Elektrik - Elektronik Mühendisliği Bölümü Koleksiyonu
Bu koleksiyon için kalıcı URI
Güncel Gönderiler
Öğe Diagnosis of Epileptic seizures and Hypoxic-ischemic encephalopathy using Artificial Intelligence based on EEG signal: A review(Institute of Electrical and Electronics Engineers Inc., 2024) Kadhim, Ezzaddin; Al-Jumaili, Saif; Uçan, Osman NuriThe brain is the nucleus for cognition and controls voluntary and involuntary activities inside the human body. Any neurological illness, regardless of its cause, will impair the brain's functionality. Certain neurological illnesses manifest symptoms as seizures. Epilepsy and Hypoxic-ischemic Encephalopathy (HIE) are the most similar disorders in symptoms, but at the neurological level, they are two completely different disorders. This difference is measured at the level of neural activity, as Electroencephalography (EEG) is one of the most distinctive tools used to measure neural activity in the brain. Experts use EEG to diagnose disorders through recorded brain activity, including seizures, but the diagnosis process consumes much time and effort. Adopting Artificial Intelligence (AI) techniques to extract the patterns of brain illnesses is a more efficient process for diagnosing disorders because it depends on computing and, thus, has high accuracy in diagnosing brain illnesses. In this research, we reviewed the most effective stages and methods adopted by researchers to diagnose brain disorders based on EEG and artificial intelligence techniques.Öğe Acoustical imaging of the nearshore seafloor depositions and deformations, a key study for Western Istanbul, Türkiye(Springer Verlag, 2024) Özgan, Sinan; Alp, Hakan; Bayat, Oğuz; Vardar, DenizhanTo protect the sustainability of the benefits from seas and near coastal areas, which have under the effect of the very complex hydrodynamic conditions and intensive human activities, without disrupting the balance of nature, it is necessary to image the status of the seafloor features. Therefore, this study presents the deformations, depositional conditions, underwater constructions, and the other non-natural impacts on the seafloor of the nearshore area at western Istanbul (between Küçükçekmece and Büyükçekmece lagoons) where it intensely used by the citizens. The results of the study may provide some guidance for understanding the impacts and risk factors of uses that are or will be conducted in coastal and/or near-coastal areas. Construction planning for civil coastal structures and areas should be done in great harmony with nature, minimizing negative environmental impacts. Although sediment distribution in the area is generally quite complex, the current state of the region, wave action, hydrodynamic conditions, the amount of material transported from the land, and bathymetry are important influencing factors. The seafloor has been damaged primarily by anchor deformation and associated bottom scanning, as well as disturbing trawl tracks. The seafloor was observed as partially shallowing near the constructions (such as natural gas pipelines, fishermen’s shelter, and port piles) of coastal areas and associated with sand deposits. Therefore, scanning the seafloor using side-scan sonar may provide valuable frequency data to prevent future disruptions.Öğe Enhanced energy efficiency through path planning for off-road missions of unmanned tracked electric vehicle(Multidisciplinary Digital Publishing Institute (MDPI), 2024) İnal, Taha Taner; Cansever, Galip; Yalçın, Barış; Çetin, Gürkan; Hartavi, Ahu EceThe primary objective of this research is to address the existing gap about the use of a path-planning algorithm that will reduce energy consumption in off-road applications of tracked electric vehicles. The study focuses on examining various off-road terrains and their impact on energy consumption to validate the effectiveness of the proposed solution. To achieve this, a tracked electric vehicle energy model that incorporates vehicle dynamics is developed and verified using real vehicle driving data logs. This model serves as the foundation for devising a strategy that can effectively enhance the energy efficiency of off-road tracked electric vehicles in real-world scenarios. The analysis involves a thorough examination of different off-road terrains to identify strategies that can adapt to diverse landscapes. The path planning strategy employed in this study is a modified version of the A*, called the Energy-Efficient Path Planning (EEPP) algorithm, specifically tailored for the dynamic energy consumption model of off-road tracked electric vehicles. The energy consumption of the produced paths is then compared using the validated energy consumption model of the tracked electric vehicle. It is important to note that the identification of an energy-efficient path heavily relies on the characteristics of the vehicle and the dynamic energy consumption model that has been developed. Furthermore, the algorithm takes into account real-world and practical considerations associated with off-road applications during its development and evaluation process. The results of the comprehensive analysis comparing the EEPP algorithm with the A* algorithm demonstrate that our proposed approach achieves energy savings of up to 6.93% and extends the vehicle’s operational range by 7.45%.Öğe Multisource data framework for prehospital emergency triage in real-time IoMT-based telemedicine systems(2024) Jasim, Abdulrahman Ahmed; Ata, Oğuz; Salman, Omar HusseinBackground and objective: The Internet of Medical Things (IoMT) has revolutionized telemedicine by enabling the remote monitoring and management of patient care. Nevertheless, the process of regeneration presents the difficulty of effectively prioritizing the information of emergency patients in light of the extensive amount of data generated by several integrated health care devices. The main goal of this study is to be improving the procedure of prioritizing emergency patients by implementing the Real-time Triage Optimization Framework (RTOF), an innovative method that utilizes diverse data from the Internet of Medical Things (IoMT). Methods: The study's methodology utilized a variety of Internet of Medical Things (IoMT) data, such as sensor data and texts derived from electronic medical records. Tier 1 supplies sensor and textual data, and Tier 3 imports textual data from electronic medical records. We employed our methodologies to handle and examine data from a sample of 100,000 patients afflicted with hypertension and heart disease, employing artificial intelligence algorithms. We utilized five machine-learning algorithms to enhance the accuracy of triage. Results: The RTOF approach has remarkable efficacy in a simulated telemedicine environment, with a triage accuracy rate of 98%. The Random Forest algorithm exhibited superior performance compared to the other approaches under scrutiny. The performance characteristics attained were an accuracy rate of 98%, a precision rate of 99%, a sensitivity rate of 98%, and a specificity rate of 100%. The findings show a significant improvement compared to the present triage methods. Conclusions: The efficiency of RTOF surpasses that of existing triage frameworks, showcasing its significant ability to enhance the quality and efficacy of telemedicine solutions. This work showcases substantial enhancements compared to existing triage approaches, while also providing a scalable approach to tackle hospital congestion and optimize resource allocation in real-time. The results of our study emphasize the capacity of RTOF to mitigate hospital overcrowding, expedite medical intervention, and enable the creation of adaptable telemedicine networks. This study highlights potential avenues for further investigation into the integration of the Internet of Medical Things (IoMT) with machine learning to develop cutting-edge medical technologies.Öğe Detection of Animals and humans in forest fires using Yolov8(2024) Alsamurai, Mustafa Qays Fadhil; Çevik, Mesut- The study uses the YOLOv8 deep learning algorithm to detect fire, smoke, humans, and animals in outdoor images. The importance of forests in protecting the biosphere is emphasized, and forest fires are identified as a major risk to the environment and living beings. The researchers created a custom dataset of outdoor images and manually annotated them. The YOLOv8 model was trained on this dataset, and its overall performance was evaluated, with varying results for different object classes. The study identified areas for improvement in the model's ability to detect small instances of fire and smoke and differentiate between animals and humans. The impact of image quality on the model's performance was also highlighted. Overall, the study provides a comprehensive evaluation of YOLOv8's performance in detecting outdoor objects and identifies areas for improvement.Öğe Examining the potential of deep learning in the early diagnosis of Alzheimer's disease using brain MRI images(2024) Mahmood, Anmar; Çevik, Mesut- Alzheimer's disease is a severe public health problem affecting millions worldwide. Deep Learning (DL) models can aid in detecting the disease using MRI data, and we evaluated three DL models for this purpose. We used detailed MRI images of Alzheimer's patients and healthy controls to train these models. A convolutional neural network (CNN) with two convolutional and two fully connected layers was employed in the initial model, which had a 95% accuracy rate. The second model, which included a leaky ReLU activation function, more fully connected layers, and a bigger kernel size, was an enhanced version of the previous one and had a 96% accuracy rate. The third model was a transfer learning model with two dense layers built on top of the VGG16 architecture, achieving an accuracy of 80%. Our findings imply how neural network models may assist with MRI data-based the disease assessment via evaluations of reliability, precision, recollection, and the F1 ranking. For enhancing the precision and usability of these gadgets for therapeutic usage, more study must be conducted.Öğe Study and analysis of PV system behavior during disturbances(Institute of Electrical and Electronics Engineers Inc., 2023) Mohammed, Ramzi Qasim; Mardikyan, Kevork; Çevik, MesutThe utilization of renewable energy sources has drawn attention because of the population's fast increase and growing worry over global warming. Renewable energy sources greatly improve the environment by lowering carbon emissions and generating cost-effective electricity. Solar energy is the most widely used renewable energy source. PV panels are becoming more affordable, have a bright commercial future, and are good for the environment. Recently, the PV solar system has drawn a lot of attention, especially in comparison to other renewable energy sources. The renewable energy source systems are intended to function normally within a set of operating parameters, but they may experience failures that alter their operational performance and behavior. The performance and behavior of a PV hybrid grid-connected system under disturbances, such as a quick change in load or a rapid change in applied irradiations, temperature and also fault conditions will be studied, analyzed, and discussed in this papers. The MATLAB Simulink application will be used to display the modeling of PV system results. In this papers the P&O MPPT technique-based power management of PV batteries is vulnerable to a number of eventualities, including dust impairing PV efficiency and raising temperature and failures. The results show that, the PV system's output power decreases as the temperature rises, but the output efficiency also suffers from dust buildup. The second goal is the direct proportion between PV current and irradiance. Different cases are proposed in this work to verify the energy management system. The results were within IEEE harmonic standards when the LC filter is used in this work.Öğe Enhancing smart grid efficiency: a modified ANN-LSTM approach for energy storage and distribution optimization(Institute of Electrical and Electronics Engineers Inc., 2023) Mohammed, Ramzi Qasim; Abdulrazzaq, Mohammed Majid; Mohammed, Ayoob Jasim; Mardikyan, Kevork; Çevik, MesutThe smart grid represents a paradigm shift in energy management, aiming to optimize energy storage and distribution while accommodating the growing demand for renewable energy sources. In this paper, we investigate the application of a modified Artificial Neural Network with Long Short-Term Memory (ANN-LSTM) in addressing the multifaceted challenges of the smart grid. Through rigorous experimentation and simulation, the ANN-LSTM is evaluated in four diverse scenarios, including normal operation, fluctuating renewable energy, peak demand, and grid instability. The results showcase the model's exceptional predictive accuracy, low Mean Squared Error (MSE), and rapid response times, outperforming other models, such as Support Vector Machine (SVM), Convolutional Neural Network (CNN), Decision Tree (DT), and Fuzzy Logic. Our findings underscore the ANN-LSTM's potential to revolutionize energy storage and distribution in the smart grid, ushering in a new era of efficiency, sustainability, and resilience in energy management.Öğe Sub-diffraction focusing of light by aperiodic masks(Taylor and Francis Ltd., 2022) Mostafavi, Seyeddyako; Nutku, Ferhat; Ekşioğlu, YasaDiffraction of a spherical wave through various types of 2D aperiodic hollow masks is investigated computationally. Unlike a periodic transmissive grating, an aperiodic hollow mask can focus light into a hotspot with sub-wavelength diameter. In this work, several types of 2D aperiodic hollow masks are investigated in the framework of sub-diffraction focusing of light and generating superoscillations at the hotspot region.Öğe Improving IoT data security and integrity using lightweight blockchain dynamic table(MDPI, 2022) Hameedi, Saleem S.; Bayat, OğuzOver the past few years, the Internet of Things (IoT) is one of the most significant technologies ever used, as everything is connected to the Internet. Integrating IoT technologies with the cloud improves the performance, activity, and innovation of such a system. However, one of the major problems which cannot be ignored in such integration is the security of the data that are transferred between the client (IoT) and the server (cloud). Solving that problem leads to the use the of IoT technologies in more critical applications and fields. This paper proposes a new security framework by combining blockchain technology with the AES algorithm. Blockchain technology is used and modified to protect data integrity and generate unique device identification within minimal power consumption and best performance. The AES algorithm is used to improve the data confidentiality when being transmitted to the server. The outcomes demonstrated that the proposed solution improves the security system of the IoT healthcare data and proved its efficiency and power consumption compared to other methods.Öğe TETRA baz istasyonları arasında frekans planlaması(2022) Yılmaz, Şakir; Aydın, Çağatay; Atilla, Doğu ÇağdaşGünümüzde kısıtlı frekans kaynaklarının tekrarlanarak kullanılması frekans planlama açısından ciddi önem arz etmektedir. Özellikle kritik ses haberleşmesinde daha az baz istasyonu ile daha fazla alan kapsanmak istendiğinde frekans tekrarı sorunu daha çok göze batmaktadır. Bu makalede kritik ses haberleşmesi teknolojilerinden olan Karasal Trunk Telsiz sistemi (Terrestrial Trunk Radio, TETRA) üzerinde bir çalışma yapılmıştır. Baz istasyonları konumları, yayın yaptığı frekans bilgisi, baz istasyonu çıkış gücü, sisteme ait bant genişliği göz önüne alınarak komşu kanal ve ortak kanal girişimleri incelenmiştir. Sayısal telsiz sisteminde mevcut hesapların yetersiz kaldığı ve bu hesaplara ek olarak komşuluk ilişkilerinin de frekans planlamada önemli olduğu tespit edilmiştir. Ayrıca konuşma trafiği yoğunluğu (Erlang) incelenerek sistemde işlevsiz kullanılan frekanslar tespit edilmeye çalışılmıştır.Öğe CSK based on priority call algorithm for detection and securing platoon from inside attacks(2020) Al-Sheikhly, Mohammed; Kurnaz, SeferThe platooning is an emerging concept in VANETS that involves a group of vehicles behaving as a single unit via the coordination of movement. The emergence of autonomous vehicles has bolstered the evolution of platooning as a trend in mobility and transportation. The autonomous vehicles and the elimination of individual and manual capabilities introduces new risks. The safety of the cargos, passenger and the advanced technology had increased the complication of the security concerns in platooning as it may attract malicious actors. In improving the security of the platoon, the threat and their potential impacts on the vehicular systems should be identified to ensure the development of security features that will secure against the identified risks. In this paper, two critical types of security breaches were identified those are Sybil attack and Delay attacks. Those security attacks can be somewhat disruptive and dangerous to the regular operation of the platoon leading to severe injuries, increased fuel consumption and delay the performance of the network. The research in this paper focuses on design, detection and the mitigation of attacks in a vehicle platoon. priority call algorithm in combination with color-shift keying modulation is used to protect the platoon alleviating the undesirable impacts such as collisions, oscillations and disintegration in the platoon caused by the attacks.Öğe Voice to face recognition using spectral ERB-DMLP algorithms(Tech Science Press, 2022) Bala, Fauzi A.; Uçan, Osman Nuri; Bayat, OğuzDesigning an authentication system for securing the power plants are important to allow only specific staffs of the power plant to access the certain blocks so that they can be restricted from using high risk-oriented equipment. This authentication is also vital to prevent any security threats or risks like compromises of business server, release of confidential data etc. Though conventional works attempted to accomplish better authentication, they lacked with respect to accuracy. Hence, the study aims to enhance the recognition rate by introducing a voice recognition system as a personal authentication based on Deep Learning (DL) due to its ability to perform effective learning. The study proposes Equivalent Rectangular Bandwidth and Deep Multi-Layer Perceptron (ERB-DMLP) as it has the ability to perform efficient and relevant feature extraction and faster classification. This algorithm also has the ability to establish effective correlation between voices and images and achieve the semantic relationship between them. Voice preprocessing is initially performed to make it suitable for further processing by removing the noise and enhancing the quality of signal. This process is also vital to minimize the extra computations so that the overall efficacy of the system can be made flexible by considering the audio files as features and the images as labels to identify a person’s voice by classifying the extracted features from the ERB Feature Extraction. This is then passed as the input into DMLP model to classify the persons, and trained the model to make an accurate classification of audio with corresponding image labels, and perform the performance test based on the trained model. Flexibility, relevant feature extraction and faster classification ability of the proposed work has made it explore better outcomes that is confirmed through results.Öğe Efficient DC biased-PAM based OFDM for visible light communication system(Springer, 2022) Zaidan, Zahraa Mustafa; Bayat, Oğuz; Abdulkafi, Ayad AtiyahThe need of high spectral efficiency to increase bandwidth utilization have been the main drivers for next generation optical wireless communication including visible light communication (VLC) systems. However, conventional optical techniques adopted Hermitian symmetry to satisfy the real and positive constraints of intensity modulation with direct detection based VLC systems on the cost of spectral efficiency loss. In this paper, a new direct current biased- pulse amplitude modulated based orthogonal frequency division multiplexing (DC-PAM-OFDM) is proposed to utilize all subcarriers without using Hermitian symmetry and hence provide more spectral efficiency for VLC systems. The proposed scheme ensures the real-valued optical signals by inserting PAM signal in frequency domain side of OFDM system, clipping, splitting, and rearranging the time domain signal instead of using Hermitian symmetry. This results in improving spectral efficiency by 100% compared to PAM based discrete multitoned modulation (DMT). In addition, theoretical analyses show that the proposed DC-PAM based OFDM scheme is more energy efficient than the PAM-DMT. Furthermore, simulation results show that the proposed scheme has better bit error rate performance and reduces the Peak-to-Average Power Ratio when compared with the existing methods under same spectral efficiency conditions.Öğe Lightweight offline authentication scheme for secure remote working environment(IEEE, 2021) Coruh, Ugur; Khan, MansoorDuring pandemic situations, remote work security and reliability become more important for sustainability. The main problem in remote working is providing a reliable internet connection between remote working employees and remote systems. Lack of internet connection issues cause remote working problems, and some companies allow employees to work on untrusted personal computers, which causes untrusted and unmanageable IT systems. According to these problems, this study proposed a lightweight, offline authentication scheme for the secure remote work environment. The proposed model is designed for LPS (Lightweight Portable Security) devices, and these LPS devices provide portable USB bootable images with a secure environment for this connection and trust problems. LPS devices are single USB dongles to make users more dependent on these LPS devices. This design provides mobile application-dependent authentication to provide strong user authentication with 2FA (2 Factor Authentication), which is something you have (mobile phone and USB dongle) and something you know (mobile PIN). Also, the proposed model provides geofencing between USB dongles and Mobile phones to offer robust security.Öğe Hovering drones-based FSO technology in weak atmospheric turbulence with pointing error(IEEE, 2021) Mahdi, Abdullah Jameel; Mazher, Jalil; Uçan, Osman NuriThe rapid development of drones that are a type of Unmanned Arial Vehicles (UAV) in different fields encourages researchers and institutes concern with wireless communication to use this technology. As wireless optical communication (OWC) has been applied and has many advantages over Radio Frequency (RF), this enables using the optical beam in UAV-based Free-space optical (FSO) technology as an alternative to RF technology. In this paper, the proposed system configuration has two subsystems: Single Input-Single Output (SISO) and Multiple Input-Single Output (MISO). The system was simulated using MATLAB software 2020. The optical signal was modulated using Pulse Position Modulation (PPM) and transmitted in a weak turbulence regime. The Average Bit error Rate (ABER) was measured depending on the pointing error HP factor. The idea was to find the specific values of the pointing error angle θr and link distance Z that are the related parameters of HP. The results have clarified that for each pointing error angle θr value, there was a specific path length Z, which can keep the system at high performance, for example, θr= rad, the applicable link distance Z=1000 m, and the ABER≈ .Öğe Ultra-wide-band microstrip patch antenna design for breast cancer detection(Electrica, 2022)In this paper, a novel design for an ultra-wide-band (UWB) microstrip antenna with enhanced bandwidth for early detection of breast cancer has been proposed. It has been designed using CST software, which is a 3D analysis software package for electromagnetic components and systems design, analysis, and optimization. FR-4 has been used as a substrate, with dimensions of 60 × 70 mm, having a circular patch with a defected ground structure to reach the desired outcomes. The antenna has a peak gain of 4.431 dBi and works between 1.6 GHz and 10 GHz, which gives a bandwidth of 8.4 GHz with an average of -15 dB. The result of the simulation is presented in terms of radiation pattern, bandwidth, and return loss, and the validation of the proposed work is presented by the gain and the efficiency. A breast phantom model has been designed containing a tumor placed in a specific location, This, when combined with the kinetics of contrast medium propagation in various tissues, may effectively simulate normal breast tissue. The cancerous tumor is detected using specific absorption rate (SAR) analysis. The SAR is the rate of energy absorption in a tissue and is measured in W/kg. The SAR results are a maximum at the coordinates (1.085, 9.47273, 32.25), close to the actual location of the tumor at (0, 10, 40) The results display the ability to detect the tumor inside the breast and to reveal its location with high accuracy, and the antenna radiation meet the SAR standards. © 2022 Istanbul University. All rights reserved.Öğe Deep neural network based digital predistorter of power amplifiers(2021) Olcay Güneş, Ece; Ozoğuz, SerdarWe show how to address nonlinearities in power amplifiers (PAs), which limit the power efficiency of mobile devices, increase the error vector magnitude, using an deep neural-network (DNN) method. DPD is frequently performed using polynomial-based algorithms that employ an indirect-learning architecture (ILA), which can be computationally complex, particularly on mobile devices, and highly sensitive to noise. By first training a DNN to model the PA and then training a predistorter using PA data through the PA DNN model. The DNN DPD successfully learns the unique PA distortions that a polynomial-based model may struggle to fit, and therefore may provide a nice balance between computation cost and DPD efficiency. We use two different DNN models to show the performance of our DNN approach and examine the complexity tradeoffs.Öğe Securing IoT devices using blockchain concept(IEEE, 2021) Islam M. Momtaz A., Sadek; Ilyas, MuhammadThe internet of things (IoT) implementation leads to an extended attack surface that requires continuous mitigation of security. Mission-critical situations (e.g., Smart Grid, Intelligent Transportation Systems, video surveillance, e-health) to businessoriented applications are all examples of IoT applications (e.g., banking, logistics, insurance, and contract law). IoT has made human existence considerably easier and more efficient. Because IoT devices are less expensive to build due to the use of various software, sensors, and the use of Artificial Intelligence, they violate several security regulations. That’s why, in the IoT systems; extensive security support is required, particularly for missioncritical applications, but also for downstream commercial applications. There have been a variety of security strategies and approaches suggested and/or used. Blockchain is an amazing concept that manages a distributed ecosystem without the need for a third party. Researchers discovered that it has the ability to solve IoT software-related security problems. The biggest obstacle is combining blockchain with resource-constrained IoT computers. An experimental setup to incorporate blockchain on a smart laboratory IoT-based was completed, and then tested against Wireshark sniffing attacks, the system was more vulnerable to cyber-crimes attacks as we found out that when we employed blockchain technology as the communication medium of IoT devices, the no. of bytes needed for packet transmission was more than the bytes needed without applying Blockchain with about 959 bytes on average.Öğe The influence of encryption techniques and dynamic routing protocols on DMVPN network performance(IEEE, 2021) Marah, Hasan Mohamed; Ilyas, MuhammadDMVPN network is a Cisco-developed technology used to interconnect remote sites and offers flexible implementation. To run DMVPN network, 3 main components must be configured, mGRE, NHRP and 1 routing protocol. GRE protocol is not secured, for this reason, IPsec/mGRE is used to ensure data confidentiality, integrity, and availability. IPsec has many attributes which can provide a different level of security depending on the application. Encryption algorithms are one of the important attributes which affect network performance. Many research works have been done to evaluate the network performance, but what is distinguishes our work is that the most common protocols with the most-used encryption techniques are tested and analyzed with two different data input streams. In this paper, Phase 3 DMVPN network is implemented using “GNS3” simulator, the research work focuses on evaluating different Routing protocol performance (EIGRP, RIP, OSPF) by applying various encryption algorithms (AES, 3DES, DES) in terms of (Throughput, Jitter, Latency, Speed, Packet loss) to find the best combination of routing protocol and encryption technique which can lead to a high DMVPN network performance. Different scenarios are tested based on fixed bandwidth and different data input amounts transferred between server and client. the results revealed that, when data input transferred (500KB)is equal to bandwidth limit (500KB), EIGRP/AES and RIP/3DES protocols are the best protocol combination that shows better performance, on the other hand, when the data input equal to (256KB) and lower than the bandwidth limit, RIP/AES shows better performance.
