Open Access. Powered by Scholars. Published by Universities.®

Engineering Commons™

Open Access. Powered by Scholars. Published by Universities.®

Discipline
Institution
Keyword
Publication Year
Publication
Publication Type
File Type

Articles 39211 - 39240 of 196033

Full-Text Articles in Engineering

Batchlens: A Visualization Approach For Analyzing Batch Jobs In Cloud Systems, Shaolun Ruan, Yong Wang, Hailong Jiang, Weijia Xu, Qiang. Guan Mar 2022

Batchlens: A Visualization Approach For Analyzing Batch Jobs In Cloud Systems, Shaolun Ruan, Yong Wang, Hailong Jiang, Weijia Xu, Qiang. Guan

Research Collection School Of Computing and Information Systems

Cloud systems are becoming increasingly powerful and complex. It is highly challenging to identify anomalous execution behaviors and pinpoint problems by examining the overwhelming intermediate results/states in complex application workflows. Domain scientists urgently need a friendly and functional interface to understand the quality of the computing services and the performance of their applications in real time. To meet these needs, we explore data generated by job schedulers and investigate general performance metrics (e.g., utilization of CPU, memory and disk I/O). Specifically, we propose an interactive visual analytics approach, BatchLens, to provide both providers and users of cloud service with an …

Go to article

Investigations On Cogging Torque Mitigation Techniques Of Transverse Flux Motorfor Direct Drive Low-Speed Spacecraft Applications, Ravichandran Mh, Venkatakirthiga Murali, Haridas Tr Mar 2022

Investigations On Cogging Torque Mitigation Techniques Of Transverse Flux Motorfor Direct Drive Low-Speed Spacecraft Applications, Ravichandran Mh, Venkatakirthiga Murali, Haridas Tr

Turkish Journal of Electrical Engineering and Computer Sciences

The transverse flux motor (TFM) is an ideal choice for direct drive high torque applications owing to its proven higher torque density compared to the radial flux and axial flux motors. TFM motors have several merits to be used for spacecraft applications, considering the everlasting demand of the industry for reduction in power and mass. This paper investigates the various cogging torque mitigation techniques for transverse flux motor to be effectively used as the drive motor for precise position control spacecraft requirement. The paper discusses the basic design variables of surface mounted TFM (SM-TFM) that are to be considered for …

Go to article

Independent Closed Loop Control Of Di/Dt And Dv/Dt For High Power Igbts, Osman Tanriverdi̇, Deni̇z Yildirim Mar 2022

Independent Closed Loop Control Of Di/Dt And Dv/Dt For High Power Igbts, Osman Tanriverdi̇, Deni̇z Yildirim

Turkish Journal of Electrical Engineering and Computer Sciences

As the insulated gate bipolar transistor (IGBT) modules have their own specific characteristic switching forms, their turn-on and turn-off times are changed according to practical applications. For the conventional gate drives, gate resistors are used to adjust the turn-on and turn-off times which change switching losses that have a significant amount in total losses. Collector current rate of change, $di_{C}/ dt$ and collector-emitter rate of change, $dv_{CE}/ dt$ are dependent on each other and they affect operating parameters in high power converters. Relations between current and voltages during the switching transitions are given and effects of the changes in electrical …

Go to article

Cryptographically Strong Random Number Generation Using Integrated Cmosphotodiodes For Low-Cost Microcontroller Based Applications, Baykal Sarioğlu Mar 2022

Cryptographically Strong Random Number Generation Using Integrated Cmosphotodiodes For Low-Cost Microcontroller Based Applications, Baykal Sarioğlu

Turkish Journal of Electrical Engineering and Computer Sciences

In this work, we propose a method to generate random numbers for low-cost, low-power, resource-limited low data-rate microcontrollers using integrated CMOS photodiodes. The proposed method utilizes an integrated CMOS photodiode in the photovoltaic mode as the entropy source. The method is based on serially capturing analog values derived from the integrated CMOS photodiode. The entropy of these values increased by a custom algorithm. The proposed random number generator is devised using an integrated CMOS photodiode manufactured in 180 nm standard CMOS technology. The wide applicably of the random number generator is demonstrated by realizing it on a lowcost Arduino UNO …

Go to article

Clustering With Density Based Initialization And Bhattacharyya Based Merging, Erdem Köse, Ali̇ Köksal Hocaoğlu Mar 2022

Clustering With Density Based Initialization And Bhattacharyya Based Merging, Erdem Köse, Ali̇ Köksal Hocaoğlu

Turkish Journal of Electrical Engineering and Computer Sciences

Centroid based clustering approaches, such as k-means, are relatively fast but inaccurate for arbitrary shape clusters. Fuzzy c-means with Mahalanobis distance can accurately identify clusters if data set can be modelled by a mixture of Gaussian distributions. However, they require number of clusters apriori and a bad initialization can cause poor results. Density based clustering methods, such as DBSCAN, overcome these disadvantages. However, they may perform poorly when the dataset is imbalanced. This paper proposes a clustering method, named clustering with density initialization and Bhattacharyya based merging based on the fuzzy clustering. The initialization is carried out by density estimation …

Go to article

Long-Term Traffic Flow Estimation: A Hybrid Approach Using Location-Basedtraffic Characteristic, Tuğberk Ayar, Ferhat Atli̇nar, Mehmet Amaç Güvensan, Hafi̇za İrem Türkmen Mar 2022

Long-Term Traffic Flow Estimation: A Hybrid Approach Using Location-Basedtraffic Characteristic, Tuğberk Ayar, Ferhat Atli̇nar, Mehmet Amaç Güvensan, Hafi̇za İrem Türkmen

Turkish Journal of Electrical Engineering and Computer Sciences

Traffic speed estimation plays a key role in various situations, ranging from individual's trip planning to urban traffic management. Despite many studies on short-term prediction, there is only a limited number of studies focusing on long-term prediction and only a couple of them does go beyond 24 h. On the contrary, this study presents a novel hybrid architecture using location-based traffic characteristic for traffic speed estimation up to 7 days. In this architecture, the introduced mean filtering estimation (MFE) model and long short-term memory (LSTM) neural network are jointly utilized for minimizing the error for traffic flow estimation. Both MFE …

Go to article

Calculating Influence Based On The Fusion Of Interest Similarity And Informationdissemination Ability, Shulin Cheng, Ziming Wang, Meng Qian, Shan Yang, Xin Zheng Mar 2022

Calculating Influence Based On The Fusion Of Interest Similarity And Informationdissemination Ability, Shulin Cheng, Ziming Wang, Meng Qian, Shan Yang, Xin Zheng

Turkish Journal of Electrical Engineering and Computer Sciences

With the popularization, in-depth development and application of the Internet, microblogs have become a mainstream social network platform. Several studies on social networks have conducted researches, and user influence evaluation is an important research hotspot. Most of the existing studies calculate user influence by improving PageRank and have achieved certain results. However, these studies ignored the fusion of users' interest theme similarity and information dissemination ability, and the analysis of interaction behaviors among users is not comprehensive. To address these issues, we propose a new microblog user influence algorithm called microblog user influence based on interest similarity and information dissemination …

Go to article

Photonic Integrated Circuit-Assisted Optical Time-Domainreflectometer System, Mehmet Cengi̇z Onbaşli Mar 2022

Photonic Integrated Circuit-Assisted Optical Time-Domainreflectometer System, Mehmet Cengi̇z Onbaşli

Turkish Journal of Electrical Engineering and Computer Sciences

Optical time-domain reflectometers (OTDR) are photonic systems that consist of an interrogator, a receiver and a fiber optical cable and have applications in telecommunications, security, environmental monitoring, distributed temperature and strain sensing. Since OTDR systems are bulk optical setups that consume multiple Watts of power, have large mass and volume footprint and are vulnerable to thermal drift, deployment of OTDR systems in the field is expensive, complicated and may not necessarily yield accurate sensing results. Thus, a compact, low-power, inexpensive and thermal drift-free OTDR system needs to be developed for improving the accuracy and the viability of OTDR in the …

Go to article

Privacy Preserving Scheme For Document Similarity Detection, Ayad Abdulsada, Salah Al-Darraji, Dhafer Honi Mar 2022

Privacy Preserving Scheme For Document Similarity Detection, Ayad Abdulsada, Salah Al-Darraji, Dhafer Honi

Turkish Journal of Electrical Engineering and Computer Sciences

The problem of detecting similar documents plays an essential role for many real-world applications, such as copyright protection and plagiarism detection. To protect data privacy, the new version of such a problem becomes more challenging, where the matched documents are distributed among two or more parties and their privacy should be preserved. In this paper, we propose new privacy-preserving document similarity detection schemes by utilizing the locality-sensitive hashing technique, which can handle the misspelled mistakes. Furthermore, the keywords' occurrences of a given document are integrated into its underlying representation to support a better ranking for the returned results. We introduced …

Go to article

Determining Allowable Parametric Uncertainty In An Uncommon Quadrotormodel For Closed Loop Stability, Mehmet Baskin, Mehmet Kemal Leblebi̇ci̇oğlu Mar 2022

Determining Allowable Parametric Uncertainty In An Uncommon Quadrotormodel For Closed Loop Stability, Mehmet Baskin, Mehmet Kemal Leblebi̇ci̇oğlu

Turkish Journal of Electrical Engineering and Computer Sciences

In this article, control oriented uncertainty modeling of an uncommon quadrotor in hover is discussed. This quadrotor consists of two counter-rotating big rotors on longitudinal axis and two counter-rotating small tilt rotors on lateral axis. Firstly, approximate linear model of this vehicle around hover is obtained by using Newton--Euler formulation. Secondly, specific uncertainty is assigned to each parameter. Resulting uncertain model is converted into a linear fractional transformation framework for robustness analysis. Next, the most critical uncertain parameters in terms of robust stability in a proposed quadrotor model are investigated using $ \mu $ sensitivities. Finally, skewed-$ \mu $ analysis …

Go to article

Improving Utilization Rate Of Semi-Parallel Successive Cancellation Architecture For Polar Codes Using 2-Bit Decoding, Dinesh Kumar Devadoss, Shantha Selva Kumari Rama Packiam Mar 2022

Improving Utilization Rate Of Semi-Parallel Successive Cancellation Architecture For Polar Codes Using 2-Bit Decoding, Dinesh Kumar Devadoss, Shantha Selva Kumari Rama Packiam

Turkish Journal of Electrical Engineering and Computer Sciences

Polar codes are the capacity-achieving error-correcting code proved to be a significant invention in coding theory. It can achieve channel capacity at infinite code length N due to its explicit code construction. However, the processing complexity along with the higher latency due to successive cancellation (SC) decoding is being a major design issue, which reduces the utilization rate in the decoder architectures. This paper presents a modified semi-parallel architecture for decoding polar code with a better decoding latency. Precomputation and look-ahead techniques are used to generate two bits in the final stage. Pipelined partial-sum unit with a less critical path …

Go to article

Predictive Optimization Of Sliding Mode Control Using Recurrent Neural Paradigmfor Nonlinear Dfig-Wpgs During Distorted Voltage, Omar Busati, Xiangjie Liu Mar 2022

Predictive Optimization Of Sliding Mode Control Using Recurrent Neural Paradigmfor Nonlinear Dfig-Wpgs During Distorted Voltage, Omar Busati, Xiangjie Liu

Turkish Journal of Electrical Engineering and Computer Sciences

Dynamic characteristics of the doubly-fed induction generator (DFIG)-based wind power generation (WPGS) are fully nonlinear. Therefore, issues such as stability and achieving high efficiency, especially under harmonics behavior, are challenges that assess the control strategy reliability to find the perfect dynamic solution. This discussion offers a control strategy for the separated stator-port power using a predictive sliding mode strategy with a resonant function (PSMC-R) based on a deep recurrent neural network (DRNN). DRNN is formed as a low-order Taylor series formula. PSMC-R predicts the perfect switching surface path and regulates the distorted nonlinear DFIG with several dynamic aims. This approach …

Go to article

Forecasting Tv Ratings Of Turkish Television Series Using A Two-Level Machinelearning Framework, Büşranur Akgül, Tayfun Küçükyilmaz Mar 2022

Forecasting Tv Ratings Of Turkish Television Series Using A Two-Level Machinelearning Framework, Büşranur Akgül, Tayfun Küçükyilmaz

Turkish Journal of Electrical Engineering and Computer Sciences

TV rating is a numeric estimate of the popularity of television programs. Forecasting TV ratings is considered an important asset for investment planning of media due to its potential of reducing the risks of future ventures. The aim of this study is to develop a machine learning model capable of efficiently forecasting the TV ratings of Turkish TV series in a practical manner. To this end, two prediction models were proposed for forecasting the TV ratings of television series, facilitating an extensive set of features. A contribution of this study is the inclusion of social media-based features using search trends …

Go to article

Scattering Analyses Of Arbitrary Roughness From 2-D Perfectly Conductiveperiodic Surfaces With Moments Method, Yunus Emre Yamaç, Ahmet Kizilay Mar 2022

Scattering Analyses Of Arbitrary Roughness From 2-D Perfectly Conductiveperiodic Surfaces With Moments Method, Yunus Emre Yamaç, Ahmet Kizilay

Turkish Journal of Electrical Engineering and Computer Sciences

In this paper, a periodic-MoM-based code with high accuracy performance is developed to calculate electromagnetic scattering from a periodic conductive surface in two dimensions with any degree of roughness. Firstly, the existing separate methods in the literature are reviewed step by step to compose a periodic-MoM solution for 2-D periodic surfaces. Then, the dynamic selection of optimal formulation of the periodic-MoM solutions created using these existing methods is evaluated to reduce solution time and obtain high accuracy. In this study, the performance parameters of the existing methods are investigated in solving a real 3-D scattering problem by a periodic-MoM for …

Go to article

Design And Aerodynamic Analysis Of A Vtol Tilt-Wing Uav, Hasan Çakir, Di̇lek Funda Kurtuluş Mar 2022

Design And Aerodynamic Analysis Of A Vtol Tilt-Wing Uav, Hasan Çakir, Di̇lek Funda Kurtuluş

Turkish Journal of Electrical Engineering and Computer Sciences

The aerodynamic design and analysis of an Unmanned Air Vehicle, capable of vertical take-off and landing by employing fixed four rotors on the tilt-wing and two rotors on the tilt-tail, will be presented in this study. Both main wing and the horizontal tail can be tilted 90°. During VTOL, transition and forward flight, aerodynamic and thrust forces have been employed. Different flight conditions, including the effects of angle of attack, side slip, wing tilt angle and control surfaces deflection angle changes, have been studied with CFD analysis. For a Tilt-Wing UAV, there are challenges like high non-linearity, vulnerability to disturbances …

Go to article

On An Electrostatic Micropump With A Rigorous Mathematical Model, İbrahi̇m Efe, Fati̇h Di̇kmen, Yury Tuchkin Mar 2022

On An Electrostatic Micropump With A Rigorous Mathematical Model, İbrahi̇m Efe, Fati̇h Di̇kmen, Yury Tuchkin

Turkish Journal of Electrical Engineering and Computer Sciences

The novel electrostatic micropump model for applications such as in biomedical drug delivery is presented. The geometrical arrangement of the coupling rigid electrodes lets us exploit our mathematically rigorous boundary integral equation formulation and its solution. Thus, the charge densities involving the fringe effects on the plates are obtained by means of analytical regularization method (ARM) constructed for annular strips earlier. The efficiency of the constructed method is demonstrated with respect to the direct integral equation solvers implemented via the entire domain Galerkin method and point matching. The main physical characteristics of the suggested system and their deviation from that …

Go to article

Robust Position/Force Control Of Nonholonomic Mobile Manipulator Forconstrained Motion On Surface In Task Space, Güli̇n Eli̇bol Seçi̇l, Serhat Obuz, Osman Parlaktuna Mar 2022

Robust Position/Force Control Of Nonholonomic Mobile Manipulator Forconstrained Motion On Surface In Task Space, Güli̇n Eli̇bol Seçi̇l, Serhat Obuz, Osman Parlaktuna

Turkish Journal of Electrical Engineering and Computer Sciences

In this paper, a robust controller is developed for a mobile manipulator (MM) to track reference position/force trajectories. Nonholonomic and holonomic constraints are considered for the mobile platform and manipulator, respectively. Additionally, the control design considers the uncertainties in parameters of the dynamics of the mobile manipulator with a bounded time varying additive disturbance (unmodelled effects, external disturbances). A Lyapunov-based stability analysis is used to prove semiglobal uniform ultimate boundedness of the tracking error signals and the position/force of the system track to an arbitrarily small neighborhood of the reference trajectories. Numerical results for a mobile manipulator, which is formed …

Go to article

A New Similarity-Based Multicriteria Recommendation Algorithm Based Onautoencoders, Zeynep Batmaz, Ci̇han Kaleli̇ Mar 2022

A New Similarity-Based Multicriteria Recommendation Algorithm Based Onautoencoders, Zeynep Batmaz, Ci̇han Kaleli̇

Turkish Journal of Electrical Engineering and Computer Sciences

Recommender systems provide their users an efficient way to handle information overload problem by offering personalized suggestions. Traditional recommender systems are based on two-dimensional user-item preference matrix constructed depending on the users' overall evaluations over items. However, they have begun to present their preferences under various circumstances. Thus, traditional recommendation techniques fail to process multicriteria ratings during the recommendation process. Multicriteria recommender systems are an extension of traditional recommender systems that utilize multicriteria-based user preferences. Multicriteria recommender systems provide more personalized and accurate predictions compared to traditional recommender systems. However, the increased amount of data dimension causes sparsity to be …

Go to article

A New Classification Method Using Soft Decision-Making Based On An Aggregation Operator Of Fuzzy Parameterized Fuzzy Soft Matrices, Samet Memi̇ş, Serdar Engi̇noğlu, Uğur Erkan Mar 2022

A New Classification Method Using Soft Decision-Making Based On An Aggregation Operator Of Fuzzy Parameterized Fuzzy Soft Matrices, Samet Memi̇ş, Serdar Engi̇noğlu, Uğur Erkan

Turkish Journal of Electrical Engineering and Computer Sciences

Recently, a precise and stable machine learning algorithm, i.e. eigenvalue classification method (EigenClass), has been developed by using the concept of generalised eigenvalues in contrast to common approaches, such as k-nearest neighbours, support vector machines, and decision trees. In this paper, we offer a new classification algorithm called fuzzy parameterized fuzzy soft aggregation classifier (FPFS-AC) to combine the modelling ability of soft decision-making (SDM) and classification success of generalised eigenvalues. FPFS-AC constructs a decision matrix by employing the similarity measures of fuzzy parameterized fuzzy soft matrices fpfs -matrices) and a generalised eigenvalue-based similarity measure. Then, it applies an SDM method …

Go to article

Defect Classification Of Railway Fasteners Using Image Preprocessing And Alightweight Convolutional Neural Network, İlhan Aydin, Mehmet Sevi̇, Mehmet Umut Salur, Erhan Akin Mar 2022

Defect Classification Of Railway Fasteners Using Image Preprocessing And Alightweight Convolutional Neural Network, İlhan Aydin, Mehmet Sevi̇, Mehmet Umut Salur, Erhan Akin

Turkish Journal of Electrical Engineering and Computer Sciences

Railway fasteners are used to securely fix rails to sleeper blocks. Partial wear or complete loss of these components can lead to serious accidents and cause train derailments. To ensure the safety of railway transportation, computer vision and pattern recognition-based methods are increasingly used to inspect railway infrastructure. In particular, it has become an important task to detect defects in railway tracks. This is challenging since rail track images are acquired using a measuring train in varying environmental conditions, at different times of day and in poor lighting conditions, and the resulting images often have low contrast. In this study, …

Go to article

Developing A Fake News Identification Model With Advanced Deep Languagetransformers For Turkish Covid-19 Misinformation Data, Mehmet Bozuyla, Akin Özçi̇ft Mar 2022

Developing A Fake News Identification Model With Advanced Deep Languagetransformers For Turkish Covid-19 Misinformation Data, Mehmet Bozuyla, Akin Özçi̇ft

Turkish Journal of Electrical Engineering and Computer Sciences

The massive use of social media causes rapid information dissemination that amplifies harmful messages such as fake news. Fake-news is misleading information presented as factual news that is generally used to manipulate public opinion. In particular, fake news related to COVID-19 is defined as 'infodemic' by World Health Organization. An infodemic is a misleading information that causes confusion which may harm health. There is a high volume of misinformation about COVID-19 that causes panic and high stress. Therefore, the importance of development of COVID-19 related fake news identification model is clear and it is particularly important for Turkish language from …

Go to article

Smart Charging Of Electric Vehicles To Minimize The Cost Of Chargingand The Rate Of Transformer Aging In A Residential Distribution Network, Arjun Visakh, M P. Selvan Mar 2022

Smart Charging Of Electric Vehicles To Minimize The Cost Of Chargingand The Rate Of Transformer Aging In A Residential Distribution Network, Arjun Visakh, M P. Selvan

Turkish Journal of Electrical Engineering and Computer Sciences

Electric vehicles (EVs) exhibit several benefits over combustion engine vehicles, making them an attractive mode of mobility for the future. However, supplying the electrical energy required to recharge their batteries could adversely affect the power system infrastructure. The most severe impact of EV integration is expected to be on the distribution transformers, which are among the costliest equipment in the distribution network. Sustained overloads on the transformer could lead to accelerated aging and early retirement. As the rate of EV deployment rises, so does the probability of transformer overloads and the subsequent loss of life. There is a need for …

Go to article

The Analysis And Optimization Of Cnn Hyperparameters With Fuzzy Tree Modelfor Image Classification, Kübra Uyar, Şaki̇r Taşdemi̇r, İlker Ali̇ Özkan Mar 2022

The Analysis And Optimization Of Cnn Hyperparameters With Fuzzy Tree Modelfor Image Classification, Kübra Uyar, Şaki̇r Taşdemi̇r, İlker Ali̇ Özkan

Turkish Journal of Electrical Engineering and Computer Sciences

The meaningful performance of convolutional neural network (CNN) has enabled the solution of various state-of-the-art problems. Although CNNs achieve satisfactory results in computer-vision problems, they still have some difficulties. As the designed CNN models are deepened to achieve much better accuracy, computational cost and complexity increase. It is significant to train CNNs with suitable topology and training hyperparameters that include initial learning rate, minibatch size, epoch number, filter size, number of filters, etc. because the initialization of hyperparameters affects classification results. On the other hand, it is not possible to make a definite inference for the hyperparameter initialization and there …

Go to article

A Novel Instrumentation Amplifier With High Tunable Gain And Cmrr Forbiomedical Applications, Riyaz Ahmad, Amit Joshi, Dharmendar Boolchandani Mar 2022

A Novel Instrumentation Amplifier With High Tunable Gain And Cmrr Forbiomedical Applications, Riyaz Ahmad, Amit Joshi, Dharmendar Boolchandani

Turkish Journal of Electrical Engineering and Computer Sciences

A new design of current mode instrumentation amplifier (CMIA) with tunable gain and low voltage operation capability is proposed in this paper, which is suitable for biomedical signals processing, especially in electrocardiogram (ECG). It consists of a new design of current differencing transconductance amplifier (CDTA) and dual z copy CDTA (DZC-CDTA). The gain of the proposed CMIA is controlled by a MOS-based tunable resistor. The main advantage of the proposed CMIA is its high gain that can be tuned over a significant range with the help of two resistances. The performance of the proposed instrumentation amplifier is evaluated through simulation …

Go to article

45-Nm Cds Qds Photoluminescent Filter For Photovoltaic Conversionefficiency Recovery, Victor Juárez-Luna, Daniel Sauceda-Carvajal, Ivett Zavala-Guillen, Enrique Rodarte-Guajardo, Francisco Carranza-Chávez, Carlos Villa Angulo Mar 2022

45-Nm Cds Qds Photoluminescent Filter For Photovoltaic Conversionefficiency Recovery, Victor Juárez-Luna, Daniel Sauceda-Carvajal, Ivett Zavala-Guillen, Enrique Rodarte-Guajardo, Francisco Carranza-Chávez, Carlos Villa Angulo

Turkish Journal of Electrical Engineering and Computer Sciences

Different energy loss mechanisms have restricted the breakthroughs in concentrated photovoltaic/thermal (CPVT) hybrid solar systems that use photoluminescent filters. Re?ected and transmitted light, emission spectrum, nonideal absorption, Stokes shift (proportional to $f_1 f_2$), overlapping absorption, and scattering of light are mechanisms in photoluminescent filters that restrict optical efficiency to below theoretical limits. In addition, increases in temperature by light concentration affect the operation of photovoltaic cells and photoluminescent filters because of an increase in molecular motion and collisions that consequently lead to energy loss. Meanwhile, nanocrystals or quantum dots (QDs) from groups II VI hold electrical, optical, chemical, and physical …

Go to article

Visual Interpretability Of Capsule Network For Medical Image Analysis, Mighty Abra Ayidzoe, Yu Yongbin, Patrick Kwabena Mensah, Jingye Cai, Faiza Umar Bawah Mar 2022

Visual Interpretability Of Capsule Network For Medical Image Analysis, Mighty Abra Ayidzoe, Yu Yongbin, Patrick Kwabena Mensah, Jingye Cai, Faiza Umar Bawah

Turkish Journal of Electrical Engineering and Computer Sciences

Deep learning (DL) models are currently not widely deployed for critical tasks such as in health. This is attributable to the "black box", making it difficult to gain the trust of practitioners. This paper proposes the use of visualizations to enhance performance verification, improve monitoring, ensure understandability, and improve interpretability needed to gain practitioners' confidence. These are demonstrated through the development of a CapsNet model for the recognition of gastrointestinal tract infection. The gastrointestinal tract comprises several organs joined in a long tube from the mouth to the anus. It is susceptive to diseases that are difficult for medics to …

Go to article

Analyzing Probabilistic Optimal Power Flow Problem By Cubature Rules, Qing Xiao Mar 2022

Analyzing Probabilistic Optimal Power Flow Problem By Cubature Rules, Qing Xiao

Turkish Journal of Electrical Engineering and Computer Sciences

This paper is devoted to revealing some properties of the probabilistic optimal power flow (POPF) problem. In conjunction with Hermite polynomial model, Nataf transformation is introduced to map POPF problem to the independent standard normal space. Firstly, a multivariate polynomial model is employed to represent the function relationship between POPF inputs and outputs. Then, moment matching equations are derived to characterize the uncertainty effects of POPF inputs on outputs; three cubature rules are derived to calculate statistical moments of POPF outputs. Finally, along with Monte Carlo simulation method, the proposed methods are tested on IEEE 57-bus system and IEEE 118-bus …

Go to article

Tara: Temperature Aware Online Dynamic Resource Allocation Scheme For Energyoptimization In Cloud Data Centres, Narayanamoorthi Thilagavathi, Arockiasamy John Prakash, Sridhar Sridevi, Vaidyanathan Rhymend Uthariaraj Mar 2022

Tara: Temperature Aware Online Dynamic Resource Allocation Scheme For Energyoptimization In Cloud Data Centres, Narayanamoorthi Thilagavathi, Arockiasamy John Prakash, Sridhar Sridevi, Vaidyanathan Rhymend Uthariaraj

Turkish Journal of Electrical Engineering and Computer Sciences

Cloud data centres, which are characteristic of dynamic workloads, if not optimized for energy consumption, may lead to increased heat dissipation and eventually impact the environment adversely. Consequently, optimizing the usage of energy has become a hard requirement in today's cloud data centres wherein the major part of energy consumption is mostly attributed to computing and cooling systems. Motivated by which this paper proposes an online algorithm for dynamic resource allocation, namely, temperature aware online dynamic resource allocation algorithm (TARA). TARA demonstrates a novel algorithm design to adapt dynamic resource allocation based on the temperature of a data centre using …

Go to article

Event-Related Microblog Retrieval In Turkish, Çağri Toraman Mar 2022

Event-Related Microblog Retrieval In Turkish, Çağri Toraman

Turkish Journal of Electrical Engineering and Computer Sciences

Microblogs, such as tweets, are short messages in which users are able to share any opinion and information. Microblogs are mostly related to real-life events reported in news articles. Finding event-related microblogs is important to analyze online social networks and understand public opinion on events. However, finding such microblogs is a challenging task due to the dynamic nature of microblogs and their limited length. In this study, assuming that news articles are given as queries and microblogs as documents, we find event-related microblogs in Turkish. In order to represent news articles and microblogs, we examine encoding methods, namely traditional bag-of-words …

Go to article

Biometric Identification Using Panoramic Dental Radiographic Images Withfew-Shot Learning, Musa Ataş, Cüneyt Özdemi̇r, İsa Ataş, Burak Ak, Esma Özeroğlu Mar 2022

Biometric Identification Using Panoramic Dental Radiographic Images Withfew-Shot Learning, Musa Ataş, Cüneyt Özdemi̇r, İsa Ataş, Burak Ak, Esma Özeroğlu

Turkish Journal of Electrical Engineering and Computer Sciences

Determining identity is a crucial task especially in the cases of mass disasters such as tsunamis, earthquakes, fires, epidemics, and in forensics. Although there are various studies in the literature on biometric identification from radiographic dental images, more research is still required. In this study, a panoramic dental radiographic (PDR) imagebased human identification system was developed using a customized deep convolutional neural network model in a few-shot learning scheme. The proposed model (PDR-net) was trained on 600 PDR images obtained from a total of 300 patients. As the PDR images of the patients were very different in terms of pose …

Go to article

First Prev Next Last