
View Publication Preview PDF
Crossref (2)
Crossref
Publication Date
Sun Dec 01 2019
Journal Name
Al-nahrain Journal Of Science
Enhancing Sparse Adjacency Matrix for Community Detection in Large Networks
...Show More Authors

View Publication
Crossref (1)
Crossref