Ain Shams University, Faculty of Computer and Information Science
International Journal of Intelligent Computing and Information Sciences
1687-109X
15
2
2015
04
01
A NEWLY PROPOSED COMBINED ROUTING ALGORITHM FOR MANET
1
14
10913
10.21608/ijicis.2015.10913
EN
Hanafy
Ali
Computers and Systems
Engineering Depart.,-Faculty of
Engineering, Minia University, El
Minia, Egypt
B
Tawfek
Faculty of Computer Science
Suez Kanal University
Adel
El-Kabbany
Higher Technology Institute for Engineering
in Belbees
Journal Article
2018
08
13
<em>The Connected Dominating Set based routing</em> is<em> a promising approach for enhancing the routing efficiency in wireless Ad hoc networks. Two types of constructing connected dominating strategies exist; the first is the constant performance ratio schemes and the second is non-constant performance ratio schemes. The constant performance ratio schemes outperforms the non-constant performance ratio schemes, because non-constant performance ratio schemes cannot guarantee generating connected dominating set of small size. This paper proposes a</em> <em>Combined Routing Algorithm which is the merger between the two algorithms, Level-Based algorithm and marking algorithm. The new routing algorithm takes advantages from both algorithms. It guarantees constructing the connected dominating set of small size using Level-Based algorithm, easily update and maintain it using marking algorithm which is used to update the new network after the random movement. Simulation results have proved that the new proposed combined routing algorithm has average better performance than both algorithms (Level- Based algorithm and Marking algorithm) in all transmission ranges.</em>
Ain Shams University, Faculty of Computer and Information Science
International Journal of Intelligent Computing and Information Sciences
1687-109X
15
2
2015
04
01
ENHANCED MIN-MIN TASK SCHEDULING ALGORITHM BASED ON LOAD BALANCING IN GRID COMPUTING
15
30
10914
10.21608/ijicis.2015.10914
EN
J
Daood
Departmant. of computer science, Faculty of Computers and Information, Mansoura University, Egypt
S
Abuelenin
Faculty of Computer and Information,Mansoura University, Egypt
S
Elmougy
Departmant. of computer science, Faculty of Computers and Information, Mansoura University, Egypt
Journal Article
2018
08
13
<strong><em>: </em></strong><em>Grid task scheduling is one of the most important parts in Grid resource management system. In this paper, a new task scheduling algorithm is proposed and implemented based on Min-Min algorithm with taking into consideration load balancing. This proposed algorithm works by executing the small tasks by slower resources while executing the relatively large tasks by faster resources under the decided makespan. Makespan and CPU utilization are the two metrics used to evaluate the performance of the proposed algorithm rather than improvement ratio and usages rate of resource. The proposed algorithm consumes the same running time of original Min-Min algorithm even it uses a new derived Expected Sum Completed Time (ESCT) metric rather than using the standard Expected Completion Time (ECT) and Expected Execution Time(EET). Experimentations results show that the proposed algorithm produces relevant equivalent heavy resources as the guaranteed load balance schedule and makespan is reduced.</em>
Ain Shams University, Faculty of Computer and Information Science
International Journal of Intelligent Computing and Information Sciences
1687-109X
15
2
2015
04
01
ENHANCED INTRUSION DETECTION TECHNIQUE BASED ON MACHINE LEARNING
31
43
15755
10.21608/ijicis.2015.15755
EN
H
Yaseen
Faculty of Computers & Information, Mansoura University - Egypt
S
Abuelenin
Faculty of Computer and Information,Mansoura University, Egypt
M
Rashad
Computer Science Department,Faculty of Computers and Information,
Mansoura University, Egypt
Journal Article
2018
10
03
Intrusion leads to violations of the security policies of a computer system. An intrusion detection system (IDS) is a software application that monitors network or system activities for pernicious activities. Many researchers propose the intrusion detection based on machine learning techniques or neural networks, but some of them didn't introduce high detection or decrease the time. The proposed framework is based on machine learning algorithms. These algorithms, discernibility classifier based k-nearest, J48 decision tree and Naïve Bayes rule, are used to discover any intrusion based on anomaly detection. The primary aim of this paper is to enhance the strength of the overall classification decision in better results than any other existent techniques. The performance metrics in our experimental are accuracy, error rate, sensitivity, specificity, and Precision. We notice during experimental results by using NSL-KDD data set, there are improvements in almost results by using the proposed framework.
Ain Shams University, Faculty of Computer and Information Science
International Journal of Intelligent Computing and Information Sciences
1687-109X
15
2
2015
04
01
USING ROUGH SET AND BOOSTING ENSEMBLE TECHNIQUES TO ENHANCE CLASSIFICATION PERFORMANCE OF HEPATITIS C VIRUS
45
59
15756
10.21608/ijicis.2015.15756
EN
M
Helal
Information Systems Deprtmant.,
Faculty of Computers and Information,
Mansoura University, Egypt
M
Elmogy
Information TechnologyDepartment,Faculty of Computers and Information,
Mansoura University - Egypt.
R
Al-Awady
Electronics and Communications Deprtmant., Faculty of Engineering, Mansoura University, Egypt
Journal Article
2018
10
03
Machine learning techniques have been extensively applied to help medical experts in making a diagnosis of many diseases. Classification is a machine learning technique that is used to forecast the relationship between data samples and classes. It is an essential task in different applications, such as image classification and medical diagnosis. There are different classification techniques, such as SVM, C5.0, Neural Network, K-Nearest Neighbor, and Naive Bayes Classifier. Feature selection for classification of cancer data means discovering feature values of malignant tumors and benign ones. It also means using this knowledge to forecast the state of new cases. In this paper, we use Rough sets as a feature selection technique to create a subset feature from the original features. Therefore, we use the resulting subset with different classification and ensemble techniques to discover classes of unknown data using HCV data set. SVM, C5.0, and Ensemble classifiers are used as classification techniques to discover classes of unknown data. In this paper, the percentage of accuracy, sensitivity, and specificity are used as evaluation parameters for the tested classification techniques. Experimental results show that the proposed hybrid RS-Boosting/SVM technique has higher accuracy, sensitivity and specificity rates with selected subset features than other tested techniques.
Ain Shams University, Faculty of Computer and Information Science
International Journal of Intelligent Computing and Information Sciences
1687-109X
15
2
2015
04
01
PERFORMANCE ANALYSIS OF MOBILITY MANAGEMENT SCHEMES FOR VEHICULAR NETWORKS
61
82
15757
10.21608/ijicis.2015.15757
EN
N
Mohammed
Electrical Engineering DepartmentPort-Said
University-EGYPT
H
Mowafi
Electrical Engineering DepartmentPort-Said
University-EGYPT
S
Abdel Mageid
Computer and System Engineering Department Al-Azhar University-EGYPT
M
Marai
Computer and System Engineering Department Al-Azhar University-EGYPT
Journal Article
2018
10
03
<em>IETF has projected Mobile IPv6-based Network Mobility (NEMO) basic support protocol (BSP) to support network mobility. NEMO BSP inherits all the drawbacks of Mobile IPv6, such as inefficient routing path, single point of failure, high handover latency and packet loss, and high packet overhead.. This inefficiency dictates a scheme to enhance QoS within NEMO environment and combining cross-layer mobility management and resource allocation design to reduce latency and packet loss during handovers. This scheme called Hi-NEMO, which is designed for all-IP networks. When a vehicle travels in the network mobility service domain, the hierarchical design and the cross-layer designed protocols offer fast QoS provisioning for the mobile network in the vehicle. The function of the MR is simplified, and an MNN can use its applications and even security mechanism without modification in the mobile network. Implementing analytical models to analyze and compare the performance of HI-NEMO and NEMO BSP shows that HI-NEMO enhances the performance of network mobility compared to NEMO BSP such as handover delay, End to End transmission, packet loss and throughput.. The vehicle mobility has a direct impact on the performance valuation of various network mobility protocols because of that we compare the performance of the two protocol in two mobility models ,randomly straight model and realistic city model called City Section Mobility model(CSM).</em>
Ain Shams University, Faculty of Computer and Information Science
International Journal of Intelligent Computing and Information Sciences
1687-109X
15
2
2015
04
01
BLADDER CANCER RECOGNITION: NEW TREND
83
96
15758
10.21608/ijicis.2015.15758
EN
S
AlKashef
Computer Engineering and Systems Department , Faculty of Engineering,
Mansoura University - Egypt
A
Ibrahim
Computer Engineering and Systems Department , Faculty of Engineering,
Mansoura University - Egypt
H
Arafat
Computer Engineering and Systems Department , Faculty of Engineering,
Mansoura University - Egypt
T
El-Diasty
Urology & Nephrology Center, Mansoura University - Egypt
Journal Article
2018
10
03
Magnetic Resonance Imaging (MRI) has been widely applied to various medical procedures. The daily growth of medical data leads to human mistakes in manual analysis; and increases the need for automatic analysis. Therefore, applying tools to collect, classify, and analyse medical data automatically is essential. Medical imaging issues are extremely complex, due to the high importance of correct diagnosis and treatment of diseases in healthcare systems. For these reasons, automatic medical image analysis algorithms are used to help increase the reliability and accurate understanding of medical images. The objective of this paper is to investigate the use of Artificial Neural Network (ANN) algorithms, such as multilayer perceptron (MLP), Jordan/Eleman network, Self-Organizing Feature Map (SOFM) and Support Vector Machine (SVM), to early detect bladder cancer (diagnosis), to determine tumour staging (for the sake of prognosis), and to assess the accuracy of MRI in T staging bladder cancer. A set of functional images, taken by Magnetic Resonance (MR), was used. It was found that multilayer perceptron (MLP) neural network gave better results than all other algorithms. We developed a model that defines cancer level in order to enhance its treatment. Experimental results show that the devised approach increases the accuracy of bladder cancer diagnosis to 81.8% using Generalized Feed Forward (GFF) after processing for more than 40 hours.