Preferred Language
Articles
/
jcoeduw-1361
Image classification with Deep Convolutional Neural Network Using Tensorflow and Transfer of Learning
...Show More Authors

The deep learning algorithm has recently achieved a lot of success, especially in the field of computer vision. This research aims to describe the classification method applied to the dataset of multiple types of images (Synthetic Aperture Radar (SAR) images and non-SAR images). In such a classification, transfer learning was used followed by fine-tuning methods. Besides, pre-trained architectures were used on the known image database ImageNet. The model VGG16 was indeed used as a feature extractor and a new classifier was trained based on extracted features.The input data mainly focused on the dataset consist of five classes including the SAR images class (houses) and the non-SAR images classes (Cats, Dogs, Horses, and Humans). The Convolutional Neural Network (CNN) has been chosen as a better option for the training process because it produces a high accuracy. The final accuracy has reached 91.18% in five different classes. The results are discussed in terms of the probability of accuracy for each class in the image classification in percentage. Cats class got 99.6 %, while houses class got 100 %.Other types of classes were with an average score of 90 % and above.

Crossref
View Publication Preview PDF
Quick Preview PDF
Publication Date
Sat Dec 01 2012
Journal Name
Journal Of Economics And Administrative Sciences
Finding the best estimation of generalized for failure rates by using Simulation
...Show More Authors

The statistical distributions study aimed to obtain on best descriptions  of variable sets phenomena, which each of them got one behavior of that distributions .  The estimation operations study for that distributions considered of important things which could n't canceled in variable behavior study, as result  this research came as trial for reaching to best method for information distribution estimation which is generalized linear failure rate distribution, throughout studying the theoretical sides by depending on statistical posteriori methods  like greatest ability, minimum squares method and Mixing method (suggested method).        

The research

... Show More
View Publication Preview PDF
Crossref
Publication Date
Fri Sep 30 2011
Journal Name
Al-khwarizmi Engineering Journal
Fuzzy Control of the Robotic Hands Catching Force Using Muscle Wires Actuator
...Show More Authors

The aim of this research is controlling the amount of the robotic hand catching force using the artificial muscle wire as an actuator to achieve the desired response of the robotic hand in order to catch different things without destroying or dropping them; where the process is to be similar to that of human hand catching way. The proper selection of the amount of the catching force is achieved through out simulation using the fuzzy control technique. The mechanism of the arrangement of the muscle wires is proposed to achieve good force selections. The results indicate the feasibility of using this proposed technique which mimics human reasoning where as the weight of the caught peace increases, the force increases also with approximatel

... Show More
View Publication Preview PDF
Publication Date
Mon Oct 22 2018
Journal Name
Journal Of Economics And Administrative Sciences
Using simulation to compare between parametric and nonparametric transfer function model
...Show More Authors

In this paper, The transfer function model in the time series was estimated using different methods, including parametric Represented by the method of the Conditional Likelihood Function, as well as the use of abilities nonparametric are in two methods  local linear regression and cubic smoothing spline method, This research aims to compare those capabilities with the nonlinear transfer function model by using the style of simulation and the study of two models as output variable and one model as input variable in addition t

... Show More
View Publication Preview PDF
Crossref
Publication Date
Sat Sep 23 2017
Journal Name
Ibn Al-haitham Journal For Pure And Applied Sciences
Image Steganalysis Using Image Quality Metrics (Structural Contents Metric)
...Show More Authors

A new method presented in this work to detect the existence of hidden

data as a secret message in images. This method must be applyied only on images which have the same visible properties (similar in perspective) where the human eyes cannot detect the difference between them.

This method is based on Image Quality Metrics (Structural Contents

Metric), which means the comparison between the original images and stego images, and determines the size ofthe hidden data. We applied the method to four different images, we detect by this method the hidden data and  find exactly the same size of the hidden data.

View Publication Preview PDF
Publication Date
Wed Mar 10 2021
Journal Name
Baghdad Science Journal
Image data compression by using multiwavelete for color image
...Show More Authors

There are many images you need to large Khoznah space With the continued evolution of storage technology for computers, there is a need nailed required to reduce Alkhoznip space for pictures and image compression in a good way, the conversion method Alamueja

View Publication Preview PDF
Publication Date
Tue Dec 27 2022
Journal Name
2022 3rd Information Technology To Enhance E-learning And Other Application (it-ela)
Diabetes Prediction Using Machine Learning
...Show More Authors

Diabetes is one of the increasing chronic diseases, affecting millions of people around the earth. Diabetes diagnosis, its prediction, proper cure, and management are compulsory. Machine learning-based prediction techniques for diabetes data analysis can help in the early detection and prediction of the disease and its consequences such as hypo/hyperglycemia. In this paper, we explored the diabetes dataset collected from the medical records of one thousand Iraqi patients. We applied three classifiers, the multilayer perceptron, the KNN and the Random Forest. We involved two experiments: the first experiment used all 12 features of the dataset. The Random Forest outperforms others with 98.8% accuracy. The second experiment used only five att

... Show More
View Publication
Scopus (5)
Crossref (1)
Scopus Crossref
Publication Date
Fri Jul 19 2024
Journal Name
An International Journal Of Optimization And Control: Theories & Applications (ijocta)
Design optimal neural network based on new LM training algorithm for solving 3D - PDEs
...Show More Authors

In this article, we design an optimal neural network based on new LM training algorithm. The traditional algorithm of LM required high memory, storage and computational overhead because of it required the updated of Hessian approximations in each iteration. The suggested design implemented to converts the original problem into a minimization problem using feed forward type to solve non-linear 3D - PDEs. Also, optimal design is obtained by computing the parameters of learning with highly precise. Examples are provided to portray the efficiency and applicability of this technique. Comparisons with other designs are also conducted to demonstrate the accuracy of the proposed design.

View Publication Preview PDF
Scopus (1)
Scopus Clarivate Crossref
Publication Date
Wed Jan 01 2014
Journal Name
International Journal Of Computer Applications
Enhancing the Delta Training Rule for a Single Layer Feedforward Heteroassociative Memory Neural Network
...Show More Authors

In this paper, an algorithm is suggested to train a single layer feedforward neural network to function as a heteroassociative memory. This algorithm enhances the ability of the memory to recall the stored patterns when partially described noisy inputs patterns are presented. The algorithm relies on adapting the standard delta rule by introducing new terms, first order term and second order term to it. Results show that the heteroassociative neural network trained with this algorithm perfectly recalls the desired stored pattern when 1.6% and 3.2% special partially described noisy inputs patterns are presented.

Publication Date
Mon May 21 2007
Journal Name
Journal Of Planner And Development
Using the Input - Output Model in building the economic plan using the computer
...Show More Authors

The origin of this technique lies in the analysis of François Kenai (1694-1774), the leader of the School of Naturalists, presented in Tableau Economique. This method was developed by Karl Marx in his analysis of the Departmental Relationships and the nature of these relations in the models of " "He said. The current picture of this type of economic analysis is credited to the Russian economist Vasily Leontif. This analytical model is commonly used in developing economic plans in developing countries (p. 1, p. 86). There are several types of input and output models, such as static model, mobile model, regional models, and so on. However, this research will be confined to the open-ended model, which found areas in practical application.

... Show More
View Publication Preview PDF
Publication Date
Tue Feb 01 2022
Journal Name
Baghdad Science Journal
Numerical Solution for Linear State Space Systems using Haar Wavelets Method
...Show More Authors

In this research, Haar wavelets method has been utilized to approximate a numerical solution for Linear state space systems. The solution technique is used Haar wavelet functions and Haar wavelet operational matrix with the operation to transform the state space system into a system of linear algebraic equations which can be resolved by MATLAB over an interval from 0 to . The exactness of the state variables can be enhanced by increasing the Haar wavelet resolution. The method has been applied for different examples and the simulation results have been illustrated in graphics and compared with the exact solution.

View Publication Preview PDF
Scopus (2)
Scopus Clarivate Crossref