Cihan Karakuzu

Cihan Karakuzu
Bilecik Şeyh Edebali University · Computer Engineering

Prof. Dr.

About

76
Publications
19,966
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
674
Citations
Citations since 2017
27 Research Items
352 Citations
20172018201920202021202220230204060
20172018201920202021202220230204060
20172018201920202021202220230204060
20172018201920202021202220230204060
Additional affiliations
September 2004 - September 2010
Kocaeli University
Position
  • Professor (Assistant)

Publications

Publications (76)
Article
Full-text available
Internet of Things (IoT) is utilized in practically every industry. As IoT becomes more common, the number of wireless communication devices grows. The notion of security becomes more crucial as the number of devices and network grows. Due to welding constraints on IoT devices, the security can not be guaranteed. Radio frequency fingerprinting (RFF...
Article
Full-text available
The use of the Internet of Things (IoT) is increasing with the advancement of technology and systems. The widespread use of IoT devices begs the question of how to secure these systems. Due to resource constraints, it is not possible to implement security measures on IoT devices. As a result, security is becoming increasingly important in IoT devic...
Article
Full-text available
The Internet of Things (IoT) concept is widely used today. As IoT becomes more widely adopted, the number of devices communicating wirelessly (using various communication standards) grows. Due to resource constraints, customized security measures are not possible on IoT devices. As a result, security is becoming increasingly important in IoT. It is...
Article
In this paper, two novel Multilayer Extreme Learning Machine (ML-ELM) networks are presented. We call them Improved Multilayer Extreme Learning Machines (IML-ELM). The proposed network architectures use neuron activations both during and after the training. In the first IML-ELM (IML-ELM1) network, each layer has connection weights assigned randomly...
Article
As the share of global offshore wind energy in the electricity generation portfolio is rapidly increasing, the grid integration of large-scale offshore wind farms is becoming of interest. Due to the intermittency of wind, the stability of power systems is challenging. Therefore, accurate and fast offshore short-term wind speed forecasting tools pla...
Article
Hearing impaired individuals can easily overcome the barriers in communicating with other members of the society via computer technology. In this study, the recognition of dynamic words in Turkish Sign Language (TSL) with two hands was studied using the Leap Motion Controller (LMC) device. 50 dynamic words were determined considering the similariti...
Article
Purpose This paper aims to deal with the optimal choice of a novel extreme learning machine (ELM) architecture based on an ensemble of classic ELM called Meta-ELM structural parameters by using a forecasting process. Design/methodology/approach The modelling performance of the Meta-ELM architecture varies depending on the network parameters it con...
Article
Full-text available
In this study, the improvement of the ant lion optimization which is inspired by ant lion’s hunting strategy is dealt with. The most disadvantageous property of this algorithm is its having a long run time due to the random walking process. In order to overcome this drawback, we proposed the improved random walking model, tournament selection metho...
Article
In this paper, distributed intrusion detection systems (IDSs)in the literature are reviewed. There are two types of IDS, depending on the interoperability. Stand-alone systems decide on their own. Distributed systems are composed of multiple components processing different data and work together to make a global decision. Distributed IDSs present s...
Article
Full-text available
Antlion optimizer algorithm (ALO) is inspired by hunting strategy of antlions. In this study, an improved antlion optimization algorithm is proposed for training parameters of adaptive neuro fuzzy inference system (ANFIS). In the standard ALO algorithm, the greatest deficiency is its long running time during optimization process. The random walking...
Conference Paper
Full-text available
The concept of energy is an indispensable component of humanity's continuity on behalf of our age and our future is one of the basic facts. Due to this important nature, it is clear that countries need continuous, safe and sustainable energy resources in order to have a healthy economy. The use of alternative energy sources is increasing rapidly du...
Conference Paper
Full-text available
Neural networks (NNs) are used to handle with many engineering and science problems. Feedforward architecture is usually preferred and gradient-based iterative learning algorithms are commonly operated to determine weights and biases parameters of NNs. This kind of training method needs a long time because of the nature of gradient-based iterative...
Conference Paper
Full-text available
Neural networks (NNs) and fuzzy systems are commonly used and popular general modeling methods to handle with many engineering and science problems. These architectures are usually trained by iterative algorithms. To overcome the slowness disadvantage of iterative algorithms, extreme learning machine (ELM) concept has brought an important evolution...
Conference Paper
Full-text available
Neural networks (NNs) is used to solve many engineering and science problem. Generally, feedforward architecture is preferred and gradient-based learning algorithms are extensively operated to tune all parameters of NN iteratively. This training method is a conventional one, but training process takes a long time due to the slowness of gradient-bas...
Conference Paper
Full-text available
In this study, the Opposition based learning S piral Optimization Algorithm (OBLS OA) is presented for training Multi-Layer Perceptron (MLP). The main idea of S piral Optimization Algorithm (S OA) is based on the dynamic step dimension in its spiral path trajectory. The primary opposition based learning (OBL) concept first was come from the Yin-Yan...
Conference Paper
In this study, an active alarm and event notification system that can provide security against theft of motorcycles has been designed. With this system, the owner of the motorcycle will be alerted at the moment of burglary action using the voice dialing method. Burglary action will be more difficult and deterrent when the horn on the bike is activa...
Article
Full-text available
Heuristic algorithms are used for optimizing a large diversity of engineering problems. In this study, the performance of six commonly used and cited meta-heuristic algorithms (MhAs) is compared based on point of view fuzzy modelling. In this study, the simplest version of MhAs is specifically used to observe and evaluate their natural optimization...
Article
Full-text available
Bu çalışmada insansı bir robot kolunun kablosuz bir eldiven sistemi ile uzaktan kontrolü ele alınmış ve bu amaçla iki farklı robot kolu oluşturulmuş ve uzaktan kontrolü için özel bir kullanıcı eldiveni tasarımı yapılmıştır. Verici eldiven yapısında kişinin parmak eklemi hareketlerinin algılanması için eldiven üzerine eğim sensörleri yerleştirilmişt...
Article
Full-text available
In this study, a new test platform was developed for rotary wing unmanned air vehicle (UAV) with the multi-rotors. This platform basically includes three different sized circles. Before the flight of UAV, all tests such as yaw, pitch, roll, elevation, etc., are done by the proposed test platform, so the problem or crash in flight of UAV will be pre...
Technical Report
Full-text available
Görüntü kararlılığı, istenmeyen kamera hareketlerinin sebep olduğu veya hareket halindeki araçlardan yapılan çekimlerde meydana gelen düzensiz titreşimleri yok etmek amacıyla yapılan yöntem ve uygulamaları içermektedir. Uzun süreli yapılan çekimlerde, görüntü çerçevesini kaybetmemek için istenmeyen ani değişimli hareketler kararlılaştırma işlemi il...
Conference Paper
Full-text available
Bu çalışmada insansı bir robot kolunun uzaktan kontrolü ele alınmış ve bu amaçla tasarlanan bir robot kolu üç boyutlu yazıcı yardımıyla oluşturulmuş ve uzaktan kontrolü için özel bir kullanıcı eldiveni tasarımı yapılmıştır. Verici eldiven yapısında kişinin parmak eklemi hareketlerinin algılanması için eldiven üzerine eğim sensörleri yerleştirilmişt...
Technical Report
Full-text available
Son yıllarda İnsansız Hava Aracı (İHA) platformlarına olan talep gün geçtikçe artmakta ve özellikle askeri alanda kullanımı stratejik bir teknoloji haline gelmektedir. İHA'lar üzerinde insan olmadan uçabilme özelliğine sahip, otonom olarak görev yapabilen ya da uzaktan kumanda aracılığıyla kontrol edilebilen hava araçlarıdır. İHA’lar araştırma geli...
Conference Paper
Full-text available
Bu çalışmada, sezgisel optimizasyon algoritmalarından biri olan yayılımcı rekabetçi algoritma (imperialist competitive algorithm, ICA) ve algoritma üzerinde iki farklı düzenleme yapılarak elde edilmiş iki yeni geliştirilmiş (G-ICA) versiyonunun optimizasyon başarımı incelenmiştir. Bu algoritmaların optimizasyon başarımı hem fonksiyon optimizasyonu...
Article
This paper presents the first hardware implementation of neuro-fuzzy system (NFS) with its metaheuristic learning ability on field programmable gate array (FPGA). Metaheuristic learning of NFS for all of its parameters is accomplished by using the improved particle swarm optimization (iPSO). As a second novelty, a new functional approach, which doe...
Conference Paper
Full-text available
In this research, we introduce a novel network, Hybrid Radial Basis Function Neural Network (HyrRbfNN), an artificial neural network (ANN) in which a hidden layer of radial basis function (RBF) is integrated. The training of weight parameters is accomplished using improved particle swarm optimization (iPSO). In total, the network has four layers. (...
Conference Paper
Full-text available
Direct current (DC) motors are commonly used to control position or speed in many applications. The speed of the DC motors is adjustable in a wide range with advantages such as easy control theorems and high performances. DC motors are used in industrial branches like transportation, electrical train, vehicle, crane, printer, drivers, paper industr...
Article
Full-text available
Electroencephalogram (EEG) is used routinely for diagnosis of diseases occurring in the brain. It is a very useful clinical tool in the classi�cation of epileptic seizures and the diagnosis of epilepsy. In this study, epilepsy diagnosis has been investigated using EEG records. For this purpose, an arti�cial neural network (ANN), widely used and kno...
Article
Full-text available
This paper presents an approach for modeling and prediction of both surface roughness and cutting zone temperature in turning of AISI304 austenitic stainless steel using multi-layer coated (TiCN + TiC + TiCN + TiN) tungsten carbide tools. The proposed approach is based on an adaptive neuro-fuzzy inference system (ANFIS) with particle swarm optimiza...
Conference Paper
Full-text available
This paper presents an on-line path-planning method for a swarm of mobile robots. The method is based on a simple heuristic search (ShS) algorithm. In the proposed method, an independent ShS swarm for each robot is used to find an appropriate sub-path in real time during a sampling instant of overall system. At each sampling instant , the ShS algor...
Conference Paper
Full-text available
In this paper, an application of user interface is presented which is used for aiming to observe virtually performance of widespread heuristic optimization algorithms such as ABC, PSO and GA. This software application executes function optimization according to minimum, maximum or a specific point on a predetermined benchmark function by user. The...
Conference Paper
Full-text available
Electroencephalogram (EEG) is used routinely for diagnosis of diseases occurring in the brain. It is a very useful clinical tool in classification of epileptic attacks and epilepsy diagnosis. In this paper, epilepsy diagnosis by evaluation of EEG records is presented. Artificial Neural Networks (ANN) is used as a classification technique. Particle...
Conference Paper
Full-text available
In this paper, epilepsy diagnosis has been investigated by using Electroencephalogram (EEG) records. For this purpose, a technique as the classifier Artificial Neural Networks (ANN), which is frequently used and known as an active classification technique, is used. Particle Swarm Optimization (PSO) method is preferred as training algorithm for ANN....
Article
This work introduces hardware implementation of artificial neural networks (ANNs) with learning ability on field programmable gate array (FPGA) for dynamic system identification. The learning phase is accomplished by using the improved particle swarm optimization (PSO). The improved PSO is obtained by modifying the velocity update function. Adding...
Technical Report
Full-text available
Yapay Arı Koloni (YAK) algoritması 2005 yılında Dervis Karaboğa tarafından bal arılarının davranışından esinlenerek geliştirilmiş popülasyon tabanlı bir optimizasyon algoritmasıdır. YAK algoritmasında yapay arılar çok boyutlu arama uzayında uçarlar ve birbirleri arasındaki deneyim paylaşımına dayalı olarak uzaydaki pozisyonlarını belirlerler. 2005'...
Article
Full-text available
Levenberg-Marquardt (LM) algoritması yapay sinir ağlarının eğitiminde sağlamış olduğu hız ve kararlılık nedeni ile tercih edilmektedir. Bu çalışmada yapay sinir ağı (YSA) eğitiminin LM algoritması ile kayan noktalı sayı formatında donanımsal olarak FPGA’da gerçeklenmesi sunulmuştur. Donanımsal gerçekleme ISE Webpack10.1 programı kullanılarak Xilinx...
Conference Paper
Full-text available
In this study, wavelet fuzzy system (WFS) together with its PSO-based learning is hardware implemented on FPGA. Floating point number format is used for the implementation considering its precision and dynamics. Although floating point numbers consume more hardware source than the other number format, WFS implementation has been achieved with only...
Conference Paper
Full-text available
In order to solve nonlinear optimization problems, usage of heuristic methods has become widespread. In this paper, performance of four heuristic search algorithms (Genetic Algoritm-GA, Ant Colony Algorithm-ACO, Particle Swarm Optimization-PSO, Differential Evolution-DE) is investigated to determine PID controller parameters for DC motor control. T...
Article
Full-text available
In this study, previously developed five different state estimation methods are examined and compared for estimation of biomass concentrations at a production scale fed-batch bioprocess. These methods are i. estimation based on kinetic model of overflow metabolism; ii. estimation based on metabolic black-box model; iii. estimation based on observer...
Article
Full-text available
In this paper, two-layered feed forward artificial neural network’s (ANN) training by back propagation and its implementation on FPGA (field programmable gate array) using floating point number format with different bit lengths are remarked based on EX-OR problem. In the study, being suitable with the parallel data-processing specification on ANN’s...
Article
Full-text available
Currently, neural and fuzzy systems are methods which have found wide application area. Implementation of these systems on a hardware platform providing their own features is important. With parallel data streaming and processing features, FPGAs have become a preferable hardware platform for implementing of neural and fuzzy systems. In hardware imp...
Article
Full-text available
In this paper, an auto-tuning fuzzy sliding-mode controller design approach using particle swarm optimization (PSO) is proposed. This approach provides a simple way of designing a fuzzy sliding controller for nonlinear systems. Moreover, for this method the heuristic sliding factors are not needed to be known. Therefore, the proposed method elimina...
Article
The objective of this study is to develop fuzzy logic based traffic junction light simulator system for design and smart traffic junction light controller purposes and also to observe its performance. Traffic junction simulator hardware is developed to overcome difficulties of working in a real environment and to easily test the performance of the...
Article
Full-text available
In this study, a new ANN training approximation on FPGA is presented using parallel processes according to the nature of ANN. Training is implemented on FPGA using particle swarm optimization (PSO) stochastic search algorithm which does not need any derivative information. All related parameter values and processes are defined with IEEE 754 floatin...
Article
Full-text available
Bu çalışmada YSAnın doğasına uygun olarak paralel işlemlerle, FPGA üzerinde, YSA eğitimi için yeni bir yaklaşım sunulmuştur. Eğitim türev bilgisine ihtiyaç duymaksızın, rastgele arama algoritması olan parçacık sürü optimizasyonu (PSO) kullanılarak FPGA üzerinde gerçeklenmiştir. FPGA’de ilgili tüm parametre değerleri ve işlemler IEEE 754 kayan nokta...
Conference Paper
Full-text available
This paper describes the effective utilization of particle swarm optimization (PSO) to train a Takagi–Sugeno (TS)-type network controller for two samples of high nonlinear systems. First sample system is continuous stirred tank reactor (CSTR) and the second is Van-Der-Pole (VDP) oscillator. For the first system first-order, for the second system se...
Conference Paper
This paper intends to cope with single target tracking nonlinear filtering problem with an Adaptive Neuro-Fuzzy Inference System (ANFIS). ANFIS provides faster adaptation, adequate convergence and easy using over other standard filters. The ANFIS used in this study is trained on-line while the target is moving to estimate the next position of targe...
Conference Paper
Full-text available
This paper intends to cope with single target tracking nonlinear filtering problem with an Adaptive Neuro-Fuzzy Inference System (ANFIS). ANFIS provides faster adaptation, adequate convergence and easy using over other standard filters. The ANFIS used in this study is trained on-line while the target is moving to estimate the next position of targe...
Article
Two soft sensors were developed for the estimation of biomass concentration and specific growth rate in fed-batch baker's yeast fermentation: one based on estimation of specific growth rate from process model, the other based on actual measurements. The first method of estimation gave satisfactory results under fixed initial condition where inoculu...
Article
The FPGAs (Field Programmable Gate Arrays) approach for neural network implementation provides flexibility in programmable systems. For the neural based instrument prototype in real time application, conventional specific VLSI neural chip design suffers from the limitation in time and cost. With low precision artificial neural network design, FPGAs...
Conference Paper
Full-text available
This paper presents design and simulation of a fuzzy controller for industrial fed-batch baker's yeast fermentation system in order to supply air feeding. The controller determines optimal air feeding profile, related to status of dissolved oxygen concentration. It has been tested on a simulated fed-batch industrial scale fermenter. The results dem...
Conference Paper
Full-text available
Conventional control systems can not give satisfactory results in fermentation systems due to process non-linearity and long delay time,. This paper presents design and simulation a fuzzy controller for industrial fed-batch baker’s yeast fermentation system in order to maximize the cell-mass production and to minimize ethanol formation. Designed fu...
Conference Paper
Full-text available
Neural, fuzzy logic and classical (PI) control techniques were compared based on an experimental application in this study. Experimental studies were implemented on a water temperature control system. The control techniques were compared through experimental studies under identical conditions with respect to set-point regulation and load disturbanc...
Article
Full-text available
By reason of the process non-linearity and response of the system with long delay time, conventional control systems can not give satisfactory results in fermentation systems.. This paper presents a fuzzy controler design and simulation for industrial fed-batch baker's yeast fermantation system. The proposed controller uses error in specific growth...
Article
Full-text available
In recent past, several neural network models which employ cutting forces for estimation as well as classification of wear have been developed. A important variation in mean, RMS, variance, standard deviation cutting forces can result in estimation and classification error. Many tool wear condition monitoring techniques have been investigated using...
Article
Full-text available
This paper describes the effective utilization of particle swarm optimization (PSO) to train a Fuzzy- Neural controller (FNC) for two samples of high nonlinear systems. First sample system is continuous stirred tank reactor (CSTR) and the second is Van- Der-Pole (VDP) oscillator. FNCs are learned by PSO to hold the selected state variable at fixed...

Network

Cited By

Projects

Project (1)
Project
Because of harmful effects of fossil fuels; renewable energy sources such as wind, solar, geothermal and biomass have begun to be used. The wind and solar energy have been used more than the other energy sources due to the conditions such as efficiency in the supply of electricity, cost and the presence of the reserve widely. Incentives and investments in this area have also become competitive with other energy sources. For these reasons, the number of studies aimed at reducing the consumption of fossil fuels is increasing rapidly. One of the systems usually consuming fossil fuels is the transport system. However, the rapid increase in fossil fuel consumption due to the internal combustion engine vehicles causes environmental problems and also reduces fossil fuel reserves. Electric vehicles are recommended as a solution to these problems in the near future.