Yazar "Senturk, Arafat" seçeneğine göre listele

Listeleniyor 1 - 5 / 5
  • Küçük Resim
    Öğe
    An analysis of the professional preferences and choices of computer engineering students
    (Wiley, 2020) Kabakus, Abdullah Talha; Senturk, Arafat
    The revelation of the preferences and choices of students is critical for understanding which areas of the discipline they aim. Especially for final-year undergraduate students, job prospects are an important concern. In this study, the graduation project choices of the final-year undergraduate students in the department of computer engineering were investigated in light of their impact on both the industry and academia. A total of 1,693 course grades of 94 final-year undergraduate students were retrieved from the Student Information System. These course grades were utilized as the features of the employed machine learning algorithms alongside the features that were deduced from them. In addition, the popularities of the graduation project topics on both GitHub and IEEE were investigated to reveal their impact on the industry and academia. To this end, we proposed an experimental study, using 14 machine learning techniques, that predicts the topics of the graduation projects that the final-year undergraduate students chose. According to the experimental results, the accuracy of the proposed model was calculated to be as high as 100 % when it was utilized with the Bayes Net, Kleene Star, or J48 algorithm. This experimental result confirms the efficiency of the proposed model. Finally, the insights gained from the data are discussed to shed light on the reasons for the choices of the graduation projects as well as their relationships with the courses.
  • Küçük Resim Yok
    Öğe
    Decision tree-based task offloading in vehicle edge computing
    (Wiley, 2024) Tay, Muhammet; Senturk, Arafat
    There are significant developments in the Internet of Vehicles (IoV) field, and the requirements needed in this area are increasing rapidly. When these needs are examined in the near future, it appears that the demand for connected, autonomous, shared, and electric vehicles will increase. Therefore, fundamental problems such as big data flow and storage will arise in the IoV field. Another problem is the delay sensitivity of IoVs and the need to minimize data loss. The use of edge computing (EC) tools can play an important role in obtaining effective solutions to overcome these problems. Delay, bandwidth, and energy consumption rate, which are important qualities in EC systems, emerge as a problem that needs to be improved for delay-sensitive systems. These improvements belong to the category of nonlinear challenging problems. Effective optimization or machine learning methods can be used to improve these types of problems. In this study, a two-stage machine learning method is proposed for a more efficient task completion rate and service time. According to the proposed method, in the first stage, the decision tree algorithm is used to select the computing tool to which the task will be sent, and the decision is made on which computing tool to send it to. In the second stage, a linear regression-based classification method is used to select a delay-sensitive computing tool. The performance analysis of the proposed method was made using the edgeCloudSim simulation tool, and according to the results obtained, the proposed method provides better results than other algorithms in the literature.
  • Küçük Resim
    Öğe
    Fuzzy Logic and Image Compression Based Energy Efficient Application Layer Algorithm for Wireless Multimedia Sensor Networks
    (Comsis Consortium, 2020) Senturk, Arafat; Kara, Resul; Ozcelik, Ibrahim
    Wireless Sensor Networks (WSN) are the networks that can realize data processing and computation skills of sensor nodes over the wireless channel and they have several communication devices. Wireless Multimedia Sensor Networks (WMSN) are the networks composed of low-cost sensor nodes that transmit real-time multimedia data like voice, image, and video to each other and to sink. WMSN needs more energy and bandwidth than WSN since they transmit a larger amount of data. The size of the data transmitted by the sensor nodes to each other or the sink becomes an important factor in their energy consumption. Energy consumption is a fundamental issue for WMSN. Other issues that affect the progress of WMSN are limited bandwidth and memory constraints. In these networks, for which the node battery lives are important sources, the limited sources must be effectively used by decreasing the transmitted data amount by removing the redundant data after proper processing of the environmental data. A new algorithm is developed to minimize the energy consumption during image data transmission between sensor nodes on WMSN, and so, make the nodes use their most important source, battery life ef-fectively in this study. This algorithm is named as Energy-aware Application Layer Algorithm based on Image Compression (EALAIC). This algorithm makes use of the top three image compression algorithms for WMSN and decides instantly to which one is the most efficient based on three parameters: the distance between the nodes, total node number, and data transmission frequency. In this way, the sensor node battery lives are used efficiently. The performance analysis of the developed algorithm is also done via Network Simulator - 2 (NS - 2) and it is compared by the existing algorithms in terms of energy rate (consumed energy/total energy) and PSNR (Peak Signal to Noise Ratio).
  • Küçük Resim
    Öğe
    A New Energy-Aware Cluster Head Selection Algorithm for Wireless Sensor Networks
    (Springer, 2021) Tay, Muhammed; Senturk, Arafat
    Wireless Sensor Networks (WSN) always need energy due to the areas they are used. The use of sensors is quite wide, and in some of the places, it is very difficult or impossible to restore the energy of the sensors such as in war areas or in wildlife. Therefore, they need to use their existing energy most efficiently. For WSN, the role of clustering is crucial in terms of using less energy. Selecting the most appropriate sensor node as cluster head (CH) according to the criteria determined within the clustered sensors reduces the energy consumption. In this study, a new clustering algorithm is proposed for WSNs to reduce energy consumption and thus prolong the life of the WSNs. The Cluster Centered Cluster Head Selection Algorithm (C3HA), which is developed in line with this objective, gives a new perspective to the selection of CH while creating a more efficient WSN than the popular clustering algorithms LEACH, and PEGASIS. This developed algorithm is compared with popular algorithms and proved to be more efficient in terms of fast and accurate CH selection.
  • Küçük Resim
    Öğe
    A transfer learning-based deep learning approach for automated COVID-19 diagnosis with audio data
    (Tubitak Scientific & Technical Research Council Turkey, 2021) Akgun, Devrim; Kabakus, Abdullah Talha; Senturk, Zehra Karapinar; Senturk, Arafat; Kucukkulahli, Enver
    The COVID-19 pandemic has caused millions of deaths and changed daily life globally. Countries have declared a half or full lockdown to prevent the spread of COVID-19. According to medical doctors, as many people as possible should be tested to identify their status, and corresponding actions then should be taken for COVID-19 positive cases. Despite the clear necessity of these medical tests, many countries are still struggling to acquire them. This fact clearly indicates the necessity of a large-scale, cheap, fast, and accurate alternative prescreening tool that can be used for the diagnosis of COVID-19 while waiting for the medical tests. To this end, a novel end-to-end transfer learning-based deep learning approach that uses only a given cough sound for the diagnosis of COVID-19 was proposed in this study. The proposed models employed various pretrained deep neural networks, namely, VGG19, ResNet50V2, DenseNet121, and MobileNet, via the transfer learning technique. Then, these models were evaluated on a gold standard dataset, namely, Cambridge data. According to the experimental result, the proposed model, which employed the MobileNet via the transfer learning technique, provided the best accuracy, 86.42%, and outperformed the state-of-the-art. Thus, the proposed model has the potential to provide automated COVID-19 diagnosis in an easily applicable and fast yet accurate way.