Yazar "Cakmak, M." seçeneğine göre listele

Listeleniyor 1 - 6 / 6
  • Küçük Resim Yok
    Öğe
    Analysis of Anomaly Detection Approaches Performed through Deep Learning Methods in SCADA Systems
    (Institute of Electrical and Electronics Engineers Inc., 2021) Altunay, H.C.; Albayrak, Z.; Ozalp, A.N.; Cakmak, M.
    Supervisory control and data acquisition (SCADA) systems are used with monitoring and control purposes for the process not to fail in industrial control systems. Today, the increase in the use of standard protocols, hardware, and software in the SCADA systems that can connect to the internet and institutional networks causes these systems to become a target for more cyber-attacks. Intrusion detection systems are used to reduce or minimize cyber-attack threats. The use of deep learning-based intrusion detection systems also increases in parallel with the increase in the amount of data in the SCADA systems. The unsupervised feature learning present in the deep learning approaches enables the learning of important features within the large datasets. The features learned in an unsupervised way by using deep learning techniques are used in order to classify the data as normal or abnormal. Architectures such as convolutional neural network (CNN), Autoencoder (AE), deep belief network (DBN), and long short-term memory network (LSTM) are used to learn the features of SCADA data. These architectures use softmax function, extreme learning machine (ELM), deep belief networks, and multilayer perceptron (MLP) in the classification process. In this study, anomaly-based intrusion detection systems consisting of convolutional neural network, autoencoder, deep belief network, long short-term memory network, or various combinations of these methods on the SCADA networks in the literature were analyzed and the positive and negative aspects of these approaches were explained through their attack detection performances. © 2021 IEEE.
  • Küçük Resim Yok
    Öğe
    Automatic Speech Recognition (ASR) System using convolutional and Recurrent neural Network Approach
    (Institute of Electrical and Electronics Engineers Inc., 2022) Al-Mansoori, K.W.; Cakmak, M.
    Nowadays, speech recognition is an active research field, where various deep neural architectures are explored. The published successful models are optimized on massive, transcribed datasets, most of which are closed. A deep neural network solves two closely related tasks. It learns to recognize phonemes and formulate grammar rules at the same time. A model can parallel and accurately build both of them when a training corpus is large enough. However, inflected languages such as Polish contain much more grammar rules to define than in the case of English. Therefore, to achieve comparable results in the Polish language, the corpus must be substantially larger than the one presented for the English language. In contrast, to build more massive datasets, we present the Synthetic Boosted Model, which is an attempt to use synthetic data to enrich more profound the implicit language model. In the presented work, we propose the new model architecture, the new objective function, and the new training policy. © 2022 IEEE.
  • Küçük Resim Yok
    Öğe
    BGP Anomali Tespitinde Hibrit Model Yaklaşimi
    (Institute of Electrical and Electronics Engineers Inc., 2022) Uluer, A.F.; Albayrak, Z.; Ozalp, A.N.; Cakmak, M.; Altunay, H.C.
    Border Gateway Protocol (BGP) is important for the quality of the connection between autonomous systems and the domains it is connected to. With attacks made at this level, any anomaly in the network will cause connection failures at the border gateways. In this study, a classification model is proposed by using machine learning and deep learning algorithms for the detection of BGP anomalies. The proposed model is developed based on decision trees and random forest and multilayer perceptron algorithms. Indirect BGP anomalies and connection failure anomalies in the model were evaluated with accuracy and F1-score. In the tests performed on the Slammer dataset, it was seen that the best result was obtained with 99,47 accuracy, and 98,85 F1-Score value in the model studied with the Hybrit Model. © 2022 IEEE.
  • Küçük Resim Yok
    Öğe
    Layer-based examination of cyber-attacks in IoT
    (Institute of Electrical and Electronics Engineers Inc., 2022) Ozalp, A.N.; Albayrak, Z.; Cakmak, M.; Ozdogan, E.
    The Internet of Things (IoT) is a network of millions of smart devices and sensors connected to a network. These devices are used in smart cities, public transportation, smart grids and power transmission lines. Considering IoT devices as a sensor that can be connected to a computer network, it has been seen that they are under many cyber threats. In this study, the concept of security in IoT devices is expressed according to layer architectures, and security requirements in IoT devices cloud layer, application layer, network layer, data layer, and physical layer are analyzed. Possible vulnerabilities and attacks against IoT devices have been examined by layers and next, IoT attacks are classified and layer-based security requirements are explained. © 2022 IEEE.
  • Küçük Resim Yok
    Öğe
    Neural Network Approach for Classification and Detection of Chest Infection
    (Institute of Electrical and Electronics Engineers Inc., 2022) Salih, M.M.M.; Cakmak, M.
    Advances in computer technology have had a profound impact on our lives and the way we see the world. The healthcare industry is advancing thanks to the use of cutting-edge computer technology, which has transformed how numerous ailments are diagnosed and treated. The number of people suffering from chest-related illnesses is increasing at an alarming pace as a result of a wide range of conditions, including air pollution. Medical applications of image processing have emerged due to data collection tool development. It is now possible to make out the diagnosis through study of the features from medical investigation reports for a group of patients. That reduces the time and cost of the diagnosis, which may help plenty of people who are unable to access regular medical facilities due to intolerable cost. In this paper, automatic chest infection diagnosis is being diagnosed using a Neural Network. Two models are used, namely the Artificial Neural Network and the CNN Neural Network. The models are tested using NIH x-ray chest image data. Results are reported with 96.7% and 99.20% accuracy from the Artificial Neural Network and CNN, respectively. © 2022 IEEE.
  • Küçük Resim Yok
    Öğe
    Sex Prediction of Hyoid Bone from Computed Tomography Images Using the DenseNet121 Deep Learning Model
    (Universidad de la Frontera, 2024) Bakici, R.S.; Cakmak, M.; Oner, Z.; Oner, S.
    The study aims to demonstrate the success of deep learning methods in sex prediction using hyoid bone. The images of people aged 15-94 years who underwent neck Computed Tomography (CT) were retrospectively scanned in the study. The neck CT images of the individuals were cleaned using the RadiAnt DICOM Viewer (version 2023.1) program, leaving only the hyoid bone. A total of 7 images in the anterior, posterior, superior, inferior, right, left, and right-anterior-upward directions were obtained from a patient's cut hyoid bone image. 2170 images were obtained from 310 hyoid bones of males, and 1820 images from 260 hyoid bones of females. 3990 images were completed to 5000 images by data enrichment. The dataset was divided into 80 % for training, 10 % for testing, and another 10 % for validation. It was compared with deep learning models DenseNet121, ResNet152, and VGG19. An accuracy rate of 87 % was achieved in the ResNet152 model and 80.2 % in the VGG19 model. The highest rate among the classified models was 89 % in the DenseNet121 model. This model had a specificity of 0.87, a sensitivity of 0.90, an F1 score of 0.89 in women, a specificity of 0.90, a sensitivity of 0.87, and an F1 score of 0.88 in men. It was observed that sex could be predicted from the hyoid bone using deep learning methods DenseNet121, ResNet152, and VGG19. Thus, a method that had not been tried on this bone before was used. This study also brings us one step closer to strengthening and perfecting the use of technologies, which will reduce the subjectivity of the methods and support the expert in the decision-making process of sex prediction. © 2024, Universidad de la Frontera. All rights reserved.