Yazar "Cogen, Fatih" seçeneğine göre listele

Listeleniyor 1 - 6 / 6
  • [ X ]
    Öğe
    Code Index Modulation-Aided Spatial Media-Based Modulation System for Future Wireless Networks
    (IEEE-Inst Electrical Electronics Engineers Inc, 2023) Ozden, Burak Ahmet; Aydin, Erdogan; Cogen, Fatih
    Future wireless networks, increment in mobile users, and Internet-connected devices have brought many needs, such as high data rate, low transmission energy, high error performance, and low latency. Index modulation-based systems have been considered as one of the strong candidates for meeting these demands and needs. In this article, a novel wireless communication system that combines code index modulation (CIM)-aided spatial modulation (SM) and media-based modulation (MBM) techniques, briefly called CIM-SMBM, is proposed for future wireless networks. In the CIM-SMBM system, source information bits are carried in transmitted symbols in addition to three indices: active antenna index selected by SM, indices of different channel states that vary depending on the propagation pattern with MBM, and selected spreading code indices determined by CIM. In order to further reduce the complexity of optimal maximum-likelihood (ML) and despreading-based ML detectors for the CIM-SMBM scheme, an enhanced low-complexity detector that can achieve near-ML error performance is proposed. The average bit error rate (ABER), throughput, energy efficiency, and complexity analyses of the CIM-SMBM system are derived over Rayleigh fading channels for the $M$-quadrature amplitude modulation technique. It has been observed that the ABER and simulation results are quite close to each other.
  • [ X ]
    Öğe
    Driver fatigue detection with image processing
    (IEEE, 2020) Duman, Mehmet; Erdogdu, Elifnaz; Cogen, Fatih; Yildiz, Tuba Conka
    In recent studies, drowsiness of drivers while driving is seen as one of the most important causes of deaths due to traffic accidents. Therefore, in this study, an algorithm that determines driver fatigue by examining the driver's eye conditions in real-time is proposed. Python versions of OpenCV (Open Source Computer Vision Library) and machine learning libraries were used to create this proposed algorithm. In the study, the face and eyes were detected with the Cascade classifier using Haar features. Detected eyes were classified as open closed or half open with the model trained by the SVM (Support Vector Machine) method according to the HOG (Histogram of Oriented Gradient) feature descriptor. Driver fatigue was decided according to the PERCLOS (Percentage of Eyelid Closure) method, which examines the percentage of eyelid closure over time. In the proposed system, fatigue was detected according to the time the driver's eyes were in the half-open or closed state, and a related user interface was designed and audio and visual warnings were given to the driver.
  • [ X ]
    Öğe
    LeafLife: Deep Learning Based Plant Disease Detection Application
    (Institute of Electrical and Electronics Engineers Inc., 2021) Soyer, Mehmet Samil; Yilmaz, Can; Ozcan, Ismail Mervan; Cogen, Fatih; Yildiz, Tuba Çonka
    In this research, using image processing and Convolutional Neural Networks (CNN) together, the detection and classification of diseases in terrestrial plants have been carried out. A CNN was created and developed using a data set containing leaf images of healthy and sick plants. The training of the model was made over a data set of various leaf images containing 87867 images with 98.88% accuracy. In addition, using the same data set, an Android-based application has been developed to detect diseases of plants. Through this application, by taking a photograph of the leaf that is thought to have a disease, it is possible to determine in advance, whether the leaf is really sick and what kind of disease it has. In this way, it is possible to intervene in the spread of the disease as soon as possible. © 2021 Chamber of Turkish Electrical Engineers.
  • [ X ]
    Öğe
    Mirror activation pattern selection for energy efficient hexagonal QAM aided media-based modulation
    (Wiley, 2023) Ozden, Burak Ahmet; Cogen, Fatih; Aydin, Erdogan
    In this article, three mirror activation pattern (MAP) selection techniques are used to improve the performance of energy-efficient hexagonal quadrature amplitude modulation (HQAM) aided media-based modulation (MBM) system called HMBM. These three MAP selection (MS) aided HQAM techniques: (i) capacity-optimized MS-based HMBM (CMS-HMBM) scheme, (ii) MAP correlation (MC) aided MS-based HMBM (MMS-HMBM) scheme, (iii) Euclidean distance (ED) based MS aided HMBM (EMS-HMBM) scheme. MBM technique, one of the newest and most competitive candidates of the index modulation family, increases spectral efficiency linearly and significantly improves error performance. When MS techniques are integrated into telecommunication techniques, they significantly increase the performance of the system. Extensive computer simulations with Monte Carlo for the considered systems are performed on Rayleigh fading channels. The suggested system offers superior error performance than the conventional MBM scheme since it incorporates CMS, MMS, and EMS techniques. Additionally, the suggested new method offers greater energy efficiency than M$$ M $$-QAM constellation schemes since HQAM constellation schemes are by their very nature high energy efficiency. It is shown that the proposed CMS-HMBM, MMS-HMBM, and EMS-HMBM systems provide better error performance than capacity-optimized antenna selection (COAS) aided hexagonal spatial modulation (COAS-HSM), antenna correlation-based AS aided HSM (ACAS-HSM), Euclidean distance optimized AS aided HSM (EDAS-HSM), SM, and MBM systems for the same spectral efficiency. The suggested systems are envisaged for usage in sixth-generation and later wireless networks because of their high performance provided by the CMS, MMS, and EMS methods in the proposed system and the high spectral efficiency provided by the HMBM approach.
  • [ X ]
    Öğe
    Reconfigurable Intelligent Surface Empowered Differential Chaos Shift Keying Assisted Media-Based Modulation over Nakagami-m Fading Channels
    (Institute of Electrical and Electronics Engineers Inc., 2021) Onal, Beyza; Cogen, Fatih; Aydin, Erdogan; Kabaoglu, Nihat
    In this study, it is proposed to apply the reconfigurable intelligent surface (RIS) system, which is seen as a key for new generation communication technologies, to the differential chaos shift keying assisted media-based modulation (DCSK-MBM) system over Nakagami-m fading channels. The system is briefly called DCSK-MBM-RIS. It provides significant performance improvements for DCSK on fading channels, which is one of the building blocks of the proposed system. In the DCSK technique, communication consists of two phases, in the first phase, only the reference symbol is transmitted to the other party, and in the second phase, information is also transmitted with the reference symbol. MBM scheme is one of the new members of the index modulation technique and together with reconfigurable antennas, it provides significant improvements in both data rate and spectral efficiency. RIS, on the other hand, creates a controllable transmission environment, unlike traditional communication models. It reduces power consumption, increases spectral efficiency and coverage. All in all, the proposed system provides high data rates, high energy efficiency, and spectral efficiency according to traditional communication techniques. Simulation results of the system are performed in Nakagami-m fading channels for M -ary modulation techniques. © 2021 Chamber of Turkish Electrical Engineers.
  • [ X ]
    Öğe
    Reconfigurable Intelligent Surface-Aided Spatial Media-Based Modulation
    (Ieee-Inst Electrical Electronics Engineers Inc, 2023) Ozden, Burak Ahmet; Aydin, Erdogan; Cogen, Fatih
    The demands for high data rate, reliability, high energy efficiency, high spectral efficiency, and low latency communication have been increasing rapidly. For this reason, communication models that use limited resources in the best way, allow fast data transmission, and increase performance have become very important. In this work, a novel high energy and spectral efficient reconfigurable intelligent surface-aided spatial media-based modulation system (RIS-SMBM) is proposed for Rayleigh fading channels. In addition to the bits carried in the M-ary quadrature amplitude modulation ( M-QAM) symbol while media-based modulation (MBM) provides data bits to be carried in the indices of different channels according to the radio frequency (RF) mirrors are on or off, spatial modulation (SM) provides data bits to be carried in the indices of the transmit antennas. By combining these two modulation schemes, the spectral efficiency increases considerably since the amount of information transmitted in the same time interval is substantially increased. The optimal maximum-likelihood (ML) detector and the enhanced low-complexity (ELC) detector for the RIS-SMBM system are proposed. The ELC detector achieves near ML performance while reducing the complexity of the optimal ML detector for the proposed RIS-SMBM system. We analyze the average bit error rate (ABER), throughput, complexity, and energy efficiency for the RIS-SMBM scheme and verify the analytical and theoretical results with Monte Carlo simulations. It has been observed that the proposed system provides better error performance as well as providing higher spectral and energy efficiency than benchmark systems. Also, the effect of imperfect channel state information on the performance of the proposed RIS-SMBM system is investigated.