| الإنجليزية | العربية | الرئسية | تسجيل الدخول |

البحوث العلمية

2021

Classification techniques’ performance evaluation for facial expression recognition

2021-02
Indonesian Journal of Electrical Engineering and Computer Science (القضية : 2) (الحجم : 21)
Facial exprestion recognition as a recently developed method in computer vision is founded upon the idea of analazing the facial changes in which are witnessed due to emotional impacts on an individual. This paper provides a performance evaluation of a set of supervised classifiers used for facial expression recognition based on minimum features selected by chi-square. These features are the most iconic and influential ones that have tangible value for result dermination. The highest ranked six features are applied on six classifiers including multi-layer preceptron, support vector machine, decision tree, random forest, radial baised function, and K-Nearest neioughbor to figure out the most accurate one when the minum number of features are utilized. This is done via analyzing and appraising the classifiers’ performance. CK+ is used as the research’s dataset. random forest with the total accuracy ratio of 94.23% is illustrated as the most accurate classifier amongst the rest.
2020

Client/Server Remote Control Administration System: Design and Implementation

2020-11
Int. J. Multidiscip. Res. Publ (القضية : 2) (الحجم : 3)
Networks of computers are everywhere, and it implemented in all sectors, including an IT, industrial, managerial sector, and need to be accessed remotely. Remote administration offers access to a remote device. As more departments of Information Technology centralize and reorganize to keep costs down, many remote sites are left with no IT support on-site. Remote computer administration is increasingly common due to the major cost advantages; many activities can be completed, and not needs to be personally accessed by the administrator. In this paper, the remotecontrol administration system has designed and implemented based on client/server architecture. The main goal of the proposed system allows clients to request help from remote servers over the Network.

A Comparison of Four Classification Algorithms for Facial Expression Recognition

2020-09
Polytechnic Journal (القضية : 1) (الحجم : 10)
Facial expression recognition (FER) has achieved an extreme role in research area since the 1990s. This paper provides a comparison approach for FER based on three feature selection methods which are correlation, gain ration, and information gain for determining the most distinguished features of face images using multi-classification algorithms which are multilayer perceptron, Naïve Bayes, decision tree, and K-nearest neighbor (KNN). These classifiers are used for the mission of expression recognition and for comparing their proportional performance. The main aim of the provided approach is to determine the most effective classifier based on minimum acceptable number of features by analyzing and comparing their performance. The provided approach has been applied on CK+ dataset. The experimental results show that KNN is proven to be better classifier with 91% accuracy using only 30 features.tree, and K-nearest neighbor (KNN). These classifiers are used for the mission of expression recognition and for comparing their proportional performance. The main aim of the provided approach is to determine the most effective classifier based on minimum acceptable number of features by analyzing and comparing their performance. The provided approach has been applied on CK+ dataset. The experimental results show that KNN is proven to be better classifier with 91% accuracy using only 30 features.

Cloud computing resources impacts on heavy-load parallel processing approaches

2020-06
IOSR Journal of Computer Engineering (IOSR-JCE) (القضية : 3) (الحجم : 22)
One of the most important subject which many researchers depending on it by applying many algorithms and methods is Cloud Computing. Some of these methods were used to enhance performance, speed, and advantage of task level parallelism and some of these methods used to deal with big data and scheduling. Many others decrease the computation’s quantity in the process of implementation; specially decrease the space of the memory. Parallel data processing is one of the common applications of infrastructure, which is classified as a service in cloud computing. The purpose of this paper is to review parallel processing in cloud. However, the results and methods are inconsistent; therefore, the scheduling concepts give easy method to use the resources and process the data in parallel and decreasing the overall implementation time of processing algorithms. Overall, this review give us and open new doors for using the suitable technique in parallel data processing filed. As a result our work show according to many factors which strategies is better.

Facial Expression Recognition based on Hybrid Feature Extraction Techniques with Different Classifiers

2020-05
TEST Engineering & Management (الحجم : 83)
Facial Expression Recognition (FER) became an important and interest challenging area in the field of computer vision. Due to its major application possibilities, FER is an active topic of research papers since the 1990s, also for the same reason, FER has accomplished a high role in the image processing area. Typically, FER is processed in three main stages including face detection, feature extraction or selection, and classification. This study presents an overview of the current work done for the techniques of the FER field and reviews some of the published researches for the last five years till the date. This paper also gives an overview of the customized made FER algorithms and focused on the method of feature extraction of these FER techniques also the databases that are used. The feature extraction techniques played an important role in making these algorithms more efficient.

Facial expression recognition based on hybrid feature extraction techniques with different classifiers

2020-05
TEST Engineering & Management (الحجم : 83)
Facial Expression Recognition (FER) became an important and interest challenging area in the field of computer vision. Due to its major application possibilities, FER is an active topic of research papers since the 1990s, also for the same reason, FER has accomplished a high role in the image processing area. Typically, FER is processed in three main stages including face detection, feature extraction or selection, and classification. This study presents an overview of the current work done for the techniques of the FER field and reviews some of the published researches for the last five years till the date. This paper also gives an overview of the customized made FER algorithms and focused on the method of feature extraction of these FER techniques also the databases that are used. The feature extraction techniques played an important role in making these algorithms more efficient.
2019

Selective Multi Keys to Modify RSA Algorithm

2019-06
JZS (الحجم : 21)
The use of the internet and communication technology noticeably contributes to development in all branches of science. The data that is transferred to communication channel are unsecured. Cryptography including security and integrity is a domain that provides policies for having privacy of the data. Protection of the data transferred through the internet is very important since such data when transferred through an unprotected channel may be attacked by a third party. RSA represents one of the public key cryptography methods that generate the modulus using two primes. These two primes represent the weakness of RSA benefited from and used by attackers. This paper proposes a new modified RSA method using selective multi keys encryption and decryption for the same modulus instead of using two keys, one for encryption and the other for decryption. This new method guarantees and increases the security of RSA.
2017

Design and Implementation of Student and Alumni Web Portal

2017-09
Science Journal of University of Zakho (القضية : 3) (الحجم : 5)
The Information and Communication Technology (ICT) has witnessed great development in the recent years. Therefore, the design of Students and Alumni Web Portal (SAWP) involves the analysis of the internal and external environment of the three universities. For this آ آ purpose, SWOT technique has been used to detect the deep effect of environment factors on the strategic plan to discover the strengths, weaknesses, opportunities and threats facing the design of the proposed system. SAWP was designed using (MySQL, HTML, CSS, Java Script, jQuery, PHP, AJAX) techniques to provide robust portal system addressing two subsystems: student and alumni portal system. Testing of the SAWP was administered through two main stages: the first, to identify the student’ s views and their preferences. The second to measure the usability of the system through using System Usability Scale (SUS) method with subscription of 22 potential آ آ system users. The best results of SUS testing are: the rate of overall satisfaction was high nearly 80%. While the implementation outcomes found very compatibility and reasonable in wide extents between available data and system requirements.

Combination of multi classification algorithms for intrusion detection system

2017-09
Int. J. Sci. Eng. Res. (القضية : 1) (الحجم : 6)
Classification is one of the common tasks that are involved in data mining to build models for the prediction of future data. It performs its task by different classifier algorithms. This paper provides an approach based on information gain to determine the most distinguishing subset features of each attack class and combine multi classification algorithms which includes (Decision Tree J48, k nearest Neighbor and Naïve Bays). These classifiers are used for the task of detecting intrusions and comparing their relative performances. The goal of this work is to analyze the performance and accuracy of classification algorithms in order to identify the most efficient algorithm for each attack class, and then build accurate intrusion detection system. The proposed model has been applied on KDD Cup 99 data set using 60% of them for training and 40% for testing. These experimental results show that multiple classifiers work better than a single classifier. Also, multiple classifiers are more accurate and have abilities of distinguishing among the different attacks and normal connections effectively.
2015

Combination of multi classification algorithms for intrusion detection system

2015-01
Int. J. Sci. Eng. Res. (القضية : 1) (الحجم : 6)
Classification is one of the common tasks that are involved in data mining to build models for the prediction of future data. It performs its task by different classifier algorithms. This paper provides an approach based on information gain to determine the most distinguishing subset features of each attack class and combine multi classification algorithms which includes (Decision Tree J48, k nearest Neighbor and Naïve Bays). These classifiers are used for the task of detecting intrusions and comparing their relative performances. The goal of this work is to analyze the performance and accuracy of classification algorithms in order to identify the most efficient algorithm for each attack class, and then build accurate intrusion detection system. The proposed model has been applied on KDD Cup 99 data set using 60% of them for training and 40% for testing. These experimental results show that multiple classifiers work better than a single classifier. Also, multiple classifiers are more accurate and have abilities of distinguishing among the different attacks and normal connections effectively.

الرجوع