Hazem noori abdulrazzak
@ruc.edu.iq
Computer communication engineering -
Al-Rafidain University College
RESEARCH, TEACHING, or OTHER INTERESTS
Computer Networks and Communications, Artificial Intelligence, Electrical and Electronic Engineering, Engineering
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
Aya Ayad Hussein, Hazem Noori Abdulrazzak, and Ali Salem Ali
Elsevier BV
Rawad Ahmed Ibrahim Almashhadani, Goh Chin Hock, Farah Hani Bt Nordin, and Hazem N. Abdulrazzak
Seventh Sense Research Group Journals
Rawad Almashhadani, Goh Chin Hock, Farah Hani Nordin, Hazem Noori Abdulrazzak, and Zaid Ali Abbas
IEEE
An automatic solar defect detection with a classification system was proposed using deep learning. This paper focuses on solar defects in photovoltaic systems identified through electroluminescence (EL) images. Convolutional Neural Networks (CNNS), Artificial Neural Networks (ANN), Support Vector Machine (SVM), and a pre-trained VGG16 network for feature extraction were compared in this paper. They adopted two classification strategies: binary classification (defective or non-defective) and multi-class classification the class names are 0%, 33%, 67%, and 100% (here % represents the percentage of defectiveness), which represents the defect likelihood. The effectiveness of the model was evaluated using various metrics, including the recall, precision, accuracy, and F1-score for two and four classes and obtained on, supported by confusion matrices. VGG-16 model outperformed other models and achieved an accuracy of 89% for 2-classes and 93% for 4-classes.
Aya Ayad Hussein and Hazem N. Abdulrazzak
IEEE
Cluster-based routing or Hierarchical is a widely recognized approach with particular benefits in terms of scalability and communication efficiency. In Wireless Sensor Networks supported $IoT$, the utilization of clustered routing is a cost-effective method of data collection and transmission, where nodes with the most energy remaining can be utilized to collect and transmit data. This paper proposed a soft Fuzzy C-Means Dynamic Clustering (FCM-DC) Approach. A new Cluster Head (CH) selection technique was presented also. The proposed model was compared with an existing cluster based routing protocol, LEACH protocol, and LEACH-C protocol. The proposed FCM-DC model reduce the packet delay about 16% in 50 nodes scenario and 86% in 100 nodes scenario compared with LEACH.
Hazem Noori Abdulrazzak, Goh Chin Hock, Nurul Asyikin Mohamed Radzi, and Nadia Mei Lin Tan
Institute of Electrical and Electronics Engineers (IEEE)
Clustering evaluation techniques are important to check the clustering algorithm quality. High cluster similarity help to reduce the distance between a node to node within the cluster, also good separation was more important to avoid overlapping clusters. The network performance will increase and the signal will be high. Many researchers proposed different validation indexes such as Davies–Bouldin, Dunn, and Silhouette indexes. These cluster validation indexes focus on the internal or external cluster similarity, and some of them deal with both cases. The employing of graph-based distance to non-spherical clusters and selection of reference points will not be effective all the time because the average distance between reference points and all nodes will be changed dynamically such as in the VANET application. To solve this problem a dynamic sample node should be selected or the similarity of all nodes should be checked. This paper proposes a new Minimum intra-distance and Maximum inter-distance Index (M2I) to improve these indexes. The proposed index checks the internal similarity and the external distance among all nodes from cluster to cluster to ensure that high separation will occur. M2I checks the similarity from node to node within the cluster and cluster to cluster. The proposed index will be an improvement of all high-rank indexes. The proposed index was applied in different scenarios (VANET and real datasets scenarios) and compared with other indexes. The index result shows that the proposed M2I outperforms the others. The M2I accuracy is 100% in the VANET scenario and 89% in the real datasets scenario.
Hazem Noori Abdulrazzak, Goh Chin Hock, Nurul Asyikin Mohamed Radzi, Nadia M. L. Tan, and Chiew Foong Kwong
MDPI AG
Many researchers have proposed algorithms to improve the network performance of vehicular ad hoc network (VANET) clustering techniques for different applications. The effectiveness of the clustering model is the most important challenge. The K-Means clustering algorithm is an effective algorithm for multi-clusters that can be used in VANETs. The problems with the K-Means algorithm concern the selection of a suitable number of clusters, the creation of a highly reliable cluster, and achieving high similarity within a cluster. To address these problems, a novel method combining a covering rough set and a K-Means clustering algorithm (RK-Means) was proposed in this paper. Firstly, RK-Means creates multi-groups of vehicles using a covering rough set based on effective parameters. Secondly, the K-value-calculating algorithm computes the optimal number of clusters. Finally, the classical K-Means algorithm is applied to create the vehicle clusters for each covering rough set group. The datasets used in this work were imported from Simulation of Urban Mobility (SUMO), representing two highway scenarios, high-density and low-density. Four evaluation indexes, namely, the root mean square error (RMSE), silhouette coefficient (SC), Davies–Bouldin (DB) index, and Dunn index (DI), were used directly to test and evaluate the results of the clustering. The evaluation process was implemented on RK-Means, K-Means++, and OK-Means models. The result of the compression showed that RK-Means had high cluster similarity, greater reliability, and error reductions of 32.5% and 24.2% compared with OK-Means and K-Means++, respectively.
Hazem Noori Abdulrazzak, Nadia M. L. Tan, and Nurul Asyikin Mohd. Radzi
IEEE
The dedicated vehicular ad-hoc network (VANET) is a communication model as vehicles can communicate with other vehicles directly or via fixed nodes called Roadside Units (RSU). It has become necessary to find supporting protocols for RSU to increase their efficiency, and thus increase the efficiency of the network. Since these nodes are distributed on the roads, it is important to find appropriate ways to distribute them to increase data transfer and reduce their energy consumption. In this paper, a zigzag distribution method is proposed and a mathematical model of Right Side–Left Side (RS-LS) is used to reduce the energy consumption of RSU and compare it with the main chain protocol. Two different cases were taken, Case-1-is for low density with 20 vehicles and Case-2-is for high density with 40 vehicles. The proposed method succeeded in saving energy and reduce the consumption in both cases, by 60% and 44%, respectively.