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 2611 - 2640 of 3106
Full-Text Articles in Computer Engineering
Multi-Objective Weighted Sum Approach Model Reduction By Routh-Pade Approximation Using Harmony Search, Hasan Nasiri Soloklo, Malihe Maghfoori Farsangi
Multi-Objective Weighted Sum Approach Model Reduction By Routh-Pade Approximation Using Harmony Search, Hasan Nasiri Soloklo, Malihe Maghfoori Farsangi
Turkish Journal of Electrical Engineering and Computer Sciences
A new weighted-sum multiobjective approach is investigated for order reduction based on Routh--Padé approximation, in which the harmony search algorithm is used to optimize the reduced-order model's parameters. In this method, apart from minimizing the errors between a set of subsequent time moments/Markov parameters of the system and those of the model, the error between the singular values of the reduced-order system and those of the original system is minimized. The Routh criterion is applied for specifying the stability conditions. The stability condition is then considered as a constraint in the optimization problem. To present the ability of the proposed …
Ssr Mitigation With Sssc Thanks To Fuzzy Control, Seyed Mohammad Hassan Hosseini, Hadi Samadzadeh, Javad Olamaei, Murtaza Farsadi
Ssr Mitigation With Sssc Thanks To Fuzzy Control, Seyed Mohammad Hassan Hosseini, Hadi Samadzadeh, Javad Olamaei, Murtaza Farsadi
Turkish Journal of Electrical Engineering and Computer Sciences
This paper deals with the capability of a static synchronous series compensator (SSSC) to attenuate the subsynchronous resonance (SSR). Two well-known controllers are designed, namely a conventional damping controller (CDC) and fuzzy logic damping controller (FLDC). These 2 damping controllers are added to a main control loop of a SSSC operating as a SSR damping controller. It should be noted that, to optimize the parameters of the CDC, a versatile optimization technique is implemented, namely particle swarm optimization (PSO). A comprehensive comparison between the 2 control methods is carried out for different operational conditions. To observe the superior performance of …
Xor-Based Artificial Bee Colony Algorithm For Binary Optimization, Mustafa Servet Kiran, Mesut Gündüz
Xor-Based Artificial Bee Colony Algorithm For Binary Optimization, Mustafa Servet Kiran, Mesut Gündüz
Turkish Journal of Electrical Engineering and Computer Sciences
The artificial bee colony (ABC) algorithm, which was inspired by the foraging and dance behaviors of real honey bee colonies, was first introduced for solving numerical optimization problems. When the solution space of the optimization problem is binary-structured, the basic ABC algorithm should be modified for solving this class of problems. In this study, we propose XOR-based modification for the solution-updating equation of the ABC algorithm in order to solve binary optimization problems. The proposed method, named binary ABC (binABC), is examined on an uncapacitated facility location problem, which is a pure binary optimization problem, and the results obtained by …
Hybrid Spr Algorithm To Select Predictive Genes For Effectual Cancer Classification, Aruna Sundaram, Nandakishore Lellapalli Venkata, Rajagopalan Sarukai Parthasarathy
Hybrid Spr Algorithm To Select Predictive Genes For Effectual Cancer Classification, Aruna Sundaram, Nandakishore Lellapalli Venkata, Rajagopalan Sarukai Parthasarathy
Turkish Journal of Electrical Engineering and Computer Sciences
Designing an automated system for classifying DNA microarray data is an extremely challenging problem because of its high dimension and low amount of sample data. In this paper, a hybrid statistical pattern recognition algorithm is proposed to reduce the dimensionality and select the predictive genes for the classification of cancer. Colon cancer gene expression profiles having 62 samples of 2000 genes were used for the experiment. A gene subset of 6 highly informative genes was selected by the algorithm, which provided a classification accuracy of 93.5%.
Minimal Controller Synthesis Algorithms With Output Feedback And Their Generalization, Ata Sevi̇nç
Minimal Controller Synthesis Algorithms With Output Feedback And Their Generalization, Ata Sevi̇nç
Turkish Journal of Electrical Engineering and Computer Sciences
This paper proposes several improvements in the minimal controller synthesis algorithms, which were developed for a class of nonlinear systems with uncertainties. The major proposition is that only the output feedback is enough to control some nonlinear systems without an observer while the existing algorithms require the complete state feedback. Next, the extended version and the parameter identification technique of the minimal controller synthesis algorithm are combined in a single method estimating some more parameters for some known forms of nonlinearities. This is applicable with or without the improvement of removing the need for using the complete state feedback. It …
Flow Velocity Measurement And Analysis Based On Froth Image Sift Features And Kalman Filter For Froth Flotation, Jinping Liu, Weihua Gui, Zhaohui Tang
Flow Velocity Measurement And Analysis Based On Froth Image Sift Features And Kalman Filter For Froth Flotation, Jinping Liu, Weihua Gui, Zhaohui Tang
Turkish Journal of Electrical Engineering and Computer Sciences
The flow velocity of flotation froth involves important information about the concentrate grade and the mineral recovery. It is significant to maintain the flow velocity of the froth at proper levels to achieve a good production performance in the machine vision-based process monitoring and control. However, the accurate velocity field measurement for the heavily deformed and seriously fragile froth bubbles is still a great challenge. Scale-invariant feature transform (SIFT) feature-based image matching provides an effective registration method for deformed objects, but most of the processing time would be wasted on the feature extraction and matching in irrelevant regions of the …
A Flexible Rule-Based Framework For Pilot Performance Analysis In Air Combat Simulation Systems, Ömer Faruk Arar, Kürşat Ayan
A Flexible Rule-Based Framework For Pilot Performance Analysis In Air Combat Simulation Systems, Ömer Faruk Arar, Kürşat Ayan
Turkish Journal of Electrical Engineering and Computer Sciences
Air combat simulation systems (ACSSs) are developed to train fighter pilots (trainees) in a virtual combat environment. In general, an ACSS consists of the following stages: planning the scenario, training, flight analysis, and performance evaluation. In this paper, the details of the framework, which is developed to analyze and evaluate the performance of the trainees, is introduced. First, the evaluation criteria for the pilot performance are defined. Next, a dynamic pilot performance evaluation system is developed that can be controlled and modified by experienced instructor pilots (instructors/trainers) to define the performance criteria details using predefined evaluation parameters. The evaluation of …
A Video-Based Eye Pupil Detection System For Diagnosing Bipolar Disorder, Gökay Akinci, Edi̇z Polat, Orhan Murat Koçak
A Video-Based Eye Pupil Detection System For Diagnosing Bipolar Disorder, Gökay Akinci, Edi̇z Polat, Orhan Murat Koçak
Turkish Journal of Electrical Engineering and Computer Sciences
Eye pupil detection systems have become increasingly popular in image processing and computer vision applications in medical systems. In this study, a video-based eye pupil detection system is developed for diagnosing bipolar disorder. Bipolar disorder is a condition in which people experience changes in cognitive processes and abilities, including reduced attentional and executive capabilities and impaired memory. In order to detect these abnormal behaviors, a number of neuropsychological tests are also designed to measure attentional and executive abilities. The system acquires the position and radius information of eye pupils in video sequences using an active contour snake model with an …
Identification Of Linear Dynamic Systems Using The Artificial Bee Colony Algorithm, Özden Erçi̇n, Ramazan Çoban
Identification Of Linear Dynamic Systems Using The Artificial Bee Colony Algorithm, Özden Erçi̇n, Ramazan Çoban
Turkish Journal of Electrical Engineering and Computer Sciences
This paper presents an investigation into the development of system identification using the artificial bee colony (ABC) algorithm. A system identification task can be formulated as an optimization problem where the objective is to obtain a model and a set of parameters that minimize the prediction error between the measured plant outputs and the model outputs. The most common existing system identification approaches, such as the recursive least squares method and autoregressive exogenous method, are substantially analytical and based on a mathematical derivation of the system's model. Evolutionary computation, which seems to be a very promising approach, is an alternative …
Compact Dual-Band Split-Ring Antenna For 2.4/5.2 Ghz Wlan Applications, Siddik Cumhur Başaran
Compact Dual-Band Split-Ring Antenna For 2.4/5.2 Ghz Wlan Applications, Siddik Cumhur Başaran
Turkish Journal of Electrical Engineering and Computer Sciences
This paper presents a compact dual-band printed antenna for 2.4/5.2 GHz WLAN applications. The radiating elements of the proposed antenna are composed of rectangular split-ring elements and metallic loadings placed appropriately between the rings. The antenna size is very compact (22 \times 26 \times 1.6 mm), and it can be integrated easily with other RF front-end circuits. It is demonstrated that the proposed antenna can completely cover the required bandwidths of IEEE 802.11b (2.4-2.484 GHz) and IEEE 802.11a (5.15-5.35 GHz) with satisfactory radiation characteristics. Analysis and design of the proposed antenna was carried out with the Ansoft highfrequency structure simulator. …
Forecasting Natural Gas Consumption In İstanbul Using Neural Networks And Multivariate Time Series Methods, Ömer Fahretti̇n Demi̇rel, Seli̇m Zai̇m, Ahmet Çalişkan, Pinar Özuyar
Forecasting Natural Gas Consumption In İstanbul Using Neural Networks And Multivariate Time Series Methods, Ömer Fahretti̇n Demi̇rel, Seli̇m Zai̇m, Ahmet Çalişkan, Pinar Özuyar
Turkish Journal of Electrical Engineering and Computer Sciences
The fast changes and developments in the world's economy have substantially increased energy consumption. Consequently, energy planning has become more critical and important. Forecasting is one of the main tools utilized in energy planning. Recently developed computational techniques such as genetic algorithms have led to easily produced and accurate forecasts. In this paper, a natural gas consumption forecasting methodology is developed and implemented with state-of-the-art techniques. We show that our forecasts are quite close to real consumption values. Accurate forecasting of natural gas consumption is extremely critical as the majority of purchasing agreements made are based on predictions. As a …
New Change Impact Factor Estimation In Software Development, Murat Kahraman Güngör, Ersi̇n Elbaşi, James Walter Fawcett
New Change Impact Factor Estimation In Software Development, Murat Kahraman Güngör, Ersi̇n Elbaşi, James Walter Fawcett
Turkish Journal of Electrical Engineering and Computer Sciences
Change in software is always an essential part of software development and maintenance. Estimating a proposed change's effect on the later phases of the development helps project managers and developers with decision-making and predicting future progress. During development, on some occasions, speedy solutions are necessary to meet project schedules. Such quick changes may lead to major quality flaws in the long term, even though they solve local problems in the short term. Controlled management of change is achieved by being able to estimate the impact of changes. In this paper, we propose a new change impact factor estimation and present …
A Video Encoder Design Combining Edge-Adaptive Lifting And Scalable Block-Matching With Motion Compensation, Sedat Telçeken, Ömer Nezi̇h Gerek
A Video Encoder Design Combining Edge-Adaptive Lifting And Scalable Block-Matching With Motion Compensation, Sedat Telçeken, Ömer Nezi̇h Gerek
Turkish Journal of Electrical Engineering and Computer Sciences
This study aimed to achieve video compression by using a novel lifting-based hybrid encoder that also uses motion compensation. The proposed encoder separates video frames into temporal groups, within which certain frames are selected for producing temporal and spatial predictions over the rest of the frames. The predictions utilize spatiotemporal lifting together with motion compensation. The combination of spatial information with temporal changes is inspired from the idea of edge-adaptive lifting, which alters prediction directions in images. A further incorporation of well-known block-matching methods with different levels was observed to improve the performance. To provide the first compression results, unpredicted …
An Improved Distributed Power-Control Scheme For Cellular Mobile Systems, Hamid Farrokhi, Mostafa Rezayi
An Improved Distributed Power-Control Scheme For Cellular Mobile Systems, Hamid Farrokhi, Mostafa Rezayi
Turkish Journal of Electrical Engineering and Computer Sciences
In this paper, a new distributed power-control (DPC) scheme is suggested to improve convergence speed and system robustness against carrier-to-interference-ratio (CIR) estimation errors. To expedite the CIR balancing in our DPC scheme, an instability detection rule was used. As compared with Foschini's DPC (FDPC) method, numerical results indicated that the proposed algorithm achieves performance improvements in terms of outage probability as well as in the algorithm's convergence speed. More specifically, by appropriate selection of some parameters, the algorithm speed reduces from about 90 iterations in FDPC to 9 iterations in the proposed algorithm. The system robustness against CIR estimation errors …
Tunable Srr-Based Substrate For A Microstrip Patch Antenna, Adnan Sondaş, Mustafa Hi̇kmet Bi̇lgehan Uçar, Yunus Emre Erdemli̇
Tunable Srr-Based Substrate For A Microstrip Patch Antenna, Adnan Sondaş, Mustafa Hi̇kmet Bi̇lgehan Uçar, Yunus Emre Erdemli̇
Turkish Journal of Electrical Engineering and Computer Sciences
In this paper, a microstrip patch antenna over an artificial substrate composed of split-ring resonator (SRR) elements is introduced. As the SRR-based substrate provides miniaturization for the patch, metallic loadings placed between the rings of the SRR elements offer frequency-tuning capability. Practical switch models are employed in lieu of those loadings to demonstrate dynamic control of the operational frequency. The full-wave analysis and design of the proposed tunable patch were carried out using CST Microwave Studio, and the cross-comparisons were provided via Ansoft HFSS. Preliminary measurements are also presented, demonstrating the prospective performance of the proposed design.
Design Parameters And Uncertainty Bound Estimation Functions For Adaptive-Robust Control Of Robot Manipulators, Recep Burkan
Design Parameters And Uncertainty Bound Estimation Functions For Adaptive-Robust Control Of Robot Manipulators, Recep Burkan
Turkish Journal of Electrical Engineering and Computer Sciences
In this paper, a parameter and uncertainty bound estimation functions for adaptive-robust control of robot manipulators are developed. A Lyapunov function is defined and parameters and uncertainty bound estimation functions are developed based on the Lyapunov function. Thus, stability of an uncertain system is guaranteed and uniform boundedness of the tracking error is achieved. As distinct from previous parameter and bound estimation laws, the parameters and uncertainty bounds are updated as a function of a combination of trigonometric function depending on robot parameters and tracking error. Based on the same Lyapunov function, a robust control law is also defined and …
Reconfigurable Antenna Structure For Rfid System Applications Using Varactor-Loading Technique, Yusuf Sevi̇nç, Adnan Kaya
Reconfigurable Antenna Structure For Rfid System Applications Using Varactor-Loading Technique, Yusuf Sevi̇nç, Adnan Kaya
Turkish Journal of Electrical Engineering and Computer Sciences
A novel method is presented for electrically tuning the frequency of a compact radio-frequency identification (RFID) tag antenna. A tuning circuit, comprising a radio frequency (RF) switch and discrete passive components, was completely integrated into the antenna element, which is thus free of DC wires. The low-profile printed antennas were fabricated together with the layouts of the DC control circuits and other RF/baseband circuit footprints. A surface-mounted varactor was applied as a frequency-tuning element at the proper places of the meandered slots in the compact antenna. Prototype designs showed that the in-band frequency (return loss < 10 dB) was tunable from 2.4 GHz to 2.8 GHz when the bias voltage varied from 4 V to 7 V. The impact of the tuning circuit on the antenna's return loss and radiation pattern were experimentally studied through comparison with the performance of a reference antenna not incorporating the tuning circuit. The proposed frequency tuning concept can be extended to more complex compact structures as well as other types of antennas to give enhanced electrical performance.
Research On Cutoff Wavelength Of Dominant Mode And Field Patterns In Trapezoidal Microshield Lines, Hai Sun, Yujiang Wu
Research On Cutoff Wavelength Of Dominant Mode And Field Patterns In Trapezoidal Microshield Lines, Hai Sun, Yujiang Wu
Turkish Journal of Electrical Engineering and Computer Sciences
The influence of the position of the metallic signal strip on the cutoff characteristic of the dominant mode and the field patterns in 3 types of trapezoidal microshield lines are calculated by the edge-based finite element method. These trapezoidal microshield lines include trapezoidal microshield lines with a single signal line, dual signal lines, and 3 signal lines. The cutoff wavelength of the dominant mode can be adjusted by changing the dimensions of metallic signal strips as well as by adjusting their positions. Field patterns of the dominant mode and the first-higher-order mode for different dimensions and the dielectric constant of …
A New Multipath Channel Transformation Technique, Tuğrul Çavdar
A New Multipath Channel Transformation Technique, Tuğrul Çavdar
Turkish Journal of Electrical Engineering and Computer Sciences
A new channel transformation technique is introduced in this paper The technique is employed on the receiver side and has 2 filters. The first filter is the inverse complex conjugate of the estimated channel. The profile of this filter's output is triangular. The taps of the second filter are calculated according to the output of the first filter to produce an exponentially decreasing profile. This technique transforms most channel profiles to exponentially decreasing channel profiles. Thus equalizers adopting the proposed technique may have better bit error rates and lower computational complexity on frequency-selective channels. This paper evaluates the efficiency of …
Study And Control Of 5-Level Pwm Rectifier-5-Level Npc Active Power Filter Cascade Using Feedback Control And Redundant Vectors, Thameur Abdelkrim, El Madjid Berkouk, Karima Benamrane, Tarak Benslimane
Study And Control Of 5-Level Pwm Rectifier-5-Level Npc Active Power Filter Cascade Using Feedback Control And Redundant Vectors, Thameur Abdelkrim, El Madjid Berkouk, Karima Benamrane, Tarak Benslimane
Turkish Journal of Electrical Engineering and Computer Sciences
The purpose of this paper is to develop a control and regulation method for the input DC voltages of a 5-level neutral point clamping (NPC) active power filter (APF). This APF is applied for the enhancement of medium-voltage network power quality by compensation of harmonic currents produced by an induction motor speed variator. In the first part, the authors present a topology of a 5-level NPC voltage source inverter and its simplified space vector pulse width modulation (SVPWM) control strategy. In the second part, the control strategy of the 5-level pulse width modulation current rectifier is presented. In the third …
Effects Of Diacritics On Turkish Information Retrieval, Adi̇l Alpkoçak, Meltem Ceylan
Effects Of Diacritics On Turkish Information Retrieval, Adi̇l Alpkoçak, Meltem Ceylan
Turkish Journal of Electrical Engineering and Computer Sciences
We investigate the effects of improper use of diacritics in the Turkish alphabet on information retrieval. A diacritic is simply a supplementary sign added to a letter to change the sound value of the letter, and the Turkish alphabet has 5 special letters derived from Latin by adding different diacritics. The statistical analysis performed in this study shows that retrieval performance significantly decreases when documents and queries contain letters with different forms, such that documents consist of letters with diacritics while queries consist of standard Latin letters and vice versa. In order to tackle this challenge, we propose 3 approaches: …
An Algorithm For The Detection And Analysis Of Arud Meter In Diwan Poetry, Atakan Kurt, Mehmet Kara
An Algorithm For The Detection And Analysis Of Arud Meter In Diwan Poetry, Atakan Kurt, Mehmet Kara
Turkish Journal of Electrical Engineering and Computer Sciences
Diwan poetry is an important branch of classical Turkish literature (or Ottoman literature) that uses arud meter (wazn AR\footnote{Denotes an Arabic word.} or bahr AR, ölçü TR\footnote{Denotes a Turkish word.}). The teaching of classical poetry in high schools and in literature departments in universities requires an understanding of this meter. Arud is also used in Arabic, Persian, Urdu, and other eastern languages. Determining the arud meter of poems written in the Ottoman language (Osmanlıca TR) is a difficult and tedious task for those who study poetry. In this paper, we focus on the computerized analysis of arud meter. We present …
Localized Power-Aware Routing With An Energy-Efficient Pipelined Wakeup Schedule For Wireless Sensor Networks, Taner Çevi̇k, Abdül Hali̇m Zai̇m, Derya Yiltaş
Localized Power-Aware Routing With An Energy-Efficient Pipelined Wakeup Schedule For Wireless Sensor Networks, Taner Çevi̇k, Abdül Hali̇m Zai̇m, Derya Yiltaş
Turkish Journal of Electrical Engineering and Computer Sciences
Depending on the evolutions in electronics, wireless sensor networks (WSNs) have been very popular in many areas of human life such as health, industry, and military. This popularity has drawn the attention of many researchers toward WSNs. WSNs are especially favorable in conditions in which it is physically difficult and dangerous for human beings to gather information. Therefore, the lifetime of those networks must be as long as possible, since it would also be infeasible to replace the energy-depleted sensors with new ones, as they may be deployed in such geographical areas that are difficult and dangerous for human beings …
Analysis Of Orthogonal Matching Pursuit Based Subsurface Imaging For Compressive Ground Penetrating Radars, Mehmet Ali̇ Çağri Tuncer, Ali̇ Cafer Gürbüz
Analysis Of Orthogonal Matching Pursuit Based Subsurface Imaging For Compressive Ground Penetrating Radars, Mehmet Ali̇ Çağri Tuncer, Ali̇ Cafer Gürbüz
Turkish Journal of Electrical Engineering and Computer Sciences
It is shown that compressive sensing (CS) theory can be used for subsurface imaging in stepped frequency ground penetrating radars (GPR), resulting in robust sparse images, using fewer measurements. Although the data acquisition time is decreased by CS, the computational complexity of the minimization based imaging algorithm is too costly, which makes the algorithm useless, especially for extensive discretization or 3D imaging. In this paper, a greedy alternative, orthogonal matching pursuit (OMP) is used for imaging subsurface and its performance under various conditions is compared to CS imaging method. Results show that OMP could reconstruct sparse signals robustly as well …
Context Gathering And Management For Centralized Context-Aware Handover In Heterogeneous Mobile Networks, Behrouz Shahgholi Ghahfarokhi, Naser Movahhedinia
Context Gathering And Management For Centralized Context-Aware Handover In Heterogeneous Mobile Networks, Behrouz Shahgholi Ghahfarokhi, Naser Movahhedinia
Turkish Journal of Electrical Engineering and Computer Sciences
Context-aware handover decision has recently been considered as a candidate for next-generation heterogeneous wireless networks. The context-aware handover methods proposed in the literature differ in some aspects, including the location of the handover decision (distributed or centralized). Depending on the location of the decision point, the appropriate part of the context knowledge should be transferred in those methods. This paper proposes a context gathering mechanism for a policy-based context-aware handover method, which implements mobile-initiated and network assisted handover. The proposed network context gathering mechanism is based on a media-independent handover (MIH) framework and the paper justifies the usability of the …
Observer Path Design By Imitation Of Competing Constraints For Bearing Only Tracking, Ridvan Gürcan, Mesut Kartal
Observer Path Design By Imitation Of Competing Constraints For Bearing Only Tracking, Ridvan Gürcan, Mesut Kartal
Turkish Journal of Electrical Engineering and Computer Sciences
In the bearing only tracking (BOT) problem the observer tries to estimate the position of the target. The observer maneuver is a requirement to guarantee the uniqueness of the estimation. Determining an observer maneuver for BOT is a difficult problem due to its nonlinear nature. This paper proposes a new method that combines the reference BOT scenarios as a priori knowledge with the incoming bearing measurements to obtain an observer maneuver in a generic optimization framework. The use of a priori knowledge makes the observer maneuver design more realistic. The maneuver recommendation process uses the imitation of competing constraints. In …
Pi And Pid Stabilization Of Neutral And Retarded Systems With Time Delay, Serdar Ethem Hamamci
Pi And Pid Stabilization Of Neutral And Retarded Systems With Time Delay, Serdar Ethem Hamamci
Turkish Journal of Electrical Engineering and Computer Sciences
Stabilization using fixed-order controllers is one of the key topics in control system design for the linear time-invariant (LTI) systems. In this paper, the stabilization of LTI neutral and retarded time-delay systems by means of PI and PID controllers is investigated in detail. The basic theme of the presented approach is to obtain a global stability region in the 2-dimensional (2-D) (k_p, k_i)-plane for the PI controller and in the 3-dimensional (3-D) (k_p, k_i, k_d)-space for the PID controllers. This region is formed by stability boundaries that are defined as the real root boundary, infinite root boundary, and complex root …
Abstract Feature Extraction For Text Classification, Göksel Bi̇ri̇ci̇k, Banu Di̇ri̇, Ahmet Coşkun Sönmez
Abstract Feature Extraction For Text Classification, Göksel Bi̇ri̇ci̇k, Banu Di̇ri̇, Ahmet Coşkun Sönmez
Turkish Journal of Electrical Engineering and Computer Sciences
Feature selection and extraction are frequently used solutions to overcome the curse of dimensionality in text classification problems. We introduce an extraction method that summarizes the features of the document samples, where the new features aggregate information about how much evidence there is in a document, for each class. We project the high dimensional features of documents onto a new feature space having dimensions equal to the number of classes in order to form the abstract features. We test our method on 7 different text classification algorithms, with different classifier design approaches. We examine performances of the classifiers applied on …
Symbolic Regression Of Crop Pest Forecasting Using Genetic Programming, Basim Alhadidi, Alaa Alafeef, Heba Al-Hiari
Symbolic Regression Of Crop Pest Forecasting Using Genetic Programming, Basim Alhadidi, Alaa Alafeef, Heba Al-Hiari
Turkish Journal of Electrical Engineering and Computer Sciences
In this paper, we propose and evaluate a mathematical model that describes the reported data on crop pests to get an accurate prediction of production costs, food safety, and the protection of the environment. Meteorological factors are not the only things that affect a bumper harvest; it is also affected by crop plant diseases and insect pests. Studies show that relying solely on the naked-eye observations of experts to forecast well-planned agriculture is not always sufficient to achieve effective control. Providing fast, automatic, cheap, and accurate artificial intelligence-based solutions for that task can be of great realistic significance. The proposed …
Three-Dimensional Numerical Simulation Of Crystal And Crucible Rotations During Czochralski Growth Of Ge_Xsi_{1-X} Single Crystals, Serkan Abbasoğlu
Three-Dimensional Numerical Simulation Of Crystal And Crucible Rotations During Czochralski Growth Of Ge_Xsi_{1-X} Single Crystals, Serkan Abbasoğlu
Turkish Journal of Electrical Engineering and Computer Sciences
The influence of crystal and crucible rotations on the flow field and the radial segregation of silicon are predicted during the growth of Ge_xSi_{1-x} crystals by the Czochralski method under microgravity conditions. Time-dependent 3-dimensional numerical simulations are carried out to present the influence of several rotation rates on the radial segregation and flow fields during the growth of Ge_xSi_{1-x}. Thermal and solutal Marangoni convection are also considered during this study. Different crystal rotation rates varying between 0 and 30 rpm and stationary or -2 rpm crucible rotation rates are considered. The results show that the crystal and crucible rotation rates …