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

Computer Engineering Commons™

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

Physical Sciences and Mathematics

Institution
Keyword
Publication Year
Publication
Publication Type
File Type

Articles 5041 - 5070 of 13565

Full-Text Articles in Computer Engineering

A Saliency-Driven Video Magnifier For People With Low Vision, Ali Selman Aydin, Shirin Feiz, Iv Ramakrishnan, Vikas Ashok Jan 2020

A Saliency-Driven Video Magnifier For People With Low Vision, Ali Selman Aydin, Shirin Feiz, Iv Ramakrishnan, Vikas Ashok

Computer Science Faculty Publications

Consuming video content poses significant challenges for many screen magnifier users, which is the “go to” assistive technology for people with low vision. While screen magnifier software could be used to achieve a zoom factor that would make the content of the video visible to low-vision users, it is oftentimes a major challenge for these users to navigate through videos. Towards making videos more accessible for low-vision users, we have developed the SViM video magnifier system [6]. Specifically, SViM consists of three different magnifier interfaces with easy-to-use means of interactions. All three interfaces are driven by visual saliency as a …

Go to article

Field-Of-View Optimization Of Magnetically Actuated 2d Gimballed Scanners, Gökçe Aköz, Yi̇ği̇t Dağhan Gökdel Jan 2020

Field-Of-View Optimization Of Magnetically Actuated 2d Gimballed Scanners, Gökçe Aköz, Yi̇ği̇t Dağhan Gökdel

Turkish Journal of Electrical Engineering and Computer Sciences

This work presents the field of view (FOV) maximization of a magnetically actuated two-dimensional (2D) gimballed scanner. The process of maximization is completed in two steps. (1) Optimization of the electrocoil providing the magnetic force that moves the scanner and (2) precise choice of optimum respective locations of both the scanner and the electrocoil. We first derived a formula relating the generated magnetic flux density, coil design parameters and driving voltage. Subsequently, we discussed the design trade-offs of an actuating electrocoil. We also conducted several experiments on a stainless steel 430 scanner having a footprint of 15 mm × 15 …

Go to article

Exploring The Power Of Supervised Learning Methods For Company Name Disambiguation In Microblog Posts, Nafi̇ye Polat, Ali̇ Çakmak, Rabi̇a Turan Jan 2020

Exploring The Power Of Supervised Learning Methods For Company Name Disambiguation In Microblog Posts, Nafi̇ye Polat, Ali̇ Çakmak, Rabi̇a Turan

Turkish Journal of Electrical Engineering and Computer Sciences

Twitter is an online social networking website where people can post short messages on any subject, and these messages become visible to other users. Users intentionally express their opinions about companies or products via microblogging texts. Analyzing such messages might help explore what customers think about company products, or what the broad feelings of customers are. Identifying tweets referring to products and companies is becoming an important tool recently. However, company names are often vague. Hence, the first step is to locate the messages that are relevant to a company. In this paper, we present a number of supervised learning …

Go to article

Fuzzy Genetic Based Dynamic Spectrum Allocation (Fgdsa) Approach For Cognitive Radio Sensor Networks, Ganesan Rajesh, Xavier Mercilin Raajini, Kulandairaj Martin Sagayam, Bharat Bhushan, Utku Kose Jan 2020

Fuzzy Genetic Based Dynamic Spectrum Allocation (Fgdsa) Approach For Cognitive Radio Sensor Networks, Ganesan Rajesh, Xavier Mercilin Raajini, Kulandairaj Martin Sagayam, Bharat Bhushan, Utku Kose

Turkish Journal of Electrical Engineering and Computer Sciences

Cognitive Radio Sensor Network (CRSN) is known as a distributed network of wireless cognitive radio sensor nodes. Such system senses an event signal and ensures collaborative dynamic communication processes over the spectrum bands. Here, the concept of Dynamic Spectrum Access (DSA) denes the method of reaching progressively to the unused range of spectrum band. As among the essential CRSN user types, the Primary User (PU) has the license to access the spectrum band. On the other hand, the Secondary User (SU) tries to access the unused spectrum eciently, by not disturbing the PU. Considering that issue, this study introduces a …

Go to article

Reconfiguration-Based Hierarchical Energy Management In Multimicrogrid Systems Considering Power Losses, Reliability Index, And Voltage Enhancement, Farid Hamzeh Aghdam, Navid Taghizadegan Kalantari, Sajad Najafi Ravadanegh Jan 2020

Reconfiguration-Based Hierarchical Energy Management In Multimicrogrid Systems Considering Power Losses, Reliability Index, And Voltage Enhancement, Farid Hamzeh Aghdam, Navid Taghizadegan Kalantari, Sajad Najafi Ravadanegh

Turkish Journal of Electrical Engineering and Computer Sciences

This paper presents a reconfiguration-based hierarchical energy management for interconnected microgrids known as multimicrogrid system. The goal is to minimize the operational costs of different entities alongside with finding the best topology to minimize the active power loss, enhance reliability index, and improve the voltage level. The distribution network (DN) includes several dispatchable and undispatchable distributed energy resources, energy storage devices, and multiple microgrids (MGs). The first layer of the optimization process is executed by each MG operator and each MG performs local energy management. Each MG operator informs the DN operator about its optimal schedules. Finally, global energy management …

Go to article

An Encrypted Speech Authentication Method Based On Uniform Subband Spectrumvariance And Perceptual Hashing, Qiuyu Zhang, Denghai Zhang, Liang Zhou Jan 2020

An Encrypted Speech Authentication Method Based On Uniform Subband Spectrumvariance And Perceptual Hashing, Qiuyu Zhang, Denghai Zhang, Liang Zhou

Turkish Journal of Electrical Engineering and Computer Sciences

In a real-world cloud server, a speech signal is prone to suffer various attacks, such as malicious muting and tampering. In such a context, the privacy security of the speech owner will not be guaranteed. In order to achieve content authentication of encrypted speech in the cloud server, an efficient encrypted speech authentication method based on uniform subband spectrum variance and perceptual hashing is proposed. Firstly, the original speech is scrambled by Henon mapping to construct an encrypted speech library in the cloud, through extracting uniform subband spectrum variance of the encrypted speech and constructing a hashing sequence to generate …

Go to article

Low Power And Low Phase Noise Vco With Dual Current Shaping For Iotapplications, Sajad Nejadhasan, Narges Moazenian, Ebrahim Abiri, Mohammah Reza Salehi Jan 2020

Low Power And Low Phase Noise Vco With Dual Current Shaping For Iotapplications, Sajad Nejadhasan, Narges Moazenian, Ebrahim Abiri, Mohammah Reza Salehi

Turkish Journal of Electrical Engineering and Computer Sciences

In this paper, two low phase noise and power consumption VCO circuits, which are suitable for Internet of things (IoT) applications, are proposed. In the first structure, in order to have more control of the current consumption, the current shaping technique is used in the PMOS and NMOS biasing circuit. In the second structure, for increasing the oscillation amplitude and reducing the phase noise, independent biasing for the NMOS section is used. In both structures, to increase the frequency tuning range (FTR), without using a capacitor bank, the varactor is used in the biasing structure. In the first structure the …

Go to article

Reducing Computational Complexity In Fingerprint Matching, Mubeen Sabir, Tariq Mahmood Khan, Munazza Arshad, Sana Munawar Jan 2020

Reducing Computational Complexity In Fingerprint Matching, Mubeen Sabir, Tariq Mahmood Khan, Munazza Arshad, Sana Munawar

Turkish Journal of Electrical Engineering and Computer Sciences

The performance of cross-correlation functions can decrease computational complexity under optimal fingerprint feature selection. In this paper, a technique is proposed to perform alignment of fingerprints followed by their matching in fewer computations. Minutiae points are extracted and alignment is performed on the basis of their spatial locations and orientation fields. Unlike traditional cross-correlation based matching algorithms, ridges are not included in the matching process to avoid redundant computations. However, optimal cross-correlation is chosen by correlating feature vectors accompanying x-y locations of minutiae points and their aligned orientation fields. As a result, matching time is significantly reduced with much improved …

Go to article

Efficient Bandwidth Management Algorithm For Ng-Epon, Ammar Rafiq, Muhammad Faisal Hayat Jan 2020

Efficient Bandwidth Management Algorithm For Ng-Epon, Ammar Rafiq, Muhammad Faisal Hayat

Turkish Journal of Electrical Engineering and Computer Sciences

Next generation ethernet passive optical network (NG-EPON) is a promising technology to cater huge bandwidth and efficient distribution demands of the future Internet services. IEEE working group has been doing efforts for the standardization of NG-EPON. Four wavelength channels of 25Gbps each are supported by NG-EPON for the transmission of optical network unit (ONU) traffic towards optical line terminal (OLT). Dynamic wavelength and bandwidth allocation (DWBA) algorithms are needed for the efficient arbitration of bandwidth resources between subscribers. In this paper, we have proposed a DWBA algorithm named as efficient bandwidth management algorithm (EBMA) for NG-EPON. EBMA has been designed …

Go to article

Construction And Performance Analysis Of A New Sac-Ocdma Code Based Onlatin Square Matrix, Amel Aissaoui, Latifa Hacini Jan 2020

Construction And Performance Analysis Of A New Sac-Ocdma Code Based Onlatin Square Matrix, Amel Aissaoui, Latifa Hacini

Turkish Journal of Electrical Engineering and Computer Sciences

In this paper a family of novel spreading code called Latin square code (LSC) is proposed for spectral amplitude coding-optical code division multiple access (SAC-OCDMA) system. The main feature of the proposed code is the zero cross-correlation which eliminates both multiple access interference (MAI) and phase induced intensity noise (PIIN). The code construction can be easily accomplished using Latin square matrix (LSM) for any weight and number of users. The simplicity in the construction code has made it a compelling candidate for future OCDMA applications. SAC-OCDMA system employing direct decoding is mathematically analyzed and then numerically simulated using Matlab and …

Go to article

An Efficient Storage-Optimizing Tick Data Clustering Model, Haleh Amintoosi, Masood Niazi Torshiz, Yahya Forghani, Sara Alinejad Jan 2020

An Efficient Storage-Optimizing Tick Data Clustering Model, Haleh Amintoosi, Masood Niazi Torshiz, Yahya Forghani, Sara Alinejad

Turkish Journal of Electrical Engineering and Computer Sciences

Tick data is a large volume of data, related to a phenomenon such as stock market or weather change, with data values changing rapidly over time. An important issue is to store tick data table in a way that it occupies minimum storage space while at the same time it can provide fast execution of queries. In this paper, a mathematical model is proposed to partition tick data tables into clusters with the aim of minimizing the required storage space. The genetic algorithm is then used to solve the mathematical model which is indeed a clustering model. The proposed method …

Go to article

Modelling Sensor Ontology With The Sosa/Ssn Frameworks:A Case Study For Laboratory Parameters, Özlem Aktaş, Mehmet Mi̇lli̇, Sanaz Lakestani̇, Musa Mi̇lli̇ Jan 2020

Modelling Sensor Ontology With The Sosa/Ssn Frameworks:A Case Study For Laboratory Parameters, Özlem Aktaş, Mehmet Mi̇lli̇, Sanaz Lakestani̇, Musa Mi̇lli̇

Turkish Journal of Electrical Engineering and Computer Sciences

Recently, the use of sensor-based systems in many areas has led to an exponential increase in the raw sensor data. However, the lack of neither syntactic nor semantic integrity between these sensor data limited their sharing, reusability, and interpretation. These inabilities can cause some problems. For example, different wireless sensor networks may not work together due to the subtle variations in their sensing methods, operating systems, syntax, and data structure. In recent years, to cope with these inabilities, the semantic sensor web approach, which enables us to enrich the meaning of sensor data, has been seen as the critical technology …

Go to article

A Subsynchronous Resonance Prevention For Dfig-Based Wind Farms, Davood Fateh, Ali Akbar Moti Birjandi, Josep M. Guerrero Jan 2020

A Subsynchronous Resonance Prevention For Dfig-Based Wind Farms, Davood Fateh, Ali Akbar Moti Birjandi, Josep M. Guerrero

Turkish Journal of Electrical Engineering and Computer Sciences

In this paper, subsynchronous resonance (SSR) instability was accurately analyzed in doubly fed induction generator (DFIG)-based wind farms by the linearization of equations and modal analysis. In addition, the possibility of high compensation for the transmission lines connected to DFIG-based wind farms was provided using a SSR prevention controller (SSRPC). For this purpose, an SSRPC was connected to the output voltage of the grid side converter (GSC) of the DFIG. The GSC output voltage was selected as the connection point of the SSRPC because it directly affects the induction generator effect (IGE) and can be an inhibitor factor in its …

Go to article

Image Subset Communication For Resource-Constrained Applications In Wirelesssensor Networks, Sajid Nazir, Omar Alzubi, Mohammad Kaleem, Hassan Hamdoun Jan 2020

Image Subset Communication For Resource-Constrained Applications In Wirelesssensor Networks, Sajid Nazir, Omar Alzubi, Mohammad Kaleem, Hassan Hamdoun

Turkish Journal of Electrical Engineering and Computer Sciences

JPEG is the most widely used image compression standard for sensing, medical, and security applications. JPEG provides a high degree of compression but field devices relying on battery power must further economize on data transmissions to prolong deployment duration with particular use cases in wireless sensor networks. Transmitting a subset of image data could potentially enhance the battery life of power-constrained devices and also meet the application requirements to identify the objects within an image. Depending on an application's needs, after the first selected subset is received at the base station, further transmissions of the image data for successive refinements …

Go to article

Adaptive Modified Artificial Bee Colony Algorithms (Amabc) For Optimization Ofcomplex Systems, Rabi̇a Korkmaz Tan, Şebnem Bora Jan 2020

Adaptive Modified Artificial Bee Colony Algorithms (Amabc) For Optimization Ofcomplex Systems, Rabi̇a Korkmaz Tan, Şebnem Bora

Turkish Journal of Electrical Engineering and Computer Sciences

Complex systems are large scale and involve numerous uncertainties, which means that such systems tend to be expensive to operate. Further, it is difficult to analyze systems of this kind in a real environment, and for this reason agent-based modeling and simulation techniques are used instead. Based on estimation methods, modeling and simulation techniques establish an output set against the existing input set. However, as the data set in a given complex systems becomes very large, it becomes impossible to use estimation methods to create the output set desired. Therefore, a new mechanism is needed to optimize data sets in …

Go to article

Formation Of A Wireless Sensor Network Using Custom-Designed Sensors Having Lowpower And Low Cost Components, Veysel Yaman Akgün, Engi̇n Maşazade Jan 2020

Formation Of A Wireless Sensor Network Using Custom-Designed Sensors Having Lowpower And Low Cost Components, Veysel Yaman Akgün, Engi̇n Maşazade

Turkish Journal of Electrical Engineering and Computer Sciences

In this paper, we first design a sensor with low power and low cost components, namely an MSP430G2553 microcontroller (MCU), nRF24L01+ communication unit, and a light-dependent resistor (LDR). Then, connecting these custom-designed sensors with a central node, a fusion center (FC), we form a wireless sensor network (WSN) in which sensors measure light intensities and send their measurements to the FC for final inference. Since the default addressing structure of nRF24L01+ can simultaneously connect up to 6 devices, in order to have more connections, we define a new addressing scheme for the transmissions between sensors and the FC. Finally, as …

Go to article

A Fuzzy Neural Network For Web Service Selection Aimed At Dynamic Software Rejuvenation, Kimia Rezaei Kalantari, Ali Ebrahimnejad, Homayun Motameni Jan 2020

A Fuzzy Neural Network For Web Service Selection Aimed At Dynamic Software Rejuvenation, Kimia Rezaei Kalantari, Ali Ebrahimnejad, Homayun Motameni

Turkish Journal of Electrical Engineering and Computer Sciences

Software rejuvenation is an effective technique to counteract software aging in continuously running applications such as web service-based systems. In these systems, web services are allocated based on the requirements of receivers and the facilities of servers. One of the challenges while assigning web services is how to select appropriate server to reduce faults. In this paper, we propose dynamic software rejuvenation as a proactive fault-tolerance technique based on the neural fuzzy system. While considering a threshold for the rejuvenation of each web service, we completed the training based on the features of the service providers as well as the …

Go to article

Combined Morphology And Svm-Based Fault Feature Extraction Technique Fordetection And Classification Of Transmission Line Faults, Revati Godse, Dr. Sunil Bhat Jan 2020

Combined Morphology And Svm-Based Fault Feature Extraction Technique Fordetection And Classification Of Transmission Line Faults, Revati Godse, Dr. Sunil Bhat

Turkish Journal of Electrical Engineering and Computer Sciences

A transmission line is the main commodity of power transmission network through which power is transmitted to the utility. These lines are often swayed by accidental breakdowns owing to different random origins. Hence, researchers try to detect and track down these failures at the earliest to avoid financial prejudice. This paper offers a new realtime mathematical morphology based approach for fault feature extraction. The morphological open-close-median filter is exploited to wrest unique fault features which are then fed as an input to support vector machine to detect and classify the short circuit faults. The acquired graphical and numerical results of …

Go to article

Highly Sensitive Fiber Optic Pressure Sensors For Wind Turbine Applications, Mali̇k Kaya, Okan Esentürk Jan 2020

Highly Sensitive Fiber Optic Pressure Sensors For Wind Turbine Applications, Mali̇k Kaya, Okan Esentürk

Turkish Journal of Electrical Engineering and Computer Sciences

Fiber optic pressure sensors utilizing ultra-high sensitive fiber loop ringdown (FLRD) spectroscopy were fabricated using a bare single mode fiber. The fiber optic pressure sensors were applied to monitor pressure change on a plastic pipe embedded into a sea sand filled container in laboratory conditions to simulate a tower. As the pressure applied to the sensor head was changed from $66.4$ kPa to $331.6$ kPa, changes in the ringdown time (RDT) were recorded. The lowest baseline stability of 0.20 % was obtained in these simple FLRD pressure sensors. The minimum detectable optical loss was $992$ $\mu$dB. The results showed that …

Go to article

Improving The Efficiency Of Dnn Hardware Accelerator By Replacing Digitalfeature Extractor With An Imprecise Neuromorphic Hardware, Majid Mohammadi Rad, Omid Sojodishijani Jan 2020

Improving The Efficiency Of Dnn Hardware Accelerator By Replacing Digitalfeature Extractor With An Imprecise Neuromorphic Hardware, Majid Mohammadi Rad, Omid Sojodishijani

Turkish Journal of Electrical Engineering and Computer Sciences

Mixed-signal in-memory computation can drastically improve the efficiency of the hardware implementing machine learning (ML) algorithms by (i) removing the need to fetch neural network parameters from internal or external memory and (ii) performing a large number of multiply-accumulate operations in parallel. However, this boost in efficiency comes with some disadvantages. Among them, the inability to precisely program nonvolatile memory devices (NVM) with neural network parameters and sensitivity to noise prevent the mixed-signal hardware to perform a precise and deterministic computation. Unfortunately, these hardware-specific errors can get magnified while propagating along with the layers of the deep neural network. In …

Go to article

Impulse Noise Removal By K-Means Clustering Identified Fuzzy Filter: A Newapproach, Aritra Bandyopadhyay, Kaustuv Deb, Atanu Das, Rajib Bag Jan 2020

Impulse Noise Removal By K-Means Clustering Identified Fuzzy Filter: A Newapproach, Aritra Bandyopadhyay, Kaustuv Deb, Atanu Das, Rajib Bag

Turkish Journal of Electrical Engineering and Computer Sciences

Removal of impulse noise from corrupted digital images has been a hitch in the field of image processing. Random nature of impulse noise makes the task of noise removal more critical. Different filters have been designed for noise removal purpose and have shown formidable results mostly for low and medium level noise densities. In this paper, a new two-stage technique called k-means clustering identified fuzzy filter (KMCIFF) is proposed for de-noising gray-scale images. KMCIFF consists of a k-Means clustering-based high density impulse noise detection, followed by a fuzzy logic-oriented noise removal mechanism. In the detection process, a 5 $\times$ 5 …

Go to article

Mlcocoa: A Machine Learning-Based Congestion Control For Coap, Alper Kami̇l Demi̇r, Fati̇h Abut Jan 2020

Mlcocoa: A Machine Learning-Based Congestion Control For Coap, Alper Kami̇l Demi̇r, Fati̇h Abut

Turkish Journal of Electrical Engineering and Computer Sciences

Internet of Things (IoT) is a technological invention that has the potential to impact on how we live and how we work by connecting any device to the Internet. Consequently, a vast amount of novel applications will enhance our lives. Internet Engineering Task Force (IETF) standardized the Constrained Application Protocol (CoAP) to accommodate the application layer and network congestion needs of such IoT networks. CoAP is designed to be very simple where it employs a genuine congestion control (CC) mechanism, named as default CoAP CC leveraging basic binary exponential backoff. Yet efficient, default CoAP CC does not always utilize the …

Go to article

Optimized Idling Grid-Connection Strategy For Synchronous Condenser, Jianxiang Shi, Heqing Huang, Teng Liu, Wei Mu, Jianfeng Zhao Jan 2020

Optimized Idling Grid-Connection Strategy For Synchronous Condenser, Jianxiang Shi, Heqing Huang, Teng Liu, Wei Mu, Jianfeng Zhao

Turkish Journal of Electrical Engineering and Computer Sciences

The rise of large-scale HVDC transmission technology has introduced new requirements for dynamic reactive power compensation in power systems. The new generation of synchronous condensers is independent of grid voltage and does not need to be dragged by a coaxial prime mover, which can improve the dynamic reactive power compensation of the power grid. This new generation of synchronous condensers is dragged by the static frequency converter to a 105% rated speed, after which the static frequency converter logs out. In the process of idling, the excitation mode switching is completed and the unit is connected to the grid simultaneously. …

Go to article

An Improved Memetic Genetic Algorithm Based On A Complex Network As Asolution To The Traveling Salesman Problem, Hadi Mohammadi, Kamal Mirzaie, Mohammad Reza Mollakhalili Meybodi Jan 2020

An Improved Memetic Genetic Algorithm Based On A Complex Network As Asolution To The Traveling Salesman Problem, Hadi Mohammadi, Kamal Mirzaie, Mohammad Reza Mollakhalili Meybodi

Turkish Journal of Electrical Engineering and Computer Sciences

A genetic algorithm (GA) is not a good option for finding solutions around in neighborhoods. The current study applies a memetic algorithm (MA) with a proposed local search to the mutation operator of a genetic algorithm in order to solve the traveling salesman problem (TSP). The proposed memetic algorithm uses swap, reversion and insertion operations to make changes in the solution. In the basic GA, unlike in the real world, the relationship between generations has not been considered. This gap is resolved using the proposed complex network to allow selection among possible solutions. The degree measure has been used for …

Go to article

Comparative Study Between Measured And Estimated Wind Energy Yield, Ayman Alquraan, Mohammed Al-Mahmodi, Ashraf Radaideh, Hussein Al-Masri Jan 2020

Comparative Study Between Measured And Estimated Wind Energy Yield, Ayman Alquraan, Mohammed Al-Mahmodi, Ashraf Radaideh, Hussein Al-Masri

Turkish Journal of Electrical Engineering and Computer Sciences

This paper proposes a power-speed (P-V) model of the wind turbine by assuming three different functions for the first performance region; cubic, quadratic and uncorrected cubic. These three functions have been compared with the manufacturer models of five different wind turbines which were installed in five different locations in Jordan; Tafila, Hofa, Fujeij, Al Rajef, and Deahan. The wind turbine of these wind farms are considered as large scale HAWT in the range of Mw. The generated P-V models are developed by applying a new method described in this paper which is basically based on generating a multiplier factor x. …

Go to article

Gabor Filter-Based Localization Of Straight And Curved Needlesin 2d Ultrasound Images, Mert Kaya, Abdurrahman Enes Şenel, Özkan Bebek Jan 2020

Gabor Filter-Based Localization Of Straight And Curved Needlesin 2d Ultrasound Images, Mert Kaya, Abdurrahman Enes Şenel, Özkan Bebek

Turkish Journal of Electrical Engineering and Computer Sciences

2D ultrasound (US) is one of the most commonly used medical imaging devices for needle localization in biopsies. However, the produced images are low-resolution and contain an excessive number of artifacts, which makes the needle localization challenging. Image processing techniques can help resolve this issue. This paper presents a novel Gabor filter-based method for needle localization in 2D US images, which enhances the needle outline in the images while suppressing other structures. The scheme works in two stages: First, the Gabor filter is applied to the image, the needle insertion angle is estimated, and the needle trajectory is found using …

Go to article

Chronic Obstructive Pulmonary Disease Severity Analysis Using Deep Learning Onmulti-Channel Lung Sounds, Gökhan Altan, Yakup Kutlu, Ahmet Gökçen Jan 2020

Chronic Obstructive Pulmonary Disease Severity Analysis Using Deep Learning Onmulti-Channel Lung Sounds, Gökhan Altan, Yakup Kutlu, Ahmet Gökçen

Turkish Journal of Electrical Engineering and Computer Sciences

Chronic obstructive pulmonary disease (COPD) is one of the deadliest diseases which cannot be treated but can be kept under control in certain stages. COPD has five severities, including at-risk, mild, moderate, severe, and very severe stages. Diagnosis of COPD at early stages needs additional clinical tests for even experienced specialists. The study aims at detecting the severity of the COPD to start treatment for preventing the progression of the disease to the next levels. We analyzed 12-channel lung sounds with different COPD severities from RespiratoryDatabase@TR. The lung sounds were recorded from the clinical auscultation points from 41 patients on …

Go to article

Variable Gain High Order Sliding Mode Control Approaches For Pmsg Basedvariable Speed Wind Energy Conversion System, Ameen Ullah, Laiq Khan, Qudrat Khan, Saghir Ahmad Jan 2020

Variable Gain High Order Sliding Mode Control Approaches For Pmsg Basedvariable Speed Wind Energy Conversion System, Ameen Ullah, Laiq Khan, Qudrat Khan, Saghir Ahmad

Turkish Journal of Electrical Engineering and Computer Sciences

This research article proposes two different variants of variable gain higher-order sliding mode control (HOSMC) strategy for a variable-speed wind energy conversion system (WECS) based on a permanent magnet synchronous generator (PMSG). The main objective is to extract the maximum wind power with reduced chattering and mechanical stress. The main flaw of the classical sliding mode control (SMC) is the high-frequency switching, called chattering, which is alleviated by employing HOSMC strategies. The control law design is based on a super-twisting algorithm (STA) and a real-twisting algorithm (RTA) with variable gains. The proposed control techniques inherit the property of robustness and …

Go to article

Performance Optimisation Of A Sensing Chamber Using Fluid Dynamics Simulationfor Electronic Nose Applications, Punjan Dohare, Sudeshna Bagchi, Amol P. Bhondekar Jan 2020

Performance Optimisation Of A Sensing Chamber Using Fluid Dynamics Simulationfor Electronic Nose Applications, Punjan Dohare, Sudeshna Bagchi, Amol P. Bhondekar

Turkish Journal of Electrical Engineering and Computer Sciences

The sensor chamber plays a significant role in order to improve the performance of an electronic nose in terms of stability, repeatability, reproducibility, and sensitivity. Fluid dynamics simulations of six different configurations of 3D sensing chambers are presented to facilitate the efficient design of an electronic nose system comprising 64 sensor arrays. Numerical simulations were carried out to investigate the gas (zero air) flow behaviour inside these chambers under steady-state conditions for velocities ranging from 0.1 to 2 m/s using ANSYS software. Design optimisation was performed in terms of area coverage, velocity, and mass fraction. The results show that the …

Go to article

Exhaustive Hard Triplet Mining Loss For Person Re-Identification, Chao Xu, Xiang Sun, Ziliang Chen, Shoubiao Tan Jan 2020

Exhaustive Hard Triplet Mining Loss For Person Re-Identification, Chao Xu, Xiang Sun, Ziliang Chen, Shoubiao Tan

Turkish Journal of Electrical Engineering and Computer Sciences

Person reidentification (Re-ID) is an important task in computer vision and has many applications in videobased surveillance. Recently, the triplet loss has been popular in the deep learning framework for person Re-ID. It is particularly important to note that the selection of hard triplets has significant influence on the performance of the learned deep model. However, the existing triplet losses only focus on some specific forms of hard triplets, thus leading to weaker generalization capability. To address this issue, we propose a novel variant of the triplet loss, named exhaustive hard triplet mining loss (EHTM), which is able to deal …

Go to article

First Prev Next Last