Yazar "Mahmood, M.T." seçeneğine göre listele
Listeleniyor 1 - 5 / 5
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Detection of vehicle with Infrared images in Road Traffic using YOLO computational mechanism(IOP Publishing Ltd, 2020) Mahmood, M.T.; Ahmed, S.R.A.; Ahmed, M.R.A.Vehicle counting is an important process in the estimation of road traffic density to evaluate the traffic conditions in intelligent transportation systems. With increased use of cameras in urban centers and transportation systems, surveillance videos have become central sources of data. Vehicle detection is one of the essential uses of object detection in intelligent transport systems. Object detection aims at extracting certain vehicle-related information from videos and pictures containing vehicles. This form of information collection in intelligent systems is faced with low detection accuracy, inaccuracy in vehicle type detection, slow processing speeds. In this research, we propose a vehicle detection system from infrared images using YOLO (You Look Only Once) computational mechanism. The YOLO mechanism can apply different machine or deep learning algorithms for accurate vehicle type detection. In this study we propose an infrared based technique to combine with YOLO for vehicle detection in traffic. This method will be compared with a machine learning technique of K-means++ clustering algorithm, a deep learning mechanism of multitarget detection and infrared imagery using convolutional neutral network © Published under licence by IOP Publishing Ltd.Öğe Scheduling Data Allocation in Packet Based Wireless Communication System Using Data Mining(Institute of Electrical and Electronics Engineers Inc., 2020) Al-Shukrawi, A.A.; Mahmood, M.T.; Ibrahim, A.A.The purpose of this thesis is scheduling data allocation in large scale networks and in packet based wireless communication system, specifically in the Evolved Packet Core network (EPC) and its various systems and sub-components in order to identify possible areas within the network where machine learning algorithms can be integrated in order to automate some of its tasks. The thesis involves the study of existing literature in order to identify viable machine learning methods that have been successfully integrated into telecommunication networks, and then evaluate whether they are applicable to be utilized within the EPC network. The thesis also involves the introduction of new features and improvements to the network which are also achieved through machine learning. The intention is to explore both supervised and unsupervised learning, depending on the type of data used and tasks that are performed by the network's various components. This is done through extensive research of the network's main and support nodes, followed by detailed proposals of implementation of new and existing tasks within the node using machine learning. This thesis aims to find out the data allocation (DA) in packet based wireless communication system using data mining strategies which achieves load balancing and better communication in wireless communication networks from the proportional fairness perspective. We will look for the DA scheduling strategy that benefits wireless communication networks the most. Wireless communication networks have an emerging wireless communication architecture where access nodes of different types are deployed throughout the geographical area to off-load traffic from macro cells to different data allocation for quick communication and this thesis will provide three major contributions to the advance research of communication. For the training, testing and validation of KDD (Knowledge Discovery and Data Mining) Cup 2019 dataset a well-known MATLAB software was used for this purpose. We used Clustering based Algorithm in Data Mining. © 2020 IEEE.Öğe Securing 5G Network using low power wireless personal area network(Institute of Electrical and Electronics Engineers Inc., 2020) Al-Sarray, Z.A.; Mahmood, M.T.; Ibrahim, A.A.The purpose of this work was to get acquainted with wireless communication technologies and the information security challenges they create from the viewpoint of 5G and its preceding technologies. 5th Generation (5G) is becoming a global phenomenon and it is currently being implemented in dozens of countries around the globe with it comes new information security challenges. Potential solutions for the challenges are also offered. The outcome of this research is an overview of information security challenges in 5G using Low-power wireless personal area Network (LPWAN) and in the technologies preceding 5G. Possible information security solutions are presented in this work for the new technologies coming with 5G. This work showed that the new technologies coming with 5G, such as the virtualization of hardware and services as well as the utilization of cloud computing, create completely new areas of attack for networks. With this knowledge, Labelled and Freely Available Dataset from Open-Source Repository will be used and it is possible to prevent attacks targeting networks by implementing necessary information security elements. For the training, testing and validation of our dataset which is an IoT and cyber-security based dataset, a well-known MATLAB R2019a software was used for this purpose. The proposed reinforcement learning algorithm for Securing 5G network is designed for mesh topology from the ground up by the model of the network itself using low power personal area networks. We model the network operating in a finite area with a finite number of nodes distributed inside the area randomly in this algorithm. Hence, we defined the service area of the target network by assuming the finiteness of the network in the model. © 2020 IEEE.Öğe Using Machine Learning to Secure IOT Systems(Institute of Electrical and Electronics Engineers Inc., 2020) Mahmood, M.T.; Ahmed, S.R.A.; Ahmed, M.R.A.In this paper we will first find out the issues that are arises when we implement IOT systems and later we will fix these issues using Machine Learning techniques. we will implement an RFID (radio frequency identification) system which is seen as the prerequisite for the IOT and the research will also show a number of different technologies available when implementing such a system, showing their differences and why certain ones can be chosen over others for certain functional or security requirements. As stated the prototype IoT system will serves as a running example. The system implemented serves as a way for passengers at an airport to track their baggage after checking it in. The findings of implementing this system, combined with a literature study led us to find five main differences between IoT and traditional systems. Briefly summarized these differences are the following:1. Technical limitations of IoT devices.2. Physical environment plays a larger role in IoT systems. Many components of an IoT system will not be in a controlled environment.3. Lack of security-focus during design and implementation process.4. IoT devices are an interesting target for attackers as tools for DDoS attacks.5. The use cases of IoT systems are more often privacy sensitive. For the training, testing and validation of KDD (Knowledge Discovery and Data Mining) Cup 1999 dataset which is an IoT and cybersecurity based dataset, a well-known MATLAB R2019a software was used for this purpose. Furthermore, this works shows that the accuracy of machine learning models can mitigated to some degree with artificial neural network technique and achieving the accuracy of up to 97.2% with execution time of 2.11s only. © 2020 IEEE.Öğe Web application based on MVC laravel architecture for online shops(Association for Computing Machinery, 2020) Mahmood, M.T.; Ashour, O.I.A.Working with traditional methods to develop a web application has great limitations, is very time-consuming and can lead to a number of unexpected errors. Therefore, a new technology, namely MVC pattern frameworks, was found by some companies to deal with such issues. In this paper, we present a design and implementation for a web-based application for e-commercial shops and third-parties to buy products from online shops using the Laravel framework. As result of our research, we were able to determine that the development was standardized and non-business logic relationships were automatically processed. Moreover, there was much scalability, which provided us with more efficiency through the implementations. © 2020 ACM.
