Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Deep learning (67)
- Classification (66)
- Machine learning (65)
- Optimization (60)
- Genetic algorithm (58)
-
- Particle swarm optimization (50)
- Support vector machine (35)
- Artificial neural network (34)
- Feature extraction (33)
- Wireless sensor networks (31)
- Feature selection (30)
- Power quality (28)
- Artificial neural networks (27)
- Fuzzy logic (26)
- Distributed generation (25)
- Induction motor (24)
- Convolutional neural network (23)
- Clustering (21)
- Support vector machines (20)
- Convolutional neural networks (19)
- Image processing (19)
- Neural networks (19)
- Sliding mode control (19)
- Energy efficiency (18)
- Renewable energy (18)
- Electric vehicle (17)
- Natural language processing (17)
- Neural network (17)
- Reliability (17)
- Adaptive control (16)
- Publication Year
Articles 1231 - 1260 of 3106
Full-Text Articles in Computer Sciences
Ultra Low-Power Dc Voltage Limiter For Rfid Application In 0.18-Μm Cmostechnology, Rezvan Dastanian, Sajad Nejadhasan
Ultra Low-Power Dc Voltage Limiter For Rfid Application In 0.18-Μm Cmostechnology, Rezvan Dastanian, Sajad Nejadhasan
Turkish Journal of Electrical Engineering and Computer Sciences
In this paper, a low-power DC voltage limiter is designed for radio frequency identification tags. In this design, the low-power bandgap reference (BGR) circuit, which is insensitive to temperature, and also the comparator are used for the voltage limiter circuit. To make the I-V curve approach the ideal one, four inverter stages are employed to the output of the comparator. The structure of the BGR and comparator use only MOSFET transistors that work in subthreshold region when the limiter is inactive. These two blocks have power consumption of 220 pW and 1300 pW, respectively. The limited output voltage is 1.5 …
An Optimized Multiobjective Cpu Job Scheduling Using Evolutionary Algorithms, Santhi Venkatraman, Dharshikha Selvagopal
An Optimized Multiobjective Cpu Job Scheduling Using Evolutionary Algorithms, Santhi Venkatraman, Dharshikha Selvagopal
Turkish Journal of Electrical Engineering and Computer Sciences
Scheduling in a multiprocessor parallel computing environment is an NP-hard optimization problem. The main objective of this work is to obtain a schedule in a distributed computing system (DCS) environment that minimizes the makespan and maximizes the throughput. We study the use of two of the evolutionary swarm optimization techniques, the firefly algorithm and the artificial bee colony (ABC) algorithm, to optimize the scheduling in a DCS. We also enhance the traditional ABC algorithm by merging the genetic algorithm techniques of crossover and mutation with the employed bee phase and the onlooker phase, respectively. The resulting enhanced ABC algorithm is …
A Strategy For Improving Netclust Server Placement For Multicloud Environments, Yuting Zhao, Jinhong Liu, Qing Fang, Lifang Xu, Changlai Du, Yuan Xiaoqun
A Strategy For Improving Netclust Server Placement For Multicloud Environments, Yuting Zhao, Jinhong Liu, Qing Fang, Lifang Xu, Changlai Du, Yuan Xiaoqun
Turkish Journal of Electrical Engineering and Computer Sciences
In this paper, we propose a fast server placement algorithm to improve the NetClust framework and make it more efficient and exible. To this end, we introduce hierarchical clustering technologies to the NetClust framework and propose a exible server placement algorithm, which integrates the agglomerative and divisive clustering technologies to reduce the time complexity and avoid the performance uctuation affected by the initial node selection. The experiment results show that our server placement algorithm may reduce the time complexity of server selection of NetClust significantly and improve the exibility and applicability of the NetClust.
Performance Analysis Of Hamming Code For Wsn-Based Smart Grid Applications, Meli̇ke Yi̇ği̇t, Vehbi̇ Çağri Güngör, Pinar Bölük
Performance Analysis Of Hamming Code For Wsn-Based Smart Grid Applications, Meli̇ke Yi̇ği̇t, Vehbi̇ Çağri Güngör, Pinar Bölük
Turkish Journal of Electrical Engineering and Computer Sciences
Many methods have been employed to detect, compare, and correct errors to increase communication reliability and efficiency in wireless sensor networks (WSNs). However, to the best of our knowledge, no existing study has compared the performance of error control codes by using different modulation techniques in a smart grid communication environment when multichannel scheduling is used. This paper presents a detailed performance evaluation and makes a comparison of different modulation techniques, such as frequency shift keying (FSK), differential phase shift keying (DPSK), binary phase shift keying (BPSK), and offset quadrature phase-shift keying (OQPSK), using Hamming codes in a 500-kV line-of-sight …
An Efficient Algorithm To Decompose A Compound Rectilinear Shape Into Simplerectilinear Shapes, Imran Sharif, Debasis Chaudhuri, Naveen Kushwaha, Ashok Samal, Brij Mohan Singh
An Efficient Algorithm To Decompose A Compound Rectilinear Shape Into Simplerectilinear Shapes, Imran Sharif, Debasis Chaudhuri, Naveen Kushwaha, Ashok Samal, Brij Mohan Singh
Turkish Journal of Electrical Engineering and Computer Sciences
Detection of a compound object is a critical problem in target recognition. For example, buildings form an important class of shapes whose recognition is important in many remote sensing based applications. Due to the coarse resolution of imaging sensors, adjacent buildings in the scenes appear as a single compound shape object. These compound objects can be represented as the union of a set of disjoint rectilinear shaped objects. Separating the individual buildings from the resulting compound objects in a segmented image is often difficult but important nevertheless. In this paper we propose a new and efficient technique to decompose a …
A New Method Based On Pixel Density In Salt And Pepper Noise Removal, Uğur Erkan, Levent Gökrem
A New Method Based On Pixel Density In Salt And Pepper Noise Removal, Uğur Erkan, Levent Gökrem
Turkish Journal of Electrical Engineering and Computer Sciences
In this paper, we deliver a new method to remove salt and pepper noise, which we refer to as based on pixel density filter (BPDF). The first step of the method is to determine whether or not a pixel is noisy, and then we decide on an adaptive window size that accepts the noisy pixel as the center. The most repetitive noiseless pixel value within the window is set as the new pixel value. By using 18 test images, we give the results of peak signal-to-noise ratio (PSNR), structural similarity (SSIM), image enhancement factor (IEF), standard median filter (SMF), adaptive …
Blood Glucose Control Using An Abc Algorithm-Based Fuzzy-Pid Controller, Seli̇m Soylu, Kenan Danişman
Blood Glucose Control Using An Abc Algorithm-Based Fuzzy-Pid Controller, Seli̇m Soylu, Kenan Danişman
Turkish Journal of Electrical Engineering and Computer Sciences
In this paper, a Mamdani-type fuzzy controller is proposed as the controller part of an artificial pancreas. The controller is optimized with the artificial bee colony optimization algorithm. The glucose{insulin regulatory system, based on a nonlinear differential model in the presence of delay, is used both for virtual patient and healthy person data. The main target of the controller is to mimic a blood glucose concentration profile of the healthy person with exogenous insulin infusion. Simulations are performed to assess the control function in terms of tracking the blood glucose concentration profile of the healthy person and minimizing errors. To …
Signal Processing In Recursive Rejection Filters In The Transient Mode, Dmitrii Popov, Sergey Smolskiy
Signal Processing In Recursive Rejection Filters In The Transient Mode, Dmitrii Popov, Sergey Smolskiy
Turkish Journal of Electrical Engineering and Computer Sciences
A recursive rejection filter (REF) oriented to the radar signal extraction from the moving targets on a background of passive interference in the form of undesired re ections from fixed or slowly moving objects (so-called clutter) is the object under investigation. By means of the state variable method, which gives the adequate filter description in the time domain, the REF structure in the transient mode is synthesized, which is improved with the aim of transient acceleration with the clutter edge arriving. The REF structure's improvement in the transient mode is achieved by its reconfiguration, which is made by REF output …
Last Level Cache Partitioning Via Multiverse Thread Classification, Burak Sezi̇n Ovant, İsa Ahmet Güney, Muhammed Emi̇n Savaş, Gürhan Küçük
Last Level Cache Partitioning Via Multiverse Thread Classification, Burak Sezi̇n Ovant, İsa Ahmet Güney, Muhammed Emi̇n Savaş, Gürhan Küçük
Turkish Journal of Electrical Engineering and Computer Sciences
Last level caches (LLCs) are part of the last line of defense against the famous memory wall problem. Today, almost all processors utilize a LLC for the same reason. This study extends our previous work, which proposed a cache-partitioning mechanism using thread classification. Here, we propose three enhancements to the existing system: 1) an adaptive traffic threshold mechanism for more portable classification hardware, 2) a new method for classifying way-hungry threads, and finally, 3) a thorough comparison of two design alternatives. Compared to the original way- partitioning mechanism, we show that the proposed mechanism's performance improved by around 6%, on …
Weighted Intensity Hue Saturation Transform For Image Enhancement Andpansharpening, Nur Hüseyi̇n Kaplan
Weighted Intensity Hue Saturation Transform For Image Enhancement Andpansharpening, Nur Hüseyi̇n Kaplan
Turkish Journal of Electrical Engineering and Computer Sciences
In this paper, a weighted intensity hue saturation transform (WIHS) is proposed for image enhancement and pansharpening. The proposed transform obtains the intensity component of the classical intensity hue saturation (IHS) transform, by weighting the bands (red, green, and blue) of the image, whereas the hue and saturation components remain unchanged. The weight for each band is determined according to the brightness interval of the corresponding band and its standard deviation. The purpose of obtaining the intensity component by weighting is to keep more information from the bands of the input image. The classical intensity component used in image processing …
Decoupled Indirect Duty Cycle Pwm Technique With Carrier Frequency Adjustmentfor A Matrix Converter, Murugesan Kullan, Senthilkumaran Mahadevan, Anitha Roseline Johnson, Ranganath Muthu
Decoupled Indirect Duty Cycle Pwm Technique With Carrier Frequency Adjustmentfor A Matrix Converter, Murugesan Kullan, Senthilkumaran Mahadevan, Anitha Roseline Johnson, Ranganath Muthu
Turkish Journal of Electrical Engineering and Computer Sciences
The conventional sinusoidal pulse width modulation (SPWM) and the space vector PWM (SVPWM) switching techniques are widely used for power converters due to their ability to control the harmonic content of the output voltage. The most popular PWM techniques used in matrix converters are direct space vector modulation (DSVM) and indirect space vector modulation (ISVM). Since these techniques are complex and difficult to implement, there is demand for a PWM technique with minimum computation to operate matrix converters continuously. In this paper, decoupled indirect duty cycle (DIDC) PWM technique is proposed for the conventional matrix converter (CMC). This technique eliminates …
Outputs Bounds For Linear Systems With Repeated Input Signals: Existence,Computation And Application To Vehicle Platooning, Harun Buğra Sağlam, Klaus Werner Schmi̇dt
Outputs Bounds For Linear Systems With Repeated Input Signals: Existence,Computation And Application To Vehicle Platooning, Harun Buğra Sağlam, Klaus Werner Schmi̇dt
Turkish Journal of Electrical Engineering and Computer Sciences
This paper investigates the effect of repeated time-limited input signals on the output excursion of stable, linear time-invariant systems. It is first shown that the maximum norm of the output signal remains bounded if the repeated input signals are separated by a nonzero dwell time. Then a novel method for computing a tight bound on the output signal norm is proposed. The setting of the paper is motivated by a vehicle platooning application, where vehicles repeatedly open/close gaps in order to perform lane changes. The developed method analyzes driving safety by computing a bound on the spacing error between vehicles …
Model Reduction Of Discrete-Time Systems In Limited Intervals, Umair Zulfiqar, Muwahida Liaquat
Model Reduction Of Discrete-Time Systems In Limited Intervals, Umair Zulfiqar, Muwahida Liaquat
Turkish Journal of Electrical Engineering and Computer Sciences
Model order reduction (MOR) is a process of obtaining a lower order surrogate model that accurately approximates the original high-order system. Since no actuator or plant operates over the entire time and frequency ranges, the reduced-order model should be accurate in the actual range of operation. In this paper, model reduction techniques for discrete time systems are presented that ensure less reduction error in the specified time and frequency intervals. The techniques are tested on the benchmark numerical examples and their efficacy is shown.
Determination Of Harmonic Current Contributions Based On Robust State Estimation, Erhan Sezgi̇n, Murat Göl, Özgül Salor
Determination Of Harmonic Current Contributions Based On Robust State Estimation, Erhan Sezgi̇n, Murat Göl, Özgül Salor
Turkish Journal of Electrical Engineering and Computer Sciences
In this paper, a state estimation based method is proposed to determine harmonic current contributions of plants supplied from a point of common coupling (PCC). This work mainly aims to reduce gross error of capacitive voltage transformer (CVT) measurements at harmonic frequencies using robust weighted least absolute value (WLAV) state estimation method, which provides the optimum state estimates for harmonic voltages in the presence of a redundant enough measurement set. Estimated harmonic voltages are then used to solve the harmonic current contribution problem based on superposition theorem. It has been shown that the proposed method can provide optimum harmonic estimates …
Technoeconomic Analysis Of A Grid-Connected Pv And Battery Energy Storagesystem Considering Time Of Use Pricing, Chinmay Kumar Nayak, Manas Ranjan Nayak
Technoeconomic Analysis Of A Grid-Connected Pv And Battery Energy Storagesystem Considering Time Of Use Pricing, Chinmay Kumar Nayak, Manas Ranjan Nayak
Turkish Journal of Electrical Engineering and Computer Sciences
This paper examines the technoeconomic optimization of the size of valve-regulated lead acid-type battery energy storage systems (BESSs) in order to minimize the total annual operating cost of a grid-connected photovoltaic BESS within the framework of system operational constraints, using the improved harmony search algorithm. The electricity cost is calculated using time of use pricing, where the price of energy varies according to the load demand. The concept of feed-in-tariff is discussed, where power can be bought from and sold back to the grid. A sensitivity analysis is performed for three cases: without storage, with storage and without peak load …
Two-Area Load Frequency Control With Redox Ow Battery Using Intelligentalgorithms In A Restructured Scenario, Lakshmi Dhandapani, Fathima Peer, Ranganath Muthu
Two-Area Load Frequency Control With Redox Ow Battery Using Intelligentalgorithms In A Restructured Scenario, Lakshmi Dhandapani, Fathima Peer, Ranganath Muthu
Turkish Journal of Electrical Engineering and Computer Sciences
Load frequency control (LFC) is an essential aspect of power system dynamics. This paper focuses on the optimization of LFC for a two-area deregulated power system under different scenarios. A recent nature-inspired ower pollination algorithm (FPA), based on the pollination process of plants, is used to tune the proportional integral (PI) controller parameters of LFC for the global minima solution. FPA is compared with a genetic algorithm, particle swarm optimization, and a conventional PI controller. During large load disturbance in the areas, controllers are incapable of reducing frequency deviations and tie-line power oscillations due to the slow response of the …
Supercapacitor Utilization For Power Smoothening And Stability Improvement Of Ahybrid Energy System In A Weak Grid Environment, Rahul Sharma, Sathans Suhag
Supercapacitor Utilization For Power Smoothening And Stability Improvement Of Ahybrid Energy System In A Weak Grid Environment, Rahul Sharma, Sathans Suhag
Turkish Journal of Electrical Engineering and Computer Sciences
In this paper, a novel control scheme based on the application of a supercapacitor (SC) is proposed for power smoothening and stability improvement of a hybrid energy system (HES) in weak grid conditions. The basic property of fast charging/discharging of the SC is utilized to design the proposed control. In weak grid conditions, the control structure is proposed for power smoothening and DC link voltage regulation with the help of the SC. Moreover, the stability is increased, ripples in voltage are reduced, there is fast dynamic response, and oscillations are damped out under different conditions. In conventional control, voltage controller …
Model-Free Approach Based On Intelligent Pd Controller For Vertical Motionreduction In Fast Ferries, Mounia Ticherfatine, Zhu Qidan
Model-Free Approach Based On Intelligent Pd Controller For Vertical Motionreduction In Fast Ferries, Mounia Ticherfatine, Zhu Qidan
Turkish Journal of Electrical Engineering and Computer Sciences
A new model-free approach was investigated to control two moving aps and a T-foil of a fast ferry traveling in the head sea. Considered as a highly perturbed system, fast ferries in sea waves suffer from the undesirable effects of pitch and heave motions causing severe vertical accelerations that lead to the discomfort of passengers who then experience seasickness. To appropriately control this multivariable system, a model-free control strategy was adopted. An augmented PD controller with compensating terms resulting from an online identification of an ultralocal model of the system was designed. Relying only on input{output data and using online …
Fragment-Based Transmission Using Minimum Power Consumed Routing(Fbtmpcr) Algorithm Of A Mimo Integrated Manet, Swati Chowdhuri, Pranab Banerjee, Sheli Sinha Chaudhury
Fragment-Based Transmission Using Minimum Power Consumed Routing(Fbtmpcr) Algorithm Of A Mimo Integrated Manet, Swati Chowdhuri, Pranab Banerjee, Sheli Sinha Chaudhury
Turkish Journal of Electrical Engineering and Computer Sciences
The establishment of an efficient broadcast routing technique in a multiple input multiple output (MIMO)- based mobile ad hoc network is a challenge in wireless communication. MIMO configuration provides enhancement of data throughput even under conditions of interference and multipath fading. Improvement of transmission efficiency by increasing saturation throughput, reducing transmission delay, and minimizing bit error rate is the main motivation of the present work. In this paper a hybrid routing algorithm, fragment-based transmission using minimum power consumed routing, has been developed. It is an integration of the cooperative transmission process and fragmentation of packet payload. The routing algorithm is …
Modified Stacking Ensemble Approach To Detect Network Intrusion, Necati̇ Demi̇r, Gökhan Dalkiliç
Modified Stacking Ensemble Approach To Detect Network Intrusion, Necati̇ Demi̇r, Gökhan Dalkiliç
Turkish Journal of Electrical Engineering and Computer Sciences
Detecting intrusions in a network traffic has remained an issue for researchers over the years. Advances in the area of machine learning provide opportunities to researchers to detect network intrusion without using a signature database. We studied and analyzed the performance of a stacking technique, which is an ensemble method that is used to combine different classification models to create a better classifier, on the KDD'99 dataset. In this study, the stacking method is improved by modifying the model generation and selection techniques and by using different classifications algorithms as a combiner method. Model generation is performed using subsets of …
Improving The Incremental Conductance Algorithm For Two-Stage Grid-Connectedphotovoltaic Systems, Mehmet Ali̇ Özçeli̇k, Ahmet Serdar Yilmaz
Improving The Incremental Conductance Algorithm For Two-Stage Grid-Connectedphotovoltaic Systems, Mehmet Ali̇ Özçeli̇k, Ahmet Serdar Yilmaz
Turkish Journal of Electrical Engineering and Computer Sciences
Efficiency of solar photovoltaic generation plants depends not only on internal operational conditions but also on external atmospheric conditions. Total efficiency is in uenced by various weather conditions such as cloudiness, temperature, and irradiation. In order to generate maximum energy, photovoltaic (PV) arrays should be operated at their maximum power point (MPP), varying external factors like partial shading and surface temperature and amount of radiation coming from the sun. In modern PV systems, maximum power point trackers (MPPTs) have been used in order to reach the MPP, changing with the factors given above. MPPT units are implemented to control DC-DC …
Comparative Analysis Of Different Cooling Fin Types For Countering Led Luminaires'heat Problems, Canan Karateki̇n, Oytun Kökkaya
Comparative Analysis Of Different Cooling Fin Types For Countering Led Luminaires'heat Problems, Canan Karateki̇n, Oytun Kökkaya
Turkish Journal of Electrical Engineering and Computer Sciences
A significant problem with high-power LED luminaires is heat. Aluminum heat sinks have been extensively used as a solution. The most common method for heat sinks that increases surface area uses fins. In the present study, pin- and plate-fins were compared and it was observed that, in equal surface areas, better cooling was achieved by pin-fins. Thus, the study's concentration narrowed to pin-fins and the results of different pin-fins were compared. Simulations of a sample group were conducted by using different numbers of fins, and the number of fins giving the lowest Tmax value (the highest junction point temperature) was …
Extra High Voltage Transmission Line Operation Simulation Using The Actualcorona-Loss Characteristics, Ashraf Balametov, Elman Halilov, Tarana Isayeva
Extra High Voltage Transmission Line Operation Simulation Using The Actualcorona-Loss Characteristics, Ashraf Balametov, Elman Halilov, Tarana Isayeva
Turkish Journal of Electrical Engineering and Computer Sciences
In transmission line equations with distributed parameters, corona power losses are represented as conduc- tivity, i.e. corona losses considered as a function of the line voltage squared. On the other hand, valid corona power losses are 4-8 degree functions from voltage. Therefore, extra high voltage transmission line equations with the distributed parameters have methodical errors. Methodical errors of extra high voltage transmission line operation mode parame- ters modeling are estimated. The method of modeling extra high voltage transmission line operation mode taking into account actual corona-loss characteristics is offered. The cascade-connected scheme is used for increasing the accuracy of modeling …
Two-Stage Optimization Method For Power Loss And Voltage Profile Control Indistribution Systems With Dgs And Evs Using Stochastic Second-Order Coneprogramming, Huiling Tang, Jiekang Wu, Zhijiang Wu, Lingmin Chen
Two-Stage Optimization Method For Power Loss And Voltage Profile Control Indistribution Systems With Dgs And Evs Using Stochastic Second-Order Coneprogramming, Huiling Tang, Jiekang Wu, Zhijiang Wu, Lingmin Chen
Turkish Journal of Electrical Engineering and Computer Sciences
This paper introduces a stochastic second-order cone programming (SSCOP) approach to solve the distributed generation coordination problem considering the uncertainty of electric vehicle charging in distribution networks. To minimize the total power loss in the distribution system, the problem is formulated to coordinate the output power of distributed generations (DGs). Two stages are presented to solve the optimization problem: the first stage is to optimize the output power of distributed generators without electric vehicle charging in the distribution system, and the second stage is to optimize the output power of distributed generators according to the stochastic increased load due to …
A Novel Perturbed Particle Swarm Optimization-Based Support Vector Machine Forfault Diagnosis In Power Distribution Systems, Hoang Thi Thom, Cho Ming-Yuan, Vu Quoc Tuan
A Novel Perturbed Particle Swarm Optimization-Based Support Vector Machine Forfault Diagnosis In Power Distribution Systems, Hoang Thi Thom, Cho Ming-Yuan, Vu Quoc Tuan
Turkish Journal of Electrical Engineering and Computer Sciences
In this paper, a novel perturbed particle swarm optimization (PPSO) algorithm is investigated to improve the performance of a support vector machine (SVM) for short-circuit fault diagnosis in power distribution systems. In the proposed PPSO algorithm, the velocity of each particle is perturbed whenever the particles strike into a local optimum, in order to achieve a higher quality solution to optimization problems. Furthermore, the concept of proposed perturbation is applied to three variants of PSO, and improved corresponding algorithms are named perturbed C-PSO (PC-PSO), perturbed T-PSO (PT-PSO), and perturbed K-PSO (PK-PSO). For the purpose of fault diagnosis, the time- domain …
Resolving Namesakes Using The Author's Social Network, Ijaz Hussain, Sohail Asghar
Resolving Namesakes Using The Author's Social Network, Ijaz Hussain, Sohail Asghar
Turkish Journal of Electrical Engineering and Computer Sciences
Author name ambiguity may occur when multiple authors share the same name or different name variations of a single author exist. This degrades search results and correct attributions in bibliographic databases. Existing solutions require either the actual number of ambiguous authors or extra information that is collected from the Web. However, in many scenarios, obtaining such auxiliary information is not possible or requires much extra effort. An effective and scalable method, ASONET, is proposed that uses graph community detection algorithms and graph operations to disambiguate namesakes. The citation dataset is preprocessed and ambiguous author blocks are formed. A graph structural …
Tempest Font Counteracting A Noninvasive Acquisition Of Text Data, Ireneusz Kubiak
Tempest Font Counteracting A Noninvasive Acquisition Of Text Data, Ireneusz Kubiak
Turkish Journal of Electrical Engineering and Computer Sciences
The protection of information against electromagnetic penetration has huge significance. Different solutions, technological or organizational, are used to protect the information-limiting levels of unintentional emissions. In particular, technological solutions are implemented in commercial devices to limit levels of electromagnetic emissions. Nevertheless, such solutions cannot always be used. This is connected with the construction of these devices. Very often the devices do not have enough space on the inside to install new elements such as filters, electromagnetic shielding, and others. In the paper a new solution is proposed. The solution does not change the construction of the devices (e.g., printers, screens). …
Demial: An Active Learning Framework For Multiple Instance Image Classificationusing Dictionary Ensembles, Gökhan Koçyi̇ği̇t, Yusuf Yaslan
Demial: An Active Learning Framework For Multiple Instance Image Classificationusing Dictionary Ensembles, Gökhan Koçyi̇ği̇t, Yusuf Yaslan
Turkish Journal of Electrical Engineering and Computer Sciences
In many machine-learning applications, each data point can be represented as a set of instances that create multiple instance learning (MIL) problems. Due to the structure of images, different regions can be interpreted as instances. Thus, multiple instances can be obtained for each image, which makes image categorization a MIL problem. With abundant unlabeled image data, this MIL problem can be solved using active learning algorithms. Active learning is a framework that utilizes unlabeled data in which labeling samples is a labor-intensive and expensive task. Although many effective MIL active learning methods have been developed, most of the existing algorithms …
An Elitist Approach For Solving The Traveling Salesman Problem Using An Animalmigration Optimization Algorithm, Ezgi̇ Ülker
An Elitist Approach For Solving The Traveling Salesman Problem Using An Animalmigration Optimization Algorithm, Ezgi̇ Ülker
Turkish Journal of Electrical Engineering and Computer Sciences
This paper presents an improved version of the animal migration optimization (AMO) algorithm for solving the traveling salesman problem (TSP), which is classified as a combinatorial NP-hard problem. AMO is one of the recent metaheuristic algorithms inspired by the migration behavior of animals and has been efficiently applied to a variety of optimization problems. The algorithm is improved by reconstructing the neighborhood topology of each animal during the migration. This modified algorithm is called the elitist animal migration optimization (ELAMO) algorithm, since elitism is introduced as a way in which the positions of the leaders are considered for the neighborhood …
Multiobjective Aerodynamic Optimization Of A Microscale Ducted Wind Turbineusing A Genetic Algorithm, Emre Alpman
Multiobjective Aerodynamic Optimization Of A Microscale Ducted Wind Turbineusing A Genetic Algorithm, Emre Alpman
Turkish Journal of Electrical Engineering and Computer Sciences
A two-objective aerodynamic optimization of a microscale ducted wind turbine was performed using a genetic algorithm. Two different fitness function pairs were considered for this purpose. In the first alternative the algorithm maximized the power produced while minimizing the drag force at a given wind speed and tip speed ratio. In the second alternative, however, the annual energy production was maximized while minimizing the maximum drag force developed between the cut-in and cut-off wind speeds. Computational uid dynamics solutions performed for selected best designs showed that optimizations performed using the second alternative yielded better turbines, which could produce more power …