Yazar "Yilmaz A." seçeneğine göre listele
Listeleniyor 1 - 3 / 3
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Comparison of ML Algorithms to Detect Vulnerabilities of RPL-Based IoT Devices in Intelligent and Fuzzy Systems(Springer Science and Business Media Deutschland GmbH, 2022) Kiraz M.U.; Yilmaz A.The RPL protocol (Routing Protocol for Low-Power and Lossy Networks) was designed by IETF [1] for 6LoWPAN to optimize power consumption on the Internet of Things (IoT) devices. These devices have limited processing power, memory, and generally limited energy because they are battery-powered. RPL aims to establish the shortest distance by setting up n number of IoT devices through each other DAG (Directed Acyclic Graph) and therefore the most optimum energy consumption. However, due to the complex infrastructure of RPL and the low capacity of IoT devices, the RPL protocol operating at the network layer is susceptible to attacks. Therefore, it is vital to develop a fast, practical, uncomplicated, and reliable intrusion detection system in the network layer. In the event of an attack on IoT devices operating with the RPL protocol, an anomaly will occur in the network packets in the 3rd layer. Processing these packages with machine learning algorithms will make the detection of the attack extremely easy. In this article, “Decision Tree,” (DT) “Logistic Regression,” (LR) “Random Forest,” (RF) “Fuzzy Pattern Tree Classifier,” (FPTC), and “Neural Network” (NN) algorithms are compared for catching Flooding Attacks (FA), Version Number Increase Attacks (VNIA), and Decreased Rank (DRA) attacks. At the end of our study, it is observed that the Random forest algorithm gave better results than other algorithms in the system built by the study. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.Öğe Hybrid handwriting character recognition with transfer deep learning [Aktarimli Derin Ö?renme ile Hibrit El Yazisi Karakter Tanima](Institute of Electrical and Electronics Engineers Inc., 2019) Can F.; Yilmaz A.Handwriting character recognition is useful and important in terms of allowing correct recognition and interpretation of all characters such as handwritten letters, numbers and figures. Deep convolutional neural networks have been used frequently for computer vision in recent years due to high performance in image processing, feature extraction and classification. A lot of sample data, processing power and time are needed to train CNNs. Transfer learning enables us to obtain specific CNNs for the classes we want by minimizing these needs In this work, firstly, different CNN models are trained with transfer learning by using NIST19 dataset with handwritten characters, and then a hybrid model is created by evaluating the results of each CNN and revealing the best value. As a result of the experiment carried out on the test data set, it is observed that a performance increase of 1.1% is achieved with the created model. © 2019 IEEE.Öğe Vehicle sales prediction using neural fuzzy logic method in industry 4.0(Peter Lang AG, 2019) Kaya U.; Yilmaz A.; Keskin K.[No abstract available]
