WoS İndeksli Yayınlar Koleksiyonu

Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/394

Browse

Filters

2011 - 201912020 - 20254

Settings

Has files: NoPublisher: search.filters.publisher.Tubitak Scientific & Technological Research Council Turkey

Search Results

Now showing 1 - 5 of 5
  • Article
    Developing a Label Propagation Approach for Cancer Subtype Classification Problem
    (Tubitak Scientific & Technological Research Council Turkey, 2022-01-01) Guner, Pinar; Bakir-Gungor, Burcu; Coskun, Mustafa
    Cancer is a disease in which abnormal cells grow uncontrollably and invade other tissues. Several types of cancer have various subtypes with different clinical and biological implications. Based on these differences, treatment methods need to be customized. The identification of distinct cancer subtypes is an important problem in bioinformatics, since it can guide future precision medicine applications. In order to design targeted treatments, bioinformatics methods attempt to discover common molecular pathology of different cancer subtypes. Along this line, several computational methods have been proposed to discover cancer subtypes or to stratify cancer into informative subtypes. However, existing works do not consider the sparseness of data (genes having low degrees) and result in an ill-conditioned solution. To address this shortcoming, in this paper, we propose an alternative unsupervised method to stratify cancer patients into subtypes using applied numerical algebra techniques. More specifically, we applied a label propagation based approach to stratify somatic mutation profiles of colon, head and neck, uterine, bladder, and breast tumors. We evaluated the performance of our method by comparing it to the baseline methods. Extensive experiments demonstrate that our approach highly renders tumor classification tasks by largely outperforming the state-of-the-art unsupervised and supervised approaches.
  • Article
    Thermal Stresses in SOFC Stacks: The Role of Mismatch Among Thermal Conductivity of Adjacent Components
    (Tubitak Scientific & Technological Research Council Turkey, 2021-06-30) Aydin, Ozgur; Matsumoto, Go; Shiratori, Yusuke
    Generating power from renewable biogas in solid oxide fuel cells (SOFCs) is an environment-friendly, efficient, and promising energy conversion process. Biogas can be used in SOFCs via a reforming process for which dry reforming is more suitable as the reforming agent exists in the biogas mixture. Biogas can be directly reformed to H-2 -rich fuel stream in the anode chamber of a SOFC by the heat released during power generation. Exploiting the heat and water produced in the SOFC for internal reforming of biogas makes the energy conversion process very efficient; however, various challenges are reported. Thus, indirect internal reforming is opted for which a separate reforming domain is required. In an indirect internal reformer operating at usual conditions, dry reforming rate is quite high in the inlet and it decreases steeply toward the fuel outlet. Great temperature gradients develop over the reformer, since the dry reforming reaction is strongly endothermic. The abruptly varying rate of the reforming reaction affects the temperature fields in the adjacent components of SOFC and hence intolerable thermal stresses emerge on the SOFC components. In our preceding study, we graded the reforming domain, homogenized the temperature profile over the reforming domain, and executed performance and durability experiments. However, most of the experiments failed due to fracturing SOFC components hinting at existence of thermal stresses. In that study, we focused on minimizing the temperature gradients within the reforming domain; namely, we neglected the other processes. To eliminate the thermal stresses, we modeled the entire module of SOFC equipped with a reformer featuring a graded reforming domain. We found that the mismatch between the thermal conductivities of the adjacent module components is the major reason for the thermal stresses. When the mismatch is eliminated, thermal stresses disappear even if the reforming domain is not graded.
  • Article
    Optimizing Parameters for Efficient Computation With Fully Homomorphic Encryption Schemes
    (Tubitak Scientific & Technological Research Council Turkey, 2025-03-21) Karaagac, Cavidan Yakupoglu; Rohloff, Kurt; Yakupoğlu Karaağaç, Cavidan; Yakupoglu, Cavidan
    In this study, we aim to provide a parameter selection approach for the BFVrns scheme, one of the prominent fully homomorphic encryption (FHE) schemes. Selecting parameters for lattice-based FHE schemes poses a practical challenge for both experts and nonexperts. To solve this problem, we introduce a hybrid approach that combines theoretical approach with experimental analysis. First, we employ regression analysis to examine the impact of parameters on both performance and security. The varying behavior of FHE parameters in terms of performance, security, and ciphertext expansion factor (CEF) makes parameter selection more challenging. To address this issue, we employ a multi-objective optimization algorithm to determine the optimal parameter set for performance, CEF, and security simultaneously. As a result of this optimization, we obtain an improved parameter set that enhances performance at a given security level while ensuring correctness and resistance to lattice-based attacks, maintaining at least 128-bit security. Our results achieve an average similar to 5x reduction in CEF and generally better performance compared to the parameter sets in a previous BFVrns study. Our approach serves as a semi-automated parameter selection method for the PALISADE homomorphic encryption library, a widely recognized FHE library. This study sets a precedent for other FHE libraries.
  • Article
    Network Intrusion Detection Based on Machine Learning Strategies: Performance Comparisons on Imbalanced Wired, Wireless, and Software Defined Networking (SDN) Network Traffics
    (Tubitak Scientific & Technological Research Council Turkey, 2024) Hacilar, Hilal; Aydin, Zafer; Gungor, Vehbi Cagri
    The rapid growth of computer networks emphasizes the urgency of addressing security issues. Organizations rely on network intrusion detection systems (NIDSs) to protect sensitive data from unauthorized access and theft. These systems analyze network traffic to detect suspicious activities, such as attempted breaches or cyberattacks. However, existing studies lack a thorough assessment of class imbalances and classification performance for different types of network intrusions: wired, wireless, and software-defined networking (SDN). This research aims to fill this gap by examining these networks' imbalances, feature selection, and binary classification to enhance intrusion detection system efficiency. Various techniques such as SMOTE, ROS, ADASYN, and SMOTETomek are used to handle imbalanced datasets. Additionally, eXtreme Gradient Boosting (XGBoost) identifies key features, and an autoenco der (AE) assists in feature extraction for the classification task. The study evaluates datasets such as AWID, UNSW, and InSDN, yielding the best results with different numbers of selected features. Bayesian optimization fine-tunes parameters, and diverse machine learning algorithms (SVM, kNN, XGBoost, random forest, ensemble classifiers, and autoencoders) are employed. The optimal results, considering F1-measure, overall accuracy, detection rate, and false alarm rate, have been achieved for the UNSW-NB15, preprocessed AWID, and InSDN datasets, with values of [0.9356, 0.9289, 0.9328, 0.07597], [0.997, 0.9995, 0.9999, 0.0171], and [0.9998, 0.9996, 0.9998, 0.0012], respectively. These findings demonstrate that combining Bayesian optimization with oversampling techniques significantly enhances classification performance across wired, wireless, and SDN networks when compared to previous research conducted on these datasets.
  • Article
    Citation - WoS: 13
    Design and Implementation of a Voice-Controlled Prosthetic Hand
    (Tubitak Scientific & Technological Research Council Turkey, 2011-01-01) Asyali, Musa Hakan; Yilmaz, Mustafa; Tokmakci, Mahmut; Sedef, Kanber; Aksebzeci, Bekir Hakan; Mittal, Rohin
    Current hand prostheses are mostly driven by electromyography (EMG) signal, and existing experiments have proved that multichannel EMG signal controls are not suitable due to early fatigue problems and high effort, requirements to perform even simple activities. Therefore, in this study we present a new voice-controlled active hand prosthesis to perform several basic tasks. We first designed a novel multifingered prosthetic hand with the ability of picking up and releasing objects. The prosthetic hand employs 3 DC motors and gears to transfer motion to the linked parts of the fingers. We used flexible thin-film, resistive force sensors at the fingertips of the prosthetic hand to adjust the grip force at the fingers. The second part of the study involves the use of speech recognition to control the prosthetic hand. The control circuit that we designed consisted of an HM2007 speech recognition IC and a PIC microcontroller to drive the DC motors moving the fingers. We implemented both the prosthetic hand and its speech recognition-based control electronics. As of now, we have programmed the control hardware to recognize simple pick up and release operations and have successfully tested them. In a future study, we will include more voice commands for the operation of the hand, such as a realistic handshake, and improve the cosmetics of the hand in order to make it look more natural.