Yazar "Calhan, Ali" seçeneğine göre listele
Listeleniyor 1 - 15 / 15
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Channel aware wireless body area network with cognitive radio technology in disaster cases(Wiley, 2020) Cicioglu, Murtaza; Calhan, AliToday, developments in wireless technologies and the increase in disaster cases reveal the necessity of various wireless technologies cooperation. Several technologies are able to cooperate with each other for eHealth, IoT, and so forth applications in disaster cases with the pros and cons of today's communications. Wireless Body Area Networks (WBAN) and cognitive radio (CR) are promising technologies that can be used together to troubleshoot communication problems and make rescue operations successful in disaster situations. WBAN is a radio frequency-based wireless network technology that aims to monitor the functions and conditions of the human body through the sensor nodes that form a network. CR proposes solutions to current problems of wireless communications such as spectrum scarcity and inefficient use of the spectrum. In this study, CR-based WBAN architecture is proposed in disaster cases, and so the emergency, time-critical, and vital signs of WBAN users (endangered people and rescue team members) are able to reach the health unit or disaster management unit in an opportunistic way. CR technology is integrated with a WBAN architecture utilizing the CSMA/C-based IEEE 802.15.6 standard, and performance analysis is executed with the Riverbed Modeler simulation software. Furthermore, using the channel bonding technique, the throughput, the delay, the packet delivery ratios, and energy consumption ratios of the proposed architecture are investigated. According to the results, it was found that CR-based WBAN architecture was 25% more successful in energy efficiency and 5% more successful in packet delivery ratio with channel bonding technique than the traditional WBAN.Öğe CNN-based automatic modulation recognition for index modulation systems(Pergamon-Elsevier Science Ltd, 2024) Leblebici, Merih; Calhan, Ali; Cicioglu, MurtazaAutomatic modulation recognition (AMR) has garnered significant attention in both civilian and military domains, with applications ranging from spectrum sensing and cognitive radio (CR) to the deterrence of adversary communication. Index modulation (IM) represents an innovative digital modulation technique that exploits the indices of parameters of communication systems to transmit extra information bits. This paper aims to examine the performance of a convolutional neural network (CNN)-based AMR across various IM systems, including spatial modulation (SM), quadrature spatial modulation (QSM), and generalized spatial modulation (GSM) with eight digital modulation schemes. In this study, we leverage confusion matrices, receiver operating characteristic (ROC) curves, and F1 scores to illustrate the recognition model's outputs.Öğe Deep learning-based modulation recognition with constellation diagram: A case study(Elsevier, 2024) Leblebici, Merih; Calhan, Ali; Cicioglu, MurtazaAutomatic modulation recognition is a promising solution for identifying and classifying signals received in heterogeneous wireless networks. In dynamic and autonomous environments, receivers must extract the relevant signal from various modulated signals to enable further communication procedures. Machine learning, including its sub-branches for classification problems, offers promising operational capabilities. This study utilized the ResNet-50 deep learning method for modulation classification. A dataset consisting of eight digital modulation techniques was generated, with constellation diagrams created as image data over the additive white Gaussian noise (AWGN) channel at signal-to-noise ratios (SNR) of 5 dB, 10 dB, and 20 dB. The deep learning algorithm's performance metrics were evaluated using a confusion matrix, and F1 scores were compared to those of the AlexNet deep learning algorithm. The simulation results clearly indicate the superior performance of ResNet-50 over AlexNet. In terms of average F1 scores, ResNet-50 exhibits a significant advantage, surpassing AlexNet by approximately 67%, 29%, and 10% at SNR values of 5 dB, 10 dB, and 20 dB, respectively.Öğe Effects of diagram plane on neural network based modulation recognition(Elsevier, 2024) Leblebici, Merih; Calhan, Ali; Cicioglu, MurtazaModulation recognition using deep learning presents challenges in effectively distinguishing high -order modulation schemes while maintaining a balance between complexity and recognition accuracy. In this study, we curate a comprehensive dataset in the r theta plane, encompassing eight distinct modulation schemes. Leveraging hyperparameter optimization and transfer learning, we explore the capabilities of various CNN -based architectures, including MobileNetV2, ResNet50V2, ResNet101V2, InceptionV3, ResNet152V2, Xception, and InceptionResNetV2, for the classification of modulation schemes. The simulation results demonstrate that with signalto-noise ratio (SNR) values exceeding 5 dB, all models exhibit classification accuracies surpassing 50% and approach near -perfect accuracy at an SNR value of 20 dB. However, under low SNR conditions, such as 5 dB, the recognition accuracies of all models, except for ResNet152V2 and InceptionV3, show minimal variation. As the SNR increases by 5 dB from -5 dB to 20 dB, ResNet152V2 and InceptionV3 demonstrate remarkable classification accuracy improvements, exceeding 40%, 30%, 30%, 10%, and 15%, respectively. In contrast, the other models do not exhibit such robust responsiveness in accuracy enhancements. The remarkable performance improvements are achieved by fine-tuning pre -trained models through these processes.Öğe EHealth monitoring testb e d with fuzzy based early warning score system(Elsevier Ireland Ltd, 2021) Calhan, Ali; Cicioglu, Murtaza; Ceylan, ArifBackground and objective: EHealth monitoring systems are able to save the persons' lives and track some vital physiological signs of patients, sportsmen, and soldiers for some purposes. Instant data tracking enables appropriate clinical interventions. The early warning score concept defines that specific vital human body signs that are considered together and gives the persons' health score. The patient's vital signs are periodically recorded with the Early Warning Score (EWS) system and the illness severity score of the patient is decided manually. The aim of the study is to monitor a person's health data continuously and calculate the EWS score thanks to the fuzzy logic. Therefore, the simulation as a testbed is constructed for real-time applications with ISO/IEEE 11073 Health informatics -Medical/health device communication standard. Methods: In our paper, a fuzzy-based early warning score system in the EHealth monitoring testbed is proposed. Real-time data are obtained from Riverbed Modeler simulation software with socket programming and stored in the InfluxDB using Node-Red and monitored on the remote desktop with Grafana. Results: Heart rate, body temperature, systolic blood pressure, respiratory rate, and SPO2 are taken into consideration in the fuzzy-based evaluation system for EWS. The data produced in the Riverbed has been provided in a realistic manner because the real human vital sign values are considered during generating vital signs. Conclusions: Using real-time Riverbed Modeler health data with fuzzy-based EWS, a more realistic testbed platform is constructed in this study. (c) 2021 Elsevier B.V. All rights reserved.Öğe Energy Efficiency Solutions for IEEE 802.15.6 Based Wireless Body Sensor Networks(Springer, 2021) Cicioglu, Murtaza; Calhan, AliIEEE 802.15.6 standard has been designed for wireless body sensor networks (WBSNs) that consist of several sensors and a coordinator node in, on or around the human body. In WBSNs, the body sensors continuously send their data to the coordinator node for remote healthcare applications. Continuously sensing body signals is a requirement for vital signs but continuously sending these signals to a destination over coordinator node is not necessary. Measured signs may be in a normal range for a healthy person, so these measurements may not be transmitted to a destination. In this study, the event-driven approach in an IEEE 802.15.6 based WBSN architecture are examined. If a vital sign exceeds the normal range in the proposed architecture, the corresponding sensor must send the sign to the coordinator node. In addition, a WBSN architecture is designed with the energy harvesting capabilities for purposing energy efficiency in a different way. Comparative performance analysis of three WBSN; traditional WBSN, event-driven WBSN, and energy harvesting aware WBSN is given in this study to show the impacts of energy efficiency methods to WBSNs. The event-driven scheme outperforms traditional WBSN, with a delay of 21% and energy consumption of 67% and the proposed energy harvesting aware scheme provides 5% additional energy to the traditional WBSN. Simulation results show that our proposed methods yield much better performance than the traditional approach.Öğe Energy-efficient and SDN-enabled routing algorithm for wireless body area networks(Elsevier, 2020) Cicioglu, Murtaza; Calhan, AliWireless Body Area Networks (WBANs) are one of the special branches of Wireless Sensor Networks (WSNs) that attract attention in various disciplines such as health, engineering, biology, and computers. Also, WBANs are an important research area that can contribute to human life and health in many ways. The Software-Defined Networking (SDN) approach is a solution that can make simpler, flexible, manageable, and more efficient the heterogeneous and complex network structures, such as WBANs. In the Software-Defined WBAN (SD-WBAN) architecture, it is of great importance to extend the network lifetime due to the limited energy of the sensor nodes and the routing process is one of the most important energy consumption processes of SD-WBANs. For an effective and efficient routing approach, service quality requirement parameters, for example, throughput, energy efficiency, end-to-end delay, and packet transmission rates need to be considered. In this study, a new energy-efficient and SDN-enabled routing algorithm (ESR-W) has been developed with the use of the Fuzzy-based Dijkstra technique. So, the most appropriate route determination is performed with a central and reactive (on-demand) approach among many SD-WBAN users. SNR, battery level and hop count metrics are used for routing decisions. In order to compare ESR-W with existing protocols AODV and SDNRouting, extensive scenarios and simulations have been performed in the Riverbed Modeler simulation software. According to the results, ESR-W has been observed very successful compared to other protocols in terms of throughput, end-to-end delay, packet transmission rate, and energy consumption.Öğe Handover scheme for 5G small cell networks with non-orthogonal multiple access(Elsevier, 2020) Calhan, Ali; Cicioglu, MurtazaThe enormous developments in new generation networks reveal the high bandwidth requirements of mobile users. Therefore, wireless communications technologies move higher frequencies with a small coverage area. The small cell concept exposes these advancements for 5G network framework. The small cell issue is a part of 5G networks with non-orthogonal multiple access, millimeter-wave communications, massive MIMO technology, IoT, spectrum sharing, ultra-dense networks, D2D communications, etc. The small cell with small coverage area and seamless communications needs of the mobile users reveal the dense networks with explosive data traffic. The handover process undertakes an important task for 5G networks according to the dense network, small coverage area, and user mobility specifications. In this study, we aim to investigate classic RSSI based handover scheme and fuzzy logic based handover scheme with NOMA for 5G networks. We take into consideration RSSI, BER, and Outage Probability parameters for fast and seamless handover decisions and utilize NOMA technique for users' multiple access. This is the first study for 5G small cell networks fuzzy logic-based handover scheme with NOMA in the literature.Öğe Hybrid cell handover strategy for O-RAN-based campus networks(Elsevier, 2024) Bilir, Emin; Cicioglu, Murtaza; Calhan, AliIn recent years, the concept of Open Radio Access Network (O -RAN) has become a prominent and ongoing research area in mobile communications, as mobile operators strive to enhance the intelligence, efficiency, and vendor independence of their RAN (Radio Access Network) architectures and components. O -RAN aims to virtualize and improve RAN functions in software and therefore it supports virtualized RANs where disaggregated network components of multiple vendors are connected via open interfaces. O -RAN is a concept based on interoperability and standardization of RAN elements including a unified interconnection standard for white -box hardware and open -source software elements from different vendors. Architecture integrates a modular base station software stack on off -the -shelf hardware which allows baseband and radio unit components from different suppliers to operate seamlessly together. Analyzing and examining the O -RAN architecture in terms of various network scenarios and different network policies is crucial for next -generation networks. This study begins by discussing the O -RAN architecture and its advantages in detail. Subsequently, a campus network has been proposed for the analysis and simulation of the O -RAN architecture, and performance analyses have been performed within the scope of different scenarios and network policies. As a result of these analysis, a new hybrid algorithm for cell handovers in the O -RAN architecture has been developed and compared with traditional cell handover methods based on Reference Signal Received Power (RSRP) and Quality of Service (QoS). The results indicate that the proposed hybrid handover algorithm for O -RAN architecture yields better outcomes.Öğe Internet of Things-Based Firefighters for Disaster Case Management(Ieee-Inst Electrical Electronics Engineers Inc, 2021) Cicioglu, Murtaza; Calhan, AliIn this study, Internet of Things (IoT) based firing zone monitoring and firefighter surveillance system (IoT-FFM) is developed with IEEE 802.15.6 standard and Ad hoc On-Demand Distance Vector (AODV) routing protocol. Fireground coordinates, fire temperature, and gas type in the environment are collected, and also, respiration rate, heart rate, pulse oximeter of the firefighter, and nearest firefighter number are gathered with the proposed IoT-FFM wireless communication system. The gathered data are saved in InfluxDB database with Node-RED programming tool and monitored in real-time with Grafana monitoring system at the remote control center. End-to-end delay, throughput, and energy consumption parameters are considered for performance evaluation of the IoT-FFM. The Nakagami channel model is used for a more realistic wireless environment and compared with the Free Path Loss model. Thanks to the IoT-FFM, the health conditions of firefighters can be kept under control, and information about the fire zone can be mapped, and the fire can be intervened appropriately.Öğe IoT-based GPS assisted surveillance system with inter-WBAN geographic routing for pandemic situations(Academic Press Inc Elsevier Science, 2021) Sen, Seda Savasci; Cicioglu, Murtaza; Calhan, AliBackground: Worldwide pandemic situations drive countries into high healthcare costs and dangerous conditions. Hospital occupancy rates and medical expenses increase dramatically. Real-time remote health monitoring and surveillance systems with IoT assisted eHealth equipment play important roles in such pandemic situations. To prevent the spread of a pandemic is as crucial as treating the infected patients. The COVID-19 pandemic is the ongoing pandemic of coronavirus disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Methods: We propose a surveillance system especially for coronavirus pandemic with IoT applications and an inter-WBAN geographic routing algorithm. In this study, coronavirus symptoms such as respiration rate, body temperature, blood pressure, oxygen saturation, heart rate can be monitored and the social distance with ?maskwearing status? of persons can be displayed with proposed IoT software (Node-RED, InfluxDB, and Grafana). Results: The geographic routing algorithm is compared with AODV in outdoor areas according to delivery ratio, delay for priority node, packet loss ratio and bit error rate. The results obtained showed that the geographic routing algorithm is more successful for the proposed architecture. Conclusion: The results show that the use of WBAN technology, geographic routing algorithm, and IoT applications helps to achieve a realistic and meaningful surveillance system with better statistical data.Öğe IoT-based wireless body area networks for disaster cases(Wiley, 2020) Cicioglu, Murtaza; Calhan, AliWireless networks have many advantages for emergency situations especially disaster cases. A disaster might happen because of various reasons such as earthquakes, hurricanes, floods, and tornadoes. In these emergency situations, wireless communication technologies are very important for the rescue of human life. Wireless technologies, especially body area networks, might monitor, collect, and send data about human in trouble to rescue unit. In this paper, Internet of things-based wireless body area network is proposed for disaster cases. The proposed architecture guarantees lifesavings by using wireless technologies for location determination, vital signs transmission, and SOS calls. Also, a gateway selection algorithm based on fuzzy logic is developed for selecting more appropriate wireless technology.Öğe A new platform for machine-learning-based network traffic classification(Elsevier, 2023) Bozkir, Ramazan; Cicioglu, Murtaza; Calhan, Ali; Togay, CengizThis study provides a new platform for classifying encrypted network traffic based on machine learning (ML) techniques. The architecture of the platform is designed for real-world network traffic classification problems with performance-oriented, practical, and up-to-date software technologies. In addition, this study introduces a new feature extraction method to the literature. The proposed platform applies ML techniques with flowbased statistical features of encrypted network traffic and new feature extraction. It takes network traffic packets as input and passes them through feature extraction, data preparation, and ML stages. In the feature extraction stage, network flows are extracted from the network traffic data by calculating their features with the NFStream tool. During the data preparation stage, the dataset is transformed into a processable state for the ML algorithm with the Apache Spark framework. This stage also includes the feature selection operation. The ML stage runs GBTree, LightGBM, and XGBoost algorithms. Moreover, we use the MLflow framework in the proposed process management to observe the ML lifecycle, including experimentation, reproducibility, and deployment. The experimental results show that the XGBoost algorithm achieves the best result with an F1 score of above 99%.Öğe SDN-enabled Cognitive Radio Network Architecture(Wiley, 2020) Cicioglu, Murtaza; Cicioglu, Seda; Calhan, AliIn this study, a new network architecture based on the software-defined networking (SDN) approach is proposed for cognitive radio networks (CRNs). The proposed network architecture [software-defined cognitive radio (SDCR)] assumes the responsibilities of network resource management for CRNs and provides a dynamic spectrum management mechanism with an SDN controller. In this way, the dependency of network users on base stations is reduced in dynamic cognitive radio environments, and network performance is improved by delegating some of the management responsibilities to the controller. The performance analysis of the SDCR is carried out through the RIVERBED MODELER simulation software. End-to-end delays and packet loss rates for the primary network are investigated by selecting different offered loads for secondary users. In addition, for the equal and different packet sizes, primary network and SDCR throughput are examined and network performance is improved by using channel bonding technique. The results indicate that the SDCR outperforms the traditional CRN architecture, in terms of the throughput, and the proposed architecture can provide effective performance. Bit error rate parameter is investigated in the study and the energy consumption parameter of the SDCR is also compared with the cognitive radio wireless network.Öğe Smart agriculture with internet of things in cornfields(Pergamon-Elsevier Science Ltd, 2021) Cicioglu, Murtaza; Calhan, AliThis paper aims to achieve productive corn harvest in large-scale fields with the help of Internet of Things hardware and software facilities. The system uses heterogeneous sensor nodes which are capable of sensing acoustic, rain, wind, light, temperature and pH levels of the cornfields for smart agriculture applications. The specific properties of the cornfields are gathered with special purpose sensors at coordinator nodes, and then the coordinator node sends the data to the Drone as a relay node. It is sufficient for the sensor nodes to detect conditions at specific times of the day because the data in the cornfields does not change rapidly. The Drone provides data to the base stations for monitoring on farmers' visual devices. Therefore, the necessity of long distance communication between sensors in a region of large-scale cornfields is eliminated.
