Yazar "Toklu, Sinan" seçeneğine göre listele
Listeleniyor 1 - 11 / 11
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Application Specific Sleep-Awake Strategy for Increasing Network Lifetime in Wireless Sensor Networks(2018) Şimşek, Mehmet; Toklu, SinanWireless Sensor Networks (WSN) is a technology that provides distributed data collection. However, thesenetworks have some limitations. The most important constraint is energy limitations. The lifespan of sensornodes that run on small battery depends on the battery life. Although there are many studies in the field ofenergy efficiency to extend the life of nodes, enough improvement has not been obtained yet. The most basicway to achieve energy efficiency is to sleep and awake the nodes or clusters of nodes. In this study, we proposedan application specific method to wake up and sleep nodes in WSNs. In traditional strategy, the nodes in thecluster sense data and send it to the Cluster Head (CH), if CHs detect redundancy of some data; they remove theduplication and send it to the base station. This is causing energy loss. Our method puts some nodes to sleepstate if there are similar data in a certain period. By this way, the life of the network is extended.Öğe An Augmented Reality Application for Computer Engineering Curriculum(2017) Şimşek, Mehmet; Toklu, Sinan; Özsaraç, Hamza; Zavrak, Sultan; Başer, Ekrem; Takgil, Büşra; Kanbur, ZaferToday, smart phones and tablet PCs have a huge application area due to their capabilities and ease of use. One of these application areas is education. Especially, supportive technologies have brought big innovations on teaching abstract concepts to the students. One of these technologies is Augmented Reality (AR) which moves graphic&animation usage one step towards. In this study, we shared our experiments on the usage of AR in computer engineering curriculum and presented the application that developed with using AR for supporting the abstract concepts of Discrete Mathematical Structures courseÖğe AVL Based Settlement Algorithm and Reservation System for Smart Parking Systems in IoT-based Smart Cities(Zarka Private Univ, 2022) Canlı, Hikmet; Toklu, SinanIn Internet of Things (IOT)-based smart cities, negative reasons such as cost, energy and air pollution when searching for a parking space increase the importance of smart parking systems. In this study, a two-stage hybrid approach is proposed so that drivers can find a parking space that will consume the least time and energy. The first stage focuses on car parks having at least one free parking space located near the target address in an n diameter circumference, which are also open for business. An AVL tree-based hierarchical structure is created with driving time from the starting point to each car park and walking time from each car park to the destination, and it focuses on the most appropriate car park. In the second stage, the most suitable parking space is searched and made available, if found, in hierarchical parking monitoring system. In order to demonstrate the effectiveness of the approach, the results compared with hierarchical, hierarchical Binary Search Tree (BST) and non-hierarchical solutions in terms of energy and time performance are shown on a simulation. Proposed approach gave the best result with 99% energy efficiency. In addition, a dynamic cloud-based reservation system was proposed for the parking lot determined in the study.Öğe A deep learning analysis on question classification task using Word2vec representations(Springer London Ltd, 2020) Yilmaz, Seyhmus; Toklu, SinanQuestion classification is a primary essential study for automatic question answering implementations. Linguistic features take a significant role to develop an accurate question classifier. Recently, deep learning systems have achieved remarkable success in various text-mining problems such as sentiment analysis, document classification, spam filtering, document summarization, and web mining. In this study, we explain our study on investigating some deep learning architectures for a question classification task in a highly inflectional language Turkish that is an agglutinative language where word structure is produced by adding suffixes (morphemes) to root word. As a non-Indo-European language, languages like Turkish have some unique features, which make it challenging for natural language processing. For instance, Turkish has no grammatical gender and noun classes. In this study, user questions in Turkish are used to train and test the deep learning architectures. In addition to this, the details of the deep learning architectures are compared in terms of test and 10-cross fold validation accuracy. We use two major deep learning models in our paper: long short-term memory (LSTM), Convolutional Neural Networks (CNN), and we also implemented the combination of CNN-LSTM, CNN-SVM structures and a number of various those architectures by changing vector sizes and the embedding types. As well as this, we have built word embeddings using the Word2vec method with a CBOW and skip gram models with different vector sizes on a large corpus composed of user questions. Our another investigation is the effect of using different Word2vec pre-trained word embeddings on these deep learning architectures. Experiment results show that the use of different Word2vec models has a significant impact on the accuracy rate on different deep learning models. Additionally, there is no Turkish question dataset labeled and so another contribution in this study is that we introduce new Turkish question dataset which is translated from UIUC English question dataset. By using these techniques, we have reached an accuracy of 94% on the question dataset.Öğe A Deep Learning-Based Seed Classification with Mobile Application(2021) Başol, Yusuf; Toklu, SinanSeed quality is an essential factor in agricultural production. Some seeds are inherently small so it is difficult to identify and classify differences between species. In the traditional method, these differences are classified by experts considering the morphological structure, texture and color. This method involves a classification process that is costly, subjective and time confusing, what makes it necessary to develop a process that can automatically detect the type of seeds. In this study, a mobile application has been developed that quickly detects and classifies seed images with high accuracy using CNN, one of the deep learning techniques.Öğe Energy Efficiency with Centralized Layering Approach for Multihop Wireless Sensor Networks(2020) Şimşek, Mehmet; Toklu, SinanSensors and Wireless Sensor Networks (WSN) are an important component of the Internet of Things (IoT) era. Sensors can be used in easily accessible areas such as factories; It is also used in places with difficult access, such as cultivated areas, forests etc. The most important constraint of sensors placed in areas where access is difficult is energy. Therefore, sensors need to spend as little energy as possible to communicate with each other. For this purpose, a number of studies were made concerning the optimization of energy in WSNs. Most of the studies are carried out in MAC and Routing Layers. In this study, we developed a new routing protocol called Base-Station Layered LEACH (BLLEACH) based on LEACH (Low Energy Adaptive Clustering Hierarchy) routing protocol, which is one of the most significant benchmarks in WSNs. BLEACH divides the network into clusters in a multi-hop environment. Experimental results show that BLLEACH outperforms LEACH and MDLEACH (Multi-hop dynamic clustering LEACH) in terms of energy efficiency and throughput.Öğe The Future of Wireless Technology and Potential Problems and Solutions(Ieee, 2017) Yılmaz, Şeyhmus; Toklu, SinanWireless is among technology's biggest contributions to human beings. Wireless technology involves the delivering of data over a distance without aid of wires, cables or any other types of electrical conductors. The delivering distance could be anyplace among a few meters and thousands of kilometers. In this paper, we outline the future of wireless technology and discuss potential problems and solutions.Öğe Implementation of Decision Support System with Data Mining Methods in the Quality Control Process of the Automotive Sector(2019) Canlı, Hikmet; Toklu, SinanToday, the automotive sector is the "key" sector for developed and even developing countries. A strongautomotive sector is striking as one of the common features of industrialized countries. Production in this sectorconsists of many processes. One of the most important of these processes is quality control. The measurementdata in this area is very large and as the volume of data increases, the rate that people understand is reduced.Variations are the enemy of quality. There are many variations in the area of quality control. In this study, adecision support system is applied in the quality control process with classification algorithms which are datamining methods. C4.5, Naive Bayes, SMO and Random Forest algorithms are run on data set collected fromproduction. These algorithms are used to measure the quality and accuracy of the product without completing theoperations during production. Algorithms have been cost-reduced by determining that the product is faultybefore operations are completed. The algorithm C4.5 has been the best performing algorithm. In addition, thesealgorithms make quality analysis very fast and easy. Thanks to this work, the cost of labor and materials hasbeen reduced in the production company.Öğe Nesnelerin İnternetinde Sahte Kimlik Saldırılarının Makine Öğrenme Yöntemleri ile Tespiti(2020) Yalçın, Nesibe; Toklu, Sinan; Çakır, SemihNesnelerin interneti (Internet of Things, IoT) cihazları, kablosuz algılayıcı ağlarında yaşanan gelişmelerle her geçen gün daha fazla kullanım oranına sahip olmaktadır. IoT cihazlarının tümünün birbirine bağlanması ile oluşan heterojen ağ, dışarıdan gelen saldırılara oldukça açıktır. Günümüze kadar birçok yönlendirme protokolü saldırıları ortaya atılmış olup gün geçtikçe saldırılar artmaya ve çeşitlenmeye devam etmektedir. Bununla birlikte, önerilen tespit ve önleme yöntemlerinin de günümüz şartlarına göre iyileştirilmesi ve güncel olması gerekmektedir. Sahte kimlik saldırıları, IoT’ de ağ katmanında kayıplı ağlarda yönlendirme protokolünde (Routing Protocol for Low-Power and Lossy Network, RPL) yer almaktadır. Sahte kimlik saldırıları türünde düğümlerin sinyal gücüne bağlı saldırı tespitleri, en yaygın kullanılan ve önerilen yöntemlerdendir. Kaynak kısıtlı olan IoT cihazlarında, enerji korunumu ve düşük işlem yükü önemli hususların başında gelmektedir. Özellikle saldırı tespitinde kullanılan klasik yöntemler, saldırıların tespiti ve önlenmesinde yetersiz kalabilmektedir. Bu çalışmada, düğümlerin paket dağıtım oranları ve makine öğrenmesi yaklaşımlarından Naive- Bayes, Random Forest ve Lojistik Regresyon ile sahte kimlik saldırılarının tespiti önerilmiştir. Sahte kimlik saldırıları, klasik yöntemlere kıyasla daha yüksek başarım oranı (99.51% doğruluk) ile tespit edilmiştir.Öğe RPL Attack Detection and Prevention in the Internet of Things Networks Using a GRU Based Deep Learning(Ieee-Inst Electrical Electronics Engineers Inc, 2020) Cakir, Semih; Toklu, Sinan; Yalcin, NesibeCyberattacks targeting Internet of Things (IoT), have increased significantly, over the past decade, with the spread of internet-connected smart devices and applications. Routing Protocol for Low-Power and Lossy Network (RPL) enables messages to be routed between nodes for the Wireless Sensor Network in the network layer. RPL protocol, which is sensitive and difficult to protect, is exposed to various attacks. These attacks negatively affect data transmission and cause great destruction to the topology by consuming the resources. Hello Flooding (HF) attacks against RPL cause consumption of constrained resources (memory, processing and energy) in nodes. Therefore, in this study, a Gated Recurrent Unit network model based deep learning has been proposed to predict and prevent HF attacks on RPL protocol in IoT networks. The proposed model has been compared with Support Vector Machine and Logistic Regression methods, and different power states and total energy consumptions of the nodes have been taken into consideration and experimented with. The results confirm the promised and expected performance from the model in terms of source efficiency and IoT security. In addition, attack detection has been carried out with a much lower error rate than literature studies for HF attacks from RPL flood attacks.Öğe Two-Layer Approach for Mixed High-Rate and Low-Rate Distributed Denial of Service (DDoS) Attack Detection and Filtering(Springer Heidelberg, 2018) Toklu, Sinan; Şimşek, MehmetDistributed denial of service (DDoS) attacks are one of the most important attacks due to reducing the performance of computer networks nowadays. In recent years, the number of devices connected to the internet has been increasing. These devices are not only computers, but also objects of everyday use. The concept of internet has accelerated the increase considerably. Therefore, many problems arise in terms of DDoS attacks. One of them is low-rate DDoS attacks. While high-rate DDoS attacks are often performed with computers, low-rate DDoS attacks can be easily performed by computers and internet-connected objects. Therefore, effective defense mechanism against both attacks must be developed. In this study, new approaches are proposed to filter mixed high-rate DDoS and low-rate DDoS attacks. The ns-2 simulation tool was used to evaluate the performance of the proposed methods. Experimental results show that the proposed methods are successfully filtered mixed DDoS attacks.
