Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Deep learning (22)
- Machine learning (11)
- COVID-19 (7)
- Transfer learning (7)
- Classification (6)
-
- Convolutional neural network (5)
- Genetic algorithm (5)
- Artificial intelligence (4)
- Convolutional neural networks (4)
- Deep neural network (4)
- Energy consumption (4)
- Feature extraction (4)
- Support vector machine (4)
- Wireless sensor networks (4)
- Breast cancer (3)
- Discrete wavelet transform (3)
- Face recognition (3)
- Long short-term memory (3)
- MapReduce (3)
- Pattern recognition (3)
- Reinforcement learning (3)
- Robust control (3)
- Artificial neural network (2)
- Artificial neural networks (2)
- Big Data (2)
- Brain tumor (2)
- Cloud computing (2)
- Convolution neural network (2)
- Data augmentation (2)
- Distributed generation (2)
Articles 1 - 30 of 202
Full-Text Articles in Computer Engineering
Line-Of-Sight Rate Construction For A Roll-Pitch Gimbal Via A Virtualpitch-Yaw Gimbal, Oğuzhan Çi̇fdalöz
Line-Of-Sight Rate Construction For A Roll-Pitch Gimbal Via A Virtualpitch-Yaw Gimbal, Oğuzhan Çi̇fdalöz
Turkish Journal of Electrical Engineering and Computer Sciences
In this paper, a method to construct the line of sight rate of a target with a roll-pitch gimbal and tracker is described. Construction of line-of-sight rate is performed via utilizing a virtual pitch-yaw gimbal. Kinematics of both the roll-pitch and pitch-yaw gimbals are described. A dynamical model for the roll-pitch gimbal is developed, and a nested control structure is designed to control the angular rates and line of sight angles. A kinematic model of the tracker is developed and a tracker controller is designed to keep the target in the field of view. Conversion equations between roll-pitch and pitch-yaw …
A New Method For Optimal Expansion Planning In Electrical Energy Distributionnetworks With Distributed Generation Resources Considering Uncertainties, Amir Masoud Mohaghegh, S Yaser Derakhshandeh, Abbas Kargar
A New Method For Optimal Expansion Planning In Electrical Energy Distributionnetworks With Distributed Generation Resources Considering Uncertainties, Amir Masoud Mohaghegh, S Yaser Derakhshandeh, Abbas Kargar
Turkish Journal of Electrical Engineering and Computer Sciences
The present study aims to introduce a robust model for distribution network expansion planning considering system uncertainties. The proposed method determines optimal size and placement of distributed generation resources, as well as installation and reinforcement of feeders and substations. This model is designed to minimize cost and to determine the best time for the installation of equipment in the expansion planning. In the proposed expansion planning, the fuzzy logic theory is employed to model uncertainties of loads and energy price. Also, since the proposed model is a nonlinear and nonconvex optimization problem, a tri-stage algorithm is developed to solve it. …
New Fail Operational Powernet Methods And Topologies For Automated Drivingwith Electric Vehicle, Ahmet Kiliç
New Fail Operational Powernet Methods And Topologies For Automated Drivingwith Electric Vehicle, Ahmet Kiliç
Turkish Journal of Electrical Engineering and Computer Sciences
Electric mobility and automation are important drivers for the future of the automotive industry. Thisrequires an extremely high level of safety, reliability, and efficiency of the energy supply in the vehicle compared to the stateof the art. It is not possible to fulfill these requirements with today's energy supply. To meet these requirements, a fault-operational, scalable powernet is needed. In this paper, a new methodology is presented for the development of powernetfor automated driving with electric vehicle. The new method enables the development of new fail operational powernettopologies, early detection of failures in powernet components and the fulfillment of automated …
A Multiple Sensor Fusion Based Drift Compensation Algorithm For Mecanumwheeled Mobile Robots, Abdurrahman Halabi̇, Mert Ezi̇m, Kansu Oğuz Canbek, Abdurrahman Eray Baran
A Multiple Sensor Fusion Based Drift Compensation Algorithm For Mecanumwheeled Mobile Robots, Abdurrahman Halabi̇, Mert Ezi̇m, Kansu Oğuz Canbek, Abdurrahman Eray Baran
Turkish Journal of Electrical Engineering and Computer Sciences
This paper investigates a multiple sensor fusion based drift compensation technique for a mecanum wheeledmobile robot platform. The mobile robot is equipped with high-precision encoders integrated to the wheels and fouraccelerometers placed on its chassis. The proposed algorithm combines the information from the encoders and theacceleration sensors to estimate the total drift in the acceleration dimension. The inner loop controller is designedutilizing a disturbance-observer-based acceleration control structure which is blind against the slipping motion of thewheels. The estimated drift acceleration from the sensor fusion is then mapped back to the joint space of the robot andused as additional compensation over …
Evaluation Of Mother Wavelets On Steady-State Visually-Evoked Potentials Fortriple-Command Brain-Computer Interfaces, Ebru Sayilgan, Yilmaz Kemal Yüce, Yalçin İşler
Evaluation Of Mother Wavelets On Steady-State Visually-Evoked Potentials Fortriple-Command Brain-Computer Interfaces, Ebru Sayilgan, Yilmaz Kemal Yüce, Yalçin İşler
Turkish Journal of Electrical Engineering and Computer Sciences
Wavelet transform (WT) is an important tool to analyze the time-frequency structure of a signal. The WT relies on a prototype signal that is called the mother wavelet. However, there is no single universal wavelet that fits all signals. Thus, the selection of mother wavelet function might be challenging to represent the signal to achieve the optimum performance. There are some studies to determine the optimal mother wavelet for other biomedical signals; however, there exists no evaluation for steady-state visually-evoked potentials (SSVEP) signals that becomes very popular among signals manipulated for brain-computer interfaces (BCIs) recently. This study aims to explore, …
Simultaneous Feedforward Online Command Rate Limiter Filters For Existingcontrollers, Gali̇p Serdar Tombul
Simultaneous Feedforward Online Command Rate Limiter Filters For Existingcontrollers, Gali̇p Serdar Tombul
Turkish Journal of Electrical Engineering and Computer Sciences
One of the biggest challenges in controller design for a mechatronics system is the actuator limitations. Either response time of the actuator or the input constraints creates limits for the controller performance and stability. In this study a novel feedforward online rate limiter scheme for arbitrary input signals is introduced by taking velocity, acceleration and jerk constraints into account, and it is investigated that how the control effort and system response is affected by the demand signal's rate of change limitations. A fin actuation system for a guided missile is given as an example where the demand signal comes from …
Comparison Of Risc-V And Transport Triggered Architectures For A Postquantumcryptography Application, Lati̇f Akçay, Siddika Berna Örs Yalçin
Comparison Of Risc-V And Transport Triggered Architectures For A Postquantumcryptography Application, Lati̇f Akçay, Siddika Berna Örs Yalçin
Turkish Journal of Electrical Engineering and Computer Sciences
Cryptography is one of the basic phenomena of security systems. However, some of the widely used publickey cryptography algorithms can be broken by using quantum computers. Therefore, many postquantum cryptography algorithms are proposed in recent years to handle this issue. NTRU (Nth degree truncated polynomial ring units) is one of the most important of these quantum-safe algorithms. Besides the importance of cryptography algorithms, the architecture where they are implemented is also essential. In this study, we developed an NTRU public key cryptosystem application and designed several processors to compare them in many aspects. We address two different architectures in this …
Efficient Hybrid Passive Method For The Detection And Localization Of Copy-Moveand Spliced Images, Navneet Kaur, Neeru Jindal, Kulbir Singh
Efficient Hybrid Passive Method For The Detection And Localization Of Copy-Moveand Spliced Images, Navneet Kaur, Neeru Jindal, Kulbir Singh
Turkish Journal of Electrical Engineering and Computer Sciences
Digital passive image forgery methods are extensively used to verify the authenticity and integrity of images.Splicing and copy-move are the most common types of passive digital image forgeries. Several approaches have beenproposed to detect these forgeries separately, but very few approaches are available that can detect them simultaneously.However, a more e?icient method is still in demand to meet the day-to-day challenges to detect these forgeries at thesame time. So, a passive hybrid approach based on discrete fractional cosine transform (DFrCT) and local binarypattern (LBP) is proposed to detect copy-move and splicing forgeries simultaneously. The extra parameter i.e. fractionalparameter of DFrCT …
Chaos In Metaheuristic Based Artificial Intelligence Algorithms:A Short Review, Gökhan Atali, İhsan Pehli̇van, Bi̇lal Gürevi̇n, Hali̇l İbrahi̇m Şeker
Chaos In Metaheuristic Based Artificial Intelligence Algorithms:A Short Review, Gökhan Atali, İhsan Pehli̇van, Bi̇lal Gürevi̇n, Hali̇l İbrahi̇m Şeker
Turkish Journal of Electrical Engineering and Computer Sciences
Metaheuristic based artificial intelligence algorithms are commonly used in the solution of optimization problems. Another area -besides engineering systems- where chaos theory is widely employed is optimization problems. Being applied easily and not trapping in local optima, chaos-based search algorithms have attracted great attention. For example, it has been reported that when random number sequences generated from different chaotic systems are replaced with parameter values in bioinspired and swarm intelligence algorithms, an increase in the performance of metaheuristic algorithms is observed. Many scientific studies on developing hybrid algorithms in which metaheuristic algorithms and chaos theory are used together are already …
Comparative Review Of Disk Type And Unconventional Transverse Flux Machines:Performance Analysis, Erhan Tuncel, Emi̇n Yildiriz
Comparative Review Of Disk Type And Unconventional Transverse Flux Machines:Performance Analysis, Erhan Tuncel, Emi̇n Yildiriz
Turkish Journal of Electrical Engineering and Computer Sciences
Transverse flux machines (TFM) can be designed with high pole numbers, so they are very useful in directdrive systems with high torque density. Although many TFM models have been proposed to date, no detailed classification and comparison has been made before. Conventional TFMs have a high power and torque density, but low power factors and high cogging torques have prevented them from being widely used. However, especially with the new disk type TFMs proposed in recent years and the methods developed, these drawbacks have been reduced. In this paper, the TFMs proposed in recent years have been classified and their …
Bagging Ensemble For Deep Learning Based Gender Recognition Using Test-Timeaugmentation On Large-Scale Datasets, Taner Danişman
Bagging Ensemble For Deep Learning Based Gender Recognition Using Test-Timeaugmentation On Large-Scale Datasets, Taner Danişman
Turkish Journal of Electrical Engineering and Computer Sciences
We present a bagging ensemble of convolutional networks in combination with the test-time augmentation technique to improve performance on the cross-dataset gender recognition problem. The bagging ensemble combines the predictions from multiple homogeneous models into the ensemble prediction. Augmentation techniques are often used in the learning phase of the CNNs to improve the generalization ability. On the other hand, test-time augmentation is not a common method used in the testing phase of the learned model. We conducted experiments on models trained using different hyperparameters. We augmented the test data and combine the predictive outputs from these network models. Experiments performed …
Advanced Single-Loop Discrete-Time Control For T-Type Voltage Source Inverterwith Minimum Capacitor Voltage Ripple Modulation, Manh Linh Nguyen, Phuong Vu
Advanced Single-Loop Discrete-Time Control For T-Type Voltage Source Inverterwith Minimum Capacitor Voltage Ripple Modulation, Manh Linh Nguyen, Phuong Vu
Turkish Journal of Electrical Engineering and Computer Sciences
This research focuses on improving the performance of the voltage source inverter (VSI), which has been widely used in practical applications such as uninterruptible power supply (UPS), photovoltaic (PV) systems in standalone mode. To reduce the total harmonic distortion (THD) of the output voltage without increasing the switching frequency, the T-type three levels inverter with enhanced modulation strategy, which minimizes the voltage ripple of the two input capacitors, is employed. In addition, a new single-loop fully digital control strategy in which various advanced control techniques such as proportional-integral observer, one-step ahead minimum prediction error, and model-based current command generator is …
Prediction Of Long-Term Physical Properties Of Low Density Polyethylene (Ldpe)Cable Insulation Materials By Artificial Neural Network Modeling Approach Underenvironmental Constraints, Ferhat Slimani, Abdallah Hedir, Mustapha Moudoud, Ali̇ Durmuş, Mounir Amir, Mohamed Megherbi
Prediction Of Long-Term Physical Properties Of Low Density Polyethylene (Ldpe)Cable Insulation Materials By Artificial Neural Network Modeling Approach Underenvironmental Constraints, Ferhat Slimani, Abdallah Hedir, Mustapha Moudoud, Ali̇ Durmuş, Mounir Amir, Mohamed Megherbi
Turkish Journal of Electrical Engineering and Computer Sciences
This study quantifies long-term physical properties of low density polyethylene (LDPE) cables insulations exposed to environmental constraints such as UV radiation and temperature via both experimental measurements and mathematical modeling approach. For this purpose, tensile test and electrical breakdown test were carried out to determine elongation at break, tensile strength, and dielectric strength of unaged and aged specimens, respectively. Experimental results showed that both UV and temperature exposures affected the LDPE properties, significantly. A supervised artificial neural network (ANN) trained by the Levenberg?Marquardt algorithm was designed for predicting the long-term characteristics of specimens and also for minimizing the experimental procedures. …
Detection Of Amyotrophic Lateral Sclerosis Disease By Variational Modedecomposition And Convolution Neural Network Methods From Event-Relatedpotential Signals, Fatma Lati̇foğlu, Firat Orhan Bulucu, Rami̇s İleri̇
Detection Of Amyotrophic Lateral Sclerosis Disease By Variational Modedecomposition And Convolution Neural Network Methods From Event-Relatedpotential Signals, Fatma Lati̇foğlu, Firat Orhan Bulucu, Rami̇s İleri̇
Turkish Journal of Electrical Engineering and Computer Sciences
Amyotrophic lateral sclerosis (ALS), also known as motor neuron disease, is a neurological disease that occurs as a result of damage to the nerves in the brain and restriction of muscle movements. Electroencephalography (EEG) is the most common method used in brain imaging to study neurological disorders. Diagnosis of neurological disorders such as ALS, Parkinson's, attention deficit hyperactivity disorder is important in biomedical studies. In recent years, deep learning (DL) models have been started to be applied in the literature for the diagnosis of these diseases. In this study, event-related potentials (ERPs) were obtained from EEG signals obtained as a …
On Performance Analysis Of Multioperator Ran Sharing For Mobile Networkoperators, Yekta Türk, Engi̇n Zeydan
On Performance Analysis Of Multioperator Ran Sharing For Mobile Networkoperators, Yekta Türk, Engi̇n Zeydan
Turkish Journal of Electrical Engineering and Computer Sciences
Enhancing the coverage and eliminating the poor performance is key to balance end-user experience andfuture network investments for mobile network operators (MNOs). Although vast amounts of infrastructure investmentsare provided by MNOs, there are still coverage and capacity planning problems at remote locations. This is because,in most cases, the population density and return-of-investments are low in those areas. In this paper, radio accessnetwork (RAN) sharing paradigm is utilized on experimental sites in Turkey to accommodate user equipment of multiplenetwork operators under the same cell sites. We first investigate characteristics, benefits, and limitations of two differentRAN sharing deployment scenarios. Then, a city-wide …
Engraved Digit Detection Using Hog-Real Adaboost And Deep Neural Network, Tuan Linh Dang, Thang Cao, Yukinobu Hoshino
Engraved Digit Detection Using Hog-Real Adaboost And Deep Neural Network, Tuan Linh Dang, Thang Cao, Yukinobu Hoshino
Turkish Journal of Electrical Engineering and Computer Sciences
This paper proposes a framework for recognizing sequences of digits engraved on steel plates. These digits are normally blurred, dirty, not clear, tilted, and sometimes overlapped by other digits. Several digits in a string with uneven spacing and different sizes are detected at the same time. The framework consists of two main components called histogram of oriented gradient-real AdaBoost module and deep neural network module. The first component is used to detect digit windows, and the second component is employed to recognize digits inside the detected windows. Experimental results demonstrated that the proposed framework could be a potential solution to …
Performance Improvement Of The Shunt Active Power Filter Using A Novel Adaptivefiltering Approach, Abderrezzaq Zoghbi, Daoud Berkani
Performance Improvement Of The Shunt Active Power Filter Using A Novel Adaptivefiltering Approach, Abderrezzaq Zoghbi, Daoud Berkani
Turkish Journal of Electrical Engineering and Computer Sciences
This paper introduces an efficient control approach to enhance harmonics mitigation performance of the shunt active power filter (SAPF). This approach is based on adaptive filters favored by their built-in automatic parameters adaptation capability. The proposed filter, which uses a variable leaky least mean square (VLLMS) adaptation, is applied with a modified instantaneous power PQ theory. This enhances its dynamic performance over the use of conventional time-invariant filters, and overcomes its limitations in the presence of nonsinusoidal voltage conditions. The studied SAPF model is simulated in MATLAB/SIMULINK with combinations of nonlinear and unbalanced loads. Simulation results indicate a significant improvement …
A Counter Based Approach For Reducer Placement With Augmented Hadoop Rackawareness, Mir Wajahat Hussain, K Hemant Reddy, Diptendu Sinha Roy
A Counter Based Approach For Reducer Placement With Augmented Hadoop Rackawareness, Mir Wajahat Hussain, K Hemant Reddy, Diptendu Sinha Roy
Turkish Journal of Electrical Engineering and Computer Sciences
As the data-driven paradigm for intelligent systems design is gaining prominence, performance requirements have become very stringent, leading to numerous fine-tuned versions of Hadoop and its MapReduce programming model. However, very few researchers have investigated the effect of intelligent reducer placement on Hadoop's performance. This paper delves into this much ignored reducer placement phase for improving Hadoop's performance and proposes to spawn reduce phase of Hadoop tasks in an asynchronous fashion across nodes in a Hadoop cluster. The main contributions of this paper are: (i) to track when map phase of tasks are completed, (ii) to count the number of …
Heuristic Based Binary Grasshopper Optimization Algorithm To Solve Unitcommitment Problem, Muhammad Shahid, Tahir Nadeem Malik, Ahsan Said
Heuristic Based Binary Grasshopper Optimization Algorithm To Solve Unitcommitment Problem, Muhammad Shahid, Tahir Nadeem Malik, Ahsan Said
Turkish Journal of Electrical Engineering and Computer Sciences
The unit commitment problem in power system is a highly nonlinear, nonconvex, multiconstrained, complex,highly dimensional, mixed integer and combinatorial generation selection problem. The phenomenon of committing anddecommitting represents a discrete problem that requires binary/discrete optimization techniques to tackle with unitcommitment optimization problem. The key functions of the unit commitment optimization problem involve decidingwhich units to commit and then to decide their optimum power (economic dispatch). This paper confers a binarygrasshopper optimization algorithm to solve the unit commitment optimization problem under multiple constraints.The grasshopper optimization algorithm is a metaheuristic, multiple solutions-based algorithm inspired by the naturalswarming behavior of grasshopper towards food. …
Using Eeg To Detect Driving Fatigue Based On Common Spatial Pattern Andsupport Vector Machine, Li Wang, David Johnson, Yingzi Lin
Using Eeg To Detect Driving Fatigue Based On Common Spatial Pattern Andsupport Vector Machine, Li Wang, David Johnson, Yingzi Lin
Turkish Journal of Electrical Engineering and Computer Sciences
To investigate the correlation between electroencephalogram (EEG) and driving fatigue states, this study used machine learning algorithms to detect driving fatigue based on EEG. 14 channels of EEG data were collected from thirty-four healthy subjects in this research at Northeastern University. Each subject participated in two scenarios (baseline and fatigue scenarios). Subjective ratings of fatigue levels were also obtained from the subjects using the NASA-Task Load Index (TLX). The common spatial pattern (CSP) algorithm was used to extract features from the raw EEG data. The support vector machine (SVM) was used as the classifier in the design of the machine …
Constrained Discrete-Time Optimal Control Of Uncertain Systems With Adaptivelyapunov Redesign, Oğuz Han Altintaş, Ali̇ Emre Turgut
Constrained Discrete-Time Optimal Control Of Uncertain Systems With Adaptivelyapunov Redesign, Oğuz Han Altintaş, Ali̇ Emre Turgut
Turkish Journal of Electrical Engineering and Computer Sciences
In this paper, the conventional estimation-based receding horizon control paradigm is enhanced by using functional approximation, the adaptive modifications on state estimation and convex projection notion from optimization theory. The mathematical formalism of parameter adaptation and uncertainty estimation procedure are based on the redesign of optimal state estimation in discrete-time. By using Lyapunov stability theory, it is shown that the online approximation of uncertainties acting on both physical system and state estimator can be obtained. Moreover, the convergence criteria for online parameter adaptation with fully matched and partially matched cases are presented and shown. In addition, it is shown that …
A New Model For Minimizing The Electric Vehicle Battery Capacity In Electrictravelling Salesman Problem With Time Windows, Kazim Erdoğdu, Korhan Karabulut
A New Model For Minimizing The Electric Vehicle Battery Capacity In Electrictravelling Salesman Problem With Time Windows, Kazim Erdoğdu, Korhan Karabulut
Turkish Journal of Electrical Engineering and Computer Sciences
The growing pollution in the environment and the negative shift in the global climate compel authorities to take action to protect the environment and human health. Transportation is one of the major contributors to this environmental decay. The harmful gases released to the air by the vehicles using petroleum fuel increase each day. One of the solutions is to make a gradual transition to electric vehicles. A major part of manufacturing an electric vehicle is to produce an efficient electric motor and battery for it. Reducing the manufacturing and operating costs of these components will result in reducing the overall …
Development Of Computationally Efficient Biorthogonal Wavelets, Mehmet Cemi̇l Kale
Development Of Computationally Efficient Biorthogonal Wavelets, Mehmet Cemi̇l Kale
Turkish Journal of Electrical Engineering and Computer Sciences
Daubechies 5-tap/3-tap (Daub 5/3) wavelet and Kale 5-tap/3-tap (Kale 5/3) wavelet are computationally efficient wavelets which can be implemented by bitwise shifts and additions in the lifting scheme. In this work, presented is a formulation for computationally efficient wavelet prediction (P) and update (U) filters of two-channel lifting structures. Their subband decomposition scheme counterparts are also given. This research bases itself on the Daub 5/3 and Kale 5/3 wavelets and develops a formula for wavelets (which can be implemented with bitwise shifts and additions) that are derived from these two wavelets. The proposed wavelets are tried on 16 test images …
Deep-Learning-Based Spraying Area Recognition System Forunmanned-Aerial-Vehicle-Based Sprayers, Shahbaz Khan, Muhammad Tufail, Muhammad Tahir Khan, Zubair Ahmed Khan, Shahzad Anwer
Deep-Learning-Based Spraying Area Recognition System Forunmanned-Aerial-Vehicle-Based Sprayers, Shahbaz Khan, Muhammad Tufail, Muhammad Tahir Khan, Zubair Ahmed Khan, Shahzad Anwer
Turkish Journal of Electrical Engineering and Computer Sciences
Unmanned aerial vehicle (UAV)-based spraying system employing machine learning techniques is a recent advancement in precision agriculture for precise spraying, promoting saving chemicals (pesticide/herbicide), and enhancing their effectiveness. This study aims to develop an efficient deep learning system for UAV-based sprayers, which has the capability to accurately recognize spraying areas. A deep learning system is proposed and developed incorporating a faster region-based convolutional neural network (R-CNN) for the imagery collected. In order to develop a classifier for identifying spraying areas from nonspraying areas, four different agriculture croplands and orchards were considered. All the experiments were performed in agriculture fields through …
A Novel Design Of Current Differencing Transconductance Amplifier With Hightransconductance Gain And Enhanced Bandwidth, Shireesh Kumar Rai, Rishikesh Pandey, Bharat Garg, Sujit Patel
A Novel Design Of Current Differencing Transconductance Amplifier With Hightransconductance Gain And Enhanced Bandwidth, Shireesh Kumar Rai, Rishikesh Pandey, Bharat Garg, Sujit Patel
Turkish Journal of Electrical Engineering and Computer Sciences
In this paper, transconductance gain of current differencing transconductance amplifier (CDTA) has been boosted by using a novel approach. Transconductance is generally varied by two well-known techniques. In the first technique, bias current of differential pair MOSFETs is varied whereas in the second technique, aspect ratios of differential pair MOSFETs are changed. The drawbacks of first technique are limited range of transconductance and higher power dissipation whereas second technique restricts dynamic range, output swing and bandwidth of CDTA. To overcome these drawbacks, 2 new structures of CDTA, namely high transconductance gain CDTAs (HTG-CDTA-I & HTG-CDTA-II) have been proposed. HTG-CDTA-I utilizes …
Development Of Majority Vote Ensemble Feature Selection Algorithm Augmentedwith Rank Allocation To Enhance Turkish Text Categorization, Emi̇n Borandağ, Akin Özçi̇ft, Yeşi̇m Kaygusuz
Development Of Majority Vote Ensemble Feature Selection Algorithm Augmentedwith Rank Allocation To Enhance Turkish Text Categorization, Emi̇n Borandağ, Akin Özçi̇ft, Yeşi̇m Kaygusuz
Turkish Journal of Electrical Engineering and Computer Sciences
The increase in the number of texts as digital documents from numerous sources such as customer reviews,news, and social media has made text categorization crucial in order to be able to manage the enormous amount ofdata. The high dimensional nature of these texts requires a preliminary feature selection task to reduce the featurespace with a potential increase in the prediction accuracy. In this study, we developed an ensemble feature selectionmethod, namely majority vote rank allocation, was developed for Turkish text categorization purposes. The methoduses a majority voting ensemble strategy in combination with a rank allocation approach to combine weak filters …
Improvements Of Torque Ripple Reduction In Dtc Im Drive Witharbitrary Number Of Voltage Intensities And Automatic Algorithm Modification, Marko Rosic, Sanja Antic, Milan Bebic
Improvements Of Torque Ripple Reduction In Dtc Im Drive Witharbitrary Number Of Voltage Intensities And Automatic Algorithm Modification, Marko Rosic, Sanja Antic, Milan Bebic
Turkish Journal of Electrical Engineering and Computer Sciences
Techniques of direct torque control (DTC) are very common in high-performance electric motor drives.Retaining the good features of the conventional DTC and reducing torque ripple have been the subject of many years ofresearch work on improving these algorithms. This paper presents the DTC algorithm with discretized voltage vectorsbased on the use of conventional switching table (ST-DTC). This algorithm enables a significant torque ripple reductionby defining the corresponding number of the given voltage intensity while retaining calculation simplicity and fast torqueresponse typical of the ST-DTC algorithms. The proposed algorithm has the ability for its automatic modificationdepending on the defined number of …
Dynamic Distributed Trust Management Scheme For The Internet Of Things, Syed Wasif Abbas Hamdani, Abdul Waheed Khan, Naima Iltaf, Javed Iqbal Bangash, Yawar Abbas Bangash, Asfandyar Khan
Dynamic Distributed Trust Management Scheme For The Internet Of Things, Syed Wasif Abbas Hamdani, Abdul Waheed Khan, Naima Iltaf, Javed Iqbal Bangash, Yawar Abbas Bangash, Asfandyar Khan
Turkish Journal of Electrical Engineering and Computer Sciences
The Internet of Things (IoT) comprises of a diverse network of homogeneous and heterogeneous nodesthat can be accessed through network ubiquitously. In unattended environments, the IoT devices are prone to variousattacks including ballot-stu?ing, bad-mouthing, self-promotion, on-off, opportunistic behavior attacks, etc. The on-offattack is di?icult to detect as nodes switch their behavior from normal to malicious alternatively. A trust managementmodel is a tool to defend the IoT system against malicious activities and provide reliable data exchange. The majorityof existing IoT trust management techniques are based on static reward and punishment values in pursuit of trustcomputation thereby allowing the misbehaving nodes to …
A Novel Pulse Plethysmograph Signal Analysis Method For Identification Of Myocardial Infarction, Dilated Cardiomyopathy, And Hypertension, Muhammad Umar Khan, Sumair Aziz
A Novel Pulse Plethysmograph Signal Analysis Method For Identification Of Myocardial Infarction, Dilated Cardiomyopathy, And Hypertension, Muhammad Umar Khan, Sumair Aziz
Turkish Journal of Electrical Engineering and Computer Sciences
Cardiac diseases (CDs) are one of the leading causes of the growing global mortality rate. Early detectionof CDs is necessary to avoid a high increase in the mortality rate. Machine learning-based computer-aided diagnosisof CDs using various physiological signals has recently been used by researchers. Since pulse plethysmograph (PuPG)signal contains a wealth of information about cardiac pathologies, therefore, this paper presents an expert system designfor the automatic diagnosis of cardiac disorders like hypertension, dilated cardiomyopathy and myocardial infarctionusing a novel fingertip PuPG signal analysis. The proposed system first performs signal denoising of raw PuPG sensordata using discrete wavelet transform (DWT). After …
A Deep Neural Network Classifier For P300 Bci Speller Based On Cohen's Classtime-Frequency Distribution, Hamed Ghazikhani, Modjtaba Rouhani
A Deep Neural Network Classifier For P300 Bci Speller Based On Cohen's Classtime-Frequency Distribution, Hamed Ghazikhani, Modjtaba Rouhani
Turkish Journal of Electrical Engineering and Computer Sciences
This paper presents a new method of predicting the P300 component of an electroencephalography (EEG)signal to recognize the characters in a P300 brain-computer interface (BCI) speller accurately. This method consistsof a deep learning model and the nonlinear time-frequency features. It is believed that the combination of the deepmodel network and extracting the nonlinear features of the EEG led this research to a better prediction of the P300and, therefore, character recognition. Cohen's class distribution is used in order to extract the nonlinear features of theEEG. Evaluating all of the kernels, Butterworth found to be more informative and it produced better results. …