Yoney Kirsal Ever

ILTDS: Intelligent Lung Tumor Detection System on CT Images

Cancer detection and research on early detection solutions play life sustaining role for human health. Computed Tomography images are widely used in radiotherapy planning. Computed Tomography images provide electronic densities of tissues of interest, which are mandatory. For certain target delineation, the good spatial resolution and soft/hard tissues contrast are needed. Also, Computed Tomography techniques are preferred compared to X-Ray and magnetic resonance imaging images. Image processing techniques have started to become popular in use of Computed Tomography images. Artificial neural networks propose a quite different approach to problem solving and known as the sixth generation of computing. In this study, two phases are proposed. For first phase, image pre-processing, image erosion, median filtering, thresholding and feature extraction of image processing techniques are applied on Computed Tomography images in detail. In second phase, an intelligent image processing system using back propagation neural networks is applied to detect lung tumors.

Seamless Key Agreement Framework for Mobile-Sink in IoT Based Cloud-Centric Secured Public Safety Sensor Networks

Recently, the Internet of Things (IoT) has emerged as a significant advancement for Internet and mobile networks with various public safety network applications. An important use of IoT-based solutions is its application in post-disaster management, where the traditional telecommunication systems may be either completely or partially damaged. Since enabling technologies have restricted authentication privileges for mobile users, in this paper, a strategy of mobile-sink is introduced for the extension of user authentication over cloud-based environments. A seamless secure authentication and key agreement (S-SAKA) approach using bilinear pairing and elliptic-curve cryptosystems is presented. It is shown that the proposed S-SAKA approach satisfies the security properties, and as well as being resilient to node-capture attacks, it also resists significant numbers of other well-known potential attacks related with data confidentiality, mutual authentication, session-key agreement, user anonymity, password guessing, and key impersonation. Moreover, the proposed approach can provide a seamless connectivity through authentication over wireless sensor networks to alleviate the computation and communication cost constraints in the system. In addition, using Burrows–Abadi–Needham logic, it is demonstrated that the proposed S-SAKA framework offers proper mutual authentication and session key agreement between the mobile-sink and the base station.

Modelling and performability evaluation for LTE wireless channel using queuing theory

Long Term Evolution (LTE) has been designed to deliver more data than the previous wireless and mobile systems. Failures are expected in many practical systems and they have a significant impact on the systems performance. The wireless and mobile telecommunication systems are prone to failures. The failures and repairs issues can affect the quality of service (QoS) measurements of the systems significantly. The irregularities caused by the wireless channel failures are complicated and do not have a simple product form solution. Hence, it is essential to consider these systems with an exact solution approach. In this paper, mobile wireless channels of LTE based cellular networks are analysed using queue theory. The characteristics of LTE system and the channel unavailabilities are considered in abstract level. An exact Spectral expansion metodu is used to obtain various QoS measurements. The results explicitly show that failures and repairs affect the system performance significantly.

Analytical Modelling and Performability Evaluation of LTE as Dominant Connectivity Technology for Internet of Things

The future network standards, Long Term Evolution (LTE), has been designed to operate at high speeds for wireless and mobile communication. The exact time at which LTE becomes the dominant connectivity technology in the Internet of Things (IoT) is not certain, however it is clear thats where the world of communications is headed and the time is approachingquickly as for both IoT and LTE adaptations are growing rapidly. In many practical systems, failures are expected and they have a significant effect on the systems performance. The wireless and mobile systems are prone to failures and such systems do not have a simple product form solution. This is because of the irregularities caused by the wireless channel failures. The study of such systems is important because system failures and repairs can affect the QoS measurements of the systems significantly. In this paper, mobile wireless channels of LTE based cellular networks are analysed using queueing theory. The characteristics of wireless channel are considered in abstract level as well as channel unavailability. The model is based on previous work in performance modelling and availability modelling of such systems. Markov Reward Model (MRM) method is used to obtain various QoS measures. The results explicitly show that failures and repairs affect the system performance significantly.

Approaches to modelling and analysis of performability evaluation in wireless environments

Most wireless communication and mobile computing systems are expected to be operational 24 hours a day, 7 days a week. However, wireless communication systems encounter failures. Performability modelling and evaluation of wireless and mobile systems have been of interest for recent research work. Especially, because of the complexity of the next generation wireless and mobile systems, modelling and performance evaluation is essential to improve the architecture according to the quality of service (QoS) requirements and performance characteristics. This paper presents a performability evaluation framework for wireless cellular networks in wireless environments using analytical modelling approaches. The availability and mobility issues are also considered in the proposed models. Well-known approximate Markov reward model solution and the exact Spectral expansion solution approaches are considered. Performability measures of proposed models, such as blocking probability and mean queue length are presented.

Evaluation of Simulation Approaches and Need for MDE in Energy Efficiency, Performance and Availability Assessment of IoT

The Internet of Things (IoT) is a novel paradigm where entities become part of the Internet. It has converged technologies in terms of sensing, computing, information processing, networking and controlling intelligent technologies. Among the technologies converged, we can count wireless sensor networks (WSNs), intelligent sensing, remote sensing, low-energy wireless communications and cloud computing. The distributed sensor networks are used as interconnecting devices to transmit measured information, and control instructions. Therefore, energy efficiency and performability of WSNs are critical for IoT applications.

A preliminary framework using bpnn for performability modelling and analyses of a kerberos server

This paper presents a preliminary framework using back propagation neural networks for performability evaluation of Kerberos servers. In the modelling approach, keys under pseudo-secure conditions are dynamically renewed and also, temporary interruption to link/server access is involved. This interruption has implications on mortification of systems performance. Since this effects the network communications cost, an analytical model is created for evaluation. Analytical models results provide understanding on the values of authentication key renewal(restoration) times, times passed between renewals(restorations) and failures(breakdowns) of the server. Additionally, another distinctive way of critical thinking and problem solving is suggested, and an intelligent system using back propagation neural networks is applied to detect performability modelling.

Analytical modelling and performability analysis for cloud computing using queuing system

In recent years, cloud computing becomes a new computing model emerged from the rapid development of the internet. Users can reach their resources with high flexibility using the cloud computing systems all over the world. However, such systems are prone to failures. In order to obtain realistic quality of service (QoS) measurements, failure and recovery behaviours of the system should be considered. Systems failures and repairs are associated with availability context in QoS measurements. In this paper, performance issues are considered with the availability of the system. Markov Reward Model (MRM) method is used to get QoS measurements. The mean queue length (MQL) results are calculated using the MRM. The results explicitly show that failures and repairs affect the system performance significantly.