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

Computer Engineering Commons™

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

Electrical and Computer Engineering

Institution
Keyword
Publication Year
Publication
Publication Type
File Type

Articles 3571 - 3600 of 7216

Full-Text Articles in Computer Engineering

Aqueous Paramagnetic Solutions For Mri Phantoms At 3 T:A Detailed Study On Relaxivities, Kalaivani Thangavel, Emi̇ne Ülkü Saritaş Jan 2017

Aqueous Paramagnetic Solutions For Mri Phantoms At 3 T:A Detailed Study On Relaxivities, Kalaivani Thangavel, Emi̇ne Ülkü Saritaş

Turkish Journal of Electrical Engineering and Computer Sciences

Phantoms with known T$_{1}$ and T$_{2}$ values that are prepared using solutions of easily accessible paramagnetic agents are commonly used in MRI imaging centers, especially with the goal of validating the accuracy of quantitative imaging protocols. The relaxivity parameters of several agents were comprehensively examined at lower B$_{0}$ field strengths, but studies at 3 T remain limited. The main goal of this study is to measure r$_{1}$ and r$_{2}$ relaxivities of three common paramagnetic agents (CuSO$_{4}$, MnCl$_{2}$, and NiCl$_{2})$ at room temperature at 3 T. Separate phantoms were prepared at various concentrations of 0.05-0.5 mM for MnCl$_{2}$ and 1-6 mM …


Reconstruction Of A Single Square Pulse Originally Having 40 Ps Width Coming From A Lossy And Noisy Channel In A Point To Point Interconnect, Alak Majumder, Bidyut Bhattacharyya Jan 2017

Reconstruction Of A Single Square Pulse Originally Having 40 Ps Width Coming From A Lossy And Noisy Channel In A Point To Point Interconnect, Alak Majumder, Bidyut Bhattacharyya

Turkish Journal of Electrical Engineering and Computer Sciences

The fundamental problem in high speed communication is that it suffers a lot of signal integrity issues due to dispersion (caused by dielectric variation with angular frequency), reflection (S$_{11})$, and insertion losses (S$_{12})$ of the channel made of copper. When a pulse width $\tau $ with magnitude V$_{0}$ is driven through a lossy channel, we observe a reduction in magnitude (due to S$_{12}$ and S$_{11})$ and an increase in pulse width (due to dispersion). It causes different values of skin effect and dielectric loss leading to different effective resistance at each segment as the pulse moves through the channel. This …


Sum Rate Enhancement And Interference Alignment For Mimo Channels, Sarmad Sohaib, Faqir Najam-Ul-Hassan, Junaid Ahmed Jan 2017

Sum Rate Enhancement And Interference Alignment For Mimo Channels, Sarmad Sohaib, Faqir Najam-Ul-Hassan, Junaid Ahmed

Turkish Journal of Electrical Engineering and Computer Sciences

Interference alignment (IA) is a cooperative technique used for multiple-input, multiple-output (MIMO) interference channels to confine the interference to a reduced signal space of the receiver. IA helps all nodes of the network to achieve half of the degree of freedom that can be achieved if there were no interference. In this paper an iterative alternating minimization algorithm is presented, which aims at providing the higher sum rate along with IA for more than three users having complete channel state information. In each iteration of the algorithm precoders and decoders are calculated to align interference in a reduced interference subspace. …


Smart Frequent Itemsets Mining Algorithm Based On Fp-Tree And Diffset Data Structures, George Gatuha, Tao Jiang Jan 2017

Smart Frequent Itemsets Mining Algorithm Based On Fp-Tree And Diffset Data Structures, George Gatuha, Tao Jiang

Turkish Journal of Electrical Engineering and Computer Sciences

Association rule data mining is an important technique for finding important relationships in large datasets. Several frequent itemsets mining techniques have been proposed using a prefix-tree structure, FP-tree, a compressed data structure for database representation. The DIFFset data structure has also been shown to significantly reduce the run time and memory utilization of some data mining algorithms. Experimental results have demonstrated the efficiency of the two data structures in frequent itemsets mining. This work proposes FDM, a new algorithm based on FP-tree and DIFFset data structures for efficiently discovering frequent patterns in data. FDM can adapt its characteristics to efficiently …


Implementation Of Energy Management And Demand Side Management Of A Solar Microgrid Using A Hybrid Platform, Leo Raju, Milton Sakaya, Senthilkumaran Mahadevan Jan 2017

Implementation Of Energy Management And Demand Side Management Of A Solar Microgrid Using A Hybrid Platform, Leo Raju, Milton Sakaya, Senthilkumaran Mahadevan

Turkish Journal of Electrical Engineering and Computer Sciences

This paper presents the implementation of the advanced distributed energy management and demand side management of a solar microgrid by a multiagent system (MAS) coordination approach. The proposed approach is built upon a hybrid platform in which a solar microgrid, modelled in MATLAB/Simulink, is controlled by a MAS implemented in Java Agent Development Framework (JADE), bringing the MAS closer to the real-time application. Novel control strategies are designed to implement all the smart grid features in the microgrid. The Simulink model is controlled by strategic action of agents in JADE, a multithreaded computing platform, through a middleware, multiagent control using …


Android Malware Classification Based On Anfis With Fuzzy C-Means Clustering Using Significant Application Permissions, Altyeb Altaher, Omar Barukab Jan 2017

Android Malware Classification Based On Anfis With Fuzzy C-Means Clustering Using Significant Application Permissions, Altyeb Altaher, Omar Barukab

Turkish Journal of Electrical Engineering and Computer Sciences

Mobile phones have become an essential part of our lives because we depend on them to perform many tasks, and they contain personal and important information. The continuous growth in the number of Android mobile applications resulted in an increase in the number of malware applications, which are real threats and can cause great losses. There is an urgent need for efficient and effective Android malware detection techniques. In this paper, we present an adaptive neuro-fuzzy inference system with fuzzy c-means clustering (FCM-ANFIS) for Android malware classification. The proposed approach utilizes the FCM clustering method to determine the optimum number …


Adaptive Sliding Mode With Time Delay Control Based On Convolutions For Power Flow Reference Tracking Using A Vsc-Hvdc System, Amar Hamache, Mohand Outahar Bensidhoum, Hachemi Chekireb Jan 2017

Adaptive Sliding Mode With Time Delay Control Based On Convolutions For Power Flow Reference Tracking Using A Vsc-Hvdc System, Amar Hamache, Mohand Outahar Bensidhoum, Hachemi Chekireb

Turkish Journal of Electrical Engineering and Computer Sciences

This paper deals with the design of an adaptive sliding mode with a time delay control based on convolutions (ASMTDCC) approach for a voltage source converter (VSC) high voltage direct current (HVDC) transmission system for power flow reference tracking over a wide range of operating conditions considering parameter variations and external disturbances. For this purpose, the model of a VSC-HVDC transmission system connecting two asynchronous electrical grids is developed. The problem of designing an ASMTDCC feedback scheme, via a control strategy, is addressed seeking a better performance. For ensuring robust behavior and reducing chattering, the ASMTDCC scheme is realized based …


An Area-Efficient And Wide-Range Digital Dll For Per-Pin Deskew Applications, Chingche Chung, Chienying Yu Jan 2017

An Area-Efficient And Wide-Range Digital Dll For Per-Pin Deskew Applications, Chingche Chung, Chienying Yu

Turkish Journal of Electrical Engineering and Computer Sciences

In this work, we present a 200 MHz to 1.6 GHz digital delay-locked loop (DLL) for per-pin deskew applications. The proposed phase shifters apply linear and scalable circuit architecture for the pin-to-pin delay mismatch of parallel I/O pins. The proposed phase detector with a detection window and the proposed consecutive phase decision method reduce the sensitivity to reference clock jitter. A test chip of the 0.042 mm$^{2}$ DLL and the 3-ps-adjustable-resolution phase shifters with a 0.0025 mm$^{2}$ per-channel area was implemented using a 90-nm CMOS process. Simulation results show that the phase error of the 90$^{\circ}$ phase shifter at 1.6 …


An Efficient Ofdm-Based System With An Insufficient Cyclic Prefix Via A Novel Constellation Algorithm, Saeed Ghazi-Maghrebi Jan 2017

An Efficient Ofdm-Based System With An Insufficient Cyclic Prefix Via A Novel Constellation Algorithm, Saeed Ghazi-Maghrebi

Turkish Journal of Electrical Engineering and Computer Sciences

In this paper, a new special triangular constellation scheme is introduced to replace the commonly used rectangular QAM constellation in orthogonal frequency division multiplexing (OFDM) modulation. We have shown that this new scheme has 3 major advantages with respect to the well-known QAM. The first advantage is its lower error probability performance, which results from better usage of the constellation space with longer minimum distances. The 2 other advantages are a lower peak to average power ratio (PAPR) and higher noise immunity. Both mathematical analysis and simulation results demonstrate that by applying standard channels in 2 cases, i.e. channels with …


An Ultrafast All-Optical Switch Based On A Nonlinear Photonic Crystal Waveguide Using Single Crystal P-Toluene Sulfonate, Mahdi Taheri, Masood Omoomi Jan 2017

An Ultrafast All-Optical Switch Based On A Nonlinear Photonic Crystal Waveguide Using Single Crystal P-Toluene Sulfonate, Mahdi Taheri, Masood Omoomi

Turkish Journal of Electrical Engineering and Computer Sciences

A novel design of an all-optical switch is proposed based on a nonlinear photonic crystal Mach-Zehnder interferometer (PC-MZI) to get the maximum switching speed and the minimum consuming power. As far as we know, this is the first study using a nonlinear polymer in one of the PC-MZI arms for realizing the switching phenomenon. All used components, such as bends, waveguides, and splitters, were individually optimized. Finite difference time domain and plane wave expansion methods were also utilized for the simulation of light propagation in the proposed structures.


Performance Enhancement Of A Dynamic Voltage Restorer, Latha Pappath Vasudevan, Valsalal Prasad Jan 2017

Performance Enhancement Of A Dynamic Voltage Restorer, Latha Pappath Vasudevan, Valsalal Prasad

Turkish Journal of Electrical Engineering and Computer Sciences

Custom power devices are widely employed to mitigate power quality issues affecting critical loads. The dynamic voltage restorer is one of the custom power devices designed to inject a voltage in series with line to present a pure sinusoidal voltage of the desired RMS value to the sensitive loads, if the supply side is affected by voltage disturbances. The design and implementation of a DVR with a quasi-impedance source inverter and variable structure control is discussed in this paper. The voltage boosting ability of a quasi-impedance (Z) source inverter is used here to improve the performance of the DVR with …


Novel Control Strategy For Hybrid Renewable Energy-Based Standalone System, Rahul Sharma, Sathans Suhag Jan 2017

Novel Control Strategy For Hybrid Renewable Energy-Based Standalone System, Rahul Sharma, Sathans Suhag

Turkish Journal of Electrical Engineering and Computer Sciences

In this paper, novel control strategies are proposed for a hybrid renewable energy system under a standalone environment. The wind unit, solar unit, supercapacitor (SC), and battery are connected to a DC link through power converters. Control methods are proposed to mitigate the limitations of the standalone system. The control method is proposed to maintain constant DC link voltage under different conditions without using a dummy load (i.e. an electrolyzer). The SC and battery are used as storage devices. A novel control scheme is proposed to control storage devices where the SC is used to improve the slow response of …


Model-Based Fault Analysis Of A High-Voltage Circuit Breaker Operating Mechanism, Ali Forootani, Ali Akbar Afzalian, Ali Nadian Ghohmshe Jan 2017

Model-Based Fault Analysis Of A High-Voltage Circuit Breaker Operating Mechanism, Ali Forootani, Ali Akbar Afzalian, Ali Nadian Ghohmshe

Turkish Journal of Electrical Engineering and Computer Sciences

In this paper, a dynamic model is developed for high-voltage circuit breakers to extract fault features and causes. Lagrange's method is applied using geometric equations of mechanism components to write the model. Unlike previous approaches, the proposed method reveals and analyzes all types of circuit breaker operating mechanism faults. Early fault detection, which is a vital requirement of the fault diagnosis system, becomes feasible by keeping track of changes in the contact travel curve in the proposed model. Resulting faults in the travel curve are analyzed mathematically in order to find out the exact origin of the fault. Field test …


Planar Array Of Right-Angled Isosceles Triangular Microstrip Antenna Using Koch And Meander Lines For The Internet Of Things, Manisha Gupta, Vinita Mathur Jan 2017

Planar Array Of Right-Angled Isosceles Triangular Microstrip Antenna Using Koch And Meander Lines For The Internet Of Things, Manisha Gupta, Vinita Mathur

Turkish Journal of Electrical Engineering and Computer Sciences

An ultrawideband antenna array using a right-angled isosceles triangular microstrip antenna as a basic element is presented using inset feed for applications in the Internet of things. A Koch fractal antenna array with defected ground plane is used to generate multiband applications. Further, meander lines are added to increase the equivalent inductance that reduces the size of the antenna and increases the bandwidth and gain. Antenna arrays have been constructed and experimentally studied. The measured results show good agreement with the numerical prediction and wideband operation.


Bayesian Estimation Of Discrete-Time Cellular Neural Network Coefficients, Hakan Meti̇n Özer, Ati̇lla Özmen, Habi̇b Şenol Jan 2017

Bayesian Estimation Of Discrete-Time Cellular Neural Network Coefficients, Hakan Meti̇n Özer, Ati̇lla Özmen, Habi̇b Şenol

Turkish Journal of Electrical Engineering and Computer Sciences

A new method for finding the network coefficients of a discrete-time cellular neural network (DTCNN) is proposed. This new method uses a probabilistic approach that itself uses Bayesian learning to estimate the network coefficients. A posterior probability density function (PDF) is composed using the likelihood and prior PDFs derived from the system model and prior information, respectively. This posterior PDF is used to draw samples with the help of the Metropolis algorithm, a special case of the Metropolis-Hastings algorithm where the proposal distribution function is symmetric, and resulting samples are then averaged to find the minimum mean square error (MMSE) …


Turkish Entity Discovery With Word Embeddings, Murat Kalender, Emi̇n Erkan Korkmaz Jan 2017

Turkish Entity Discovery With Word Embeddings, Murat Kalender, Emi̇n Erkan Korkmaz

Turkish Journal of Electrical Engineering and Computer Sciences

Entity-linking systems link noun phrase mentions in a text to their corresponding knowledge base entities in order to enrich a text with metadata. Wikipedia is a popular and comprehensive knowledge base that is widely used in entity-linking systems. However, long-tail entities are not popular enough to have their own Wikipedia articles. Therefore, a knowledge base created by using Wikipedia entities would be limited to only popular entities. In order to overcome the knowledge base coverage limitation of Wikipedia-based entity-linking systems, this paper presents an entity-discovery system that can detect semantic types of entities that are not defined in Wikipedia. The …


A Cnfet Full Adder Cell Design For High-Speed Arithmetic Units, Mokhtar Mohammadi Ghanaghestani, Behnam Ghavami, Honeya Salehpour Jan 2017

A Cnfet Full Adder Cell Design For High-Speed Arithmetic Units, Mokhtar Mohammadi Ghanaghestani, Behnam Ghavami, Honeya Salehpour

Turkish Journal of Electrical Engineering and Computer Sciences

Carbon nanotube field-effect transistors (CNFETs) utilize an array of carbon nanotubes as the channel material instead of bulk silicon in the traditional MOSFET structure, which holds great promise for the future of integrated circuits. In this paper, a full adder cell based on a parallel design using CNFETs is presented. The main objective of designing this full adder cell is to reduce critical path delay in CNFET-based adder circuits. The proposed design positively affects speed and power consumption by shortening the data path. In order to evaluate the proposed design, several simulations were performed with different load capacitors, frequencies, and …


A 0.65-1.35 Ghz Synthesizable All-Digital Phase Locked Loop With Quantization Noise Suppressing Time-To-Digital Converter, Yalçin Balcioğlu, Günhan Dündar Jan 2017

A 0.65-1.35 Ghz Synthesizable All-Digital Phase Locked Loop With Quantization Noise Suppressing Time-To-Digital Converter, Yalçin Balcioğlu, Günhan Dündar

Turkish Journal of Electrical Engineering and Computer Sciences

This paper presents a new quantization noise suppression method for a time-to-digital converter (TDC) and proposes an all-digital phase-locked loop (ADPLL) architecture using only standard cell logic gates. Using a new multiple input multiple output (MIMO) quantization noise suppression method provides an order of $\sqrt {2N} $ improvement in TDC resolution with $N$ parallel TDC channels. Suppressed noise in the TDC allows the ADPLL to achieve superior jitter performance in both theoretical calculations and simulation results. In order to allow fast portability between process nodes, short design cycle time, ease of modification, and flexibility, ADPLL architecture is designed completely in …


A Novel Generation And Capacitor Integration Technique For Today's Distribution Systems, Okan Özgönenel, Serap Karagöl Jan 2017

A Novel Generation And Capacitor Integration Technique For Today's Distribution Systems, Okan Özgönenel, Serap Karagöl

Turkish Journal of Electrical Engineering and Computer Sciences

In this paper, the problem of optimally placing shunt capacitors and generators in radial distribution systems is handled and a new calculation technique based on wavelet neural network (WNN), which is computationally effective compared to well-known techniques, is proposed. The objectives for the proposed method are simply selected as the minimum cost of peak power and losses and maximum voltage stability. The suggested optimization technique is tested on various IEEE radial buses and then compared to the well-known methods in the literature, i.e. golden section search, grid search, and Acharya's heuristic method. The proposed and conventional methods are applied to …


Analysis Of Feature Detector And Descriptor Combinations With A Localization Experiment For Various Performance Metrics, Ertuğrul Bayraktar, Pinar Boyraz Jan 2017

Analysis Of Feature Detector And Descriptor Combinations With A Localization Experiment For Various Performance Metrics, Ertuğrul Bayraktar, Pinar Boyraz

Turkish Journal of Electrical Engineering and Computer Sciences

The purpose of this study is to provide a detailed performance comparison of feature detector/descriptor methods, particularly when their various combinations are used for image-matching. The localization experiments of a mobile robot in an indoor environment are presented as a case study. In these experiments, 3090 query images and 127 dataset images were used. This study includes five methods for feature detectors (features from accelerated segment test (FAST), oriented FAST and rotated binary robust independent elementary features (BRIEF) (ORB), speeded-up robust features (SURF), scale invariant feature transform (SIFT), and binary robust invariant scalable keypoints (BRISK)) and five other methods for …


A Ternary Zero-Correlation Zone Sequence Sets Construction Procedure, Mouad Addad, Ali Djebbari Jan 2017

A Ternary Zero-Correlation Zone Sequence Sets Construction Procedure, Mouad Addad, Ali Djebbari

Turkish Journal of Electrical Engineering and Computer Sciences

In the present paper, we propose ternary zero-correlation zone (ZCZ) sequence sets with ideal correlation properties for phase shifts within the ZCZ. The proposed ternary ZCZ sequence sets can be constructed from binary mutually orthogonal complementary sets (MOCS) and ternary perfect sequences.


Thermomechanical Mems Membranes For Fiber Optic Temperature Sensing, Onur Ferhanoğlu Jan 2017

Thermomechanical Mems Membranes For Fiber Optic Temperature Sensing, Onur Ferhanoğlu

Turkish Journal of Electrical Engineering and Computer Sciences

In this study, the design, fabrication, and characterization results of square and circular cross-sectioned, bimaterial microelectromechanical system (MEMS) membranes are presented. The MEMS structures, having width of 250 $\mu $m to 1.5 mm and 1-4 mm$^{2}$ die area, were designed towards integration on a single-mode fiber tip for temperature-sensing. Embedded diffraction grating underneath each membrane allows for interferometric detection of thermomechanical response through backside laser illumination. The displacement of MEMS membranes was monitored under direct heating, revealing 50--1800 nm/$^{\circ}$C thermomechanical sensitivity range. Furthermore, atomic force microscopy-based stiffness measurement on the MEMS membranes revealed a spring constant within 2--30 N/m range. …


Edge Distance Graph Kernel And Its Application To Small Molecule Classification, Mehmet Tan Jan 2017

Edge Distance Graph Kernel And Its Application To Small Molecule Classification, Mehmet Tan

Turkish Journal of Electrical Engineering and Computer Sciences

Graph classification is an important problem in graph mining with various applications in different fields. Kernel methods have been successfully applied to this problem, recently producing promising results. A graph kernel that mostly specifies classification performance has to be defined in order to apply kernel methods to a graph classification problem. Although there are various previously proposed graph kernels, the problem is still worth investigating, as the available kernels are far from perfect. In this paper, we propose a new graph kernel based on a recently proposed concept called edge distance-k graphs. These new graphs are derived from the original …


Investigation Of Adaptive Control Of Robot Manipulators With Uncertain Features For Trajectory Tracking Employing Hil Simulation Technique, Senthil Kumar Jagatheesa Perumal, Senthil Kumar Natarajan Jan 2017

Investigation Of Adaptive Control Of Robot Manipulators With Uncertain Features For Trajectory Tracking Employing Hil Simulation Technique, Senthil Kumar Jagatheesa Perumal, Senthil Kumar Natarajan

Turkish Journal of Electrical Engineering and Computer Sciences

This paper investigates the hardware-in-the-loop (HIL) simulation approach for dynamic control of a three-link rigid robot manipulator that possesses ambiguous dynamics and kinematics. The task with two adaptive control schemes has been realized with the objective of task space trajectory-tracking of the end effector of the robotic manipulator. Both proposed controllers are designed by considering the joint reference velocities and the additional separation property. Based on these, the controllers can be referred to as reference velocity (RV) and reference velocity separation (RVS) adaptive controllers, respectively. The RV adaptive controller can yield better performance with proper alterations, without the cost of …


A Frequency-Reconfigurable Elliptical Monopole Antenna For Cognitive Radio Networks, Santasri Koley, Debjani Mitra Jan 2017

A Frequency-Reconfigurable Elliptical Monopole Antenna For Cognitive Radio Networks, Santasri Koley, Debjani Mitra

Turkish Journal of Electrical Engineering and Computer Sciences

In this paper, an elliptical disk monopole antenna with seven switchable states, including an ultrawideband (UWB) state and six narrowband states, is presented. It consists of an elliptical disk radiator to operate in the UWB mode for cognitive radio (CR) sensing. To operate in the narrowband mode, the antenna is fed through a defected ground structure (DGS) integrated microstrip line. Frequency reconfigurability is achieved by changing the DGS slot length using six electronic switches. The simple proposed design can cover a wide range of frequency bands from 0.75 to 12 GHz, has an omnidirectional radiation pattern with high gain, and …


Safety-Critical Wireless Sensor Networks Under A Polyphase Spreading Sequences Scenario, Poonam Goyal, Brahmjit Singh Jan 2017

Safety-Critical Wireless Sensor Networks Under A Polyphase Spreading Sequences Scenario, Poonam Goyal, Brahmjit Singh

Turkish Journal of Electrical Engineering and Computer Sciences

Reliable communication is a vital issue for safety- and mission-critical wireless sensor network environments such as industrial monitoring, medical care, and battlefield surveillance. These networks require highly accurate and delay-intolerant wireless communications. Under such critical conditions, the chip sequences used in these networks become vulnerable because of channel impairments and other interferences, thereby significantly decreasing overall system performance. In this paper, polyphase sequences are employed at the physical layer of IEEE Standard 802.15.4 to enhance the communication reliability of wireless sensor networks. Through an extensive simulation, it is found that upon applying polyphase sequences, the chip errors are reduced to …


Design And Implementation Of A Six-Port Junction Based On Substrate Integrated Waveguide, Masoud Jafari, Gholamreza Moradi, Reza Sarraf Shirazi, Rashid Mirzavand Jan 2017

Design And Implementation Of A Six-Port Junction Based On Substrate Integrated Waveguide, Masoud Jafari, Gholamreza Moradi, Reza Sarraf Shirazi, Rashid Mirzavand

Turkish Journal of Electrical Engineering and Computer Sciences

A six-port junction based on substrate integrated waveguide technology with high reliability and efficient performance is proposed in a sub-K-band of 21-23.5 GHz. This substrate integrated waveguide (SIW) six-port junction is constructed from three directional couplers and one T-junction power divider as fundamental components in SIW form, where using appropriate via techniques led to -6 dB coupling coefficients and -15 dB return loss. There is good agreement between the simulation and the measurement results.


Support Vector Machines For Predicting The Hamstring And Quadriceps Muscle Strength Of College-Aged Athletes, Mehmet Fati̇h Akay, Fati̇h Abut, Ebru Çeti̇n, İmdat Yarim, Boubacar Sow Jan 2017

Support Vector Machines For Predicting The Hamstring And Quadriceps Muscle Strength Of College-Aged Athletes, Mehmet Fati̇h Akay, Fati̇h Abut, Ebru Çeti̇n, İmdat Yarim, Boubacar Sow

Turkish Journal of Electrical Engineering and Computer Sciences

Hamstring and quadriceps muscles are essential for the performance of athletes in various sport branches. Hamstring muscles control running activities and stabilize the knee during turns or tackles, while quadriceps muscles play an important role in jumping and kicking. Although hamstring and quadriceps muscle strength in athletes can be accurately measured using isokinetic dynamometry, practical difficulties, such as the requirement of nonportable and costly equipment as well as a long period of measurement time, motivate the researcher to predict hamstring and quadriceps muscle strength using promising machine-learning methods. The purpose of this study is to build prediction models for estimating …


Taller Peaks: An Improved Spike Detection Algorithm That Simultaneously Reduces Type I And Type Ii Errors For Wave_Clus, Murat Okatan Jan 2017

Taller Peaks: An Improved Spike Detection Algorithm That Simultaneously Reduces Type I And Type Ii Errors For Wave_Clus, Murat Okatan

Turkish Journal of Electrical Engineering and Computer Sciences

Wave_clus is an unsupervised spike detection and sorting algorithm that has been used in dozens of experimental studies as a spike sorting tool. It is often used as a benchmark for comparing the performance of new spike sorting algorithms. For these reasons, the spike detection performance of Wave_clus is important for both experimental and computational studies that involve spike sorting. Two measures of spike detection performance are the number of false positive detections (type I error) and the number of missed spikes (type II error). Here, a new spike detection algorithm is proposed that reduces the number of misses and …


Application Of Reinforcement Learning For Active Noise Control, Seyed Amir Hoseini Sabzevari, Majid Moavenian Jan 2017

Application Of Reinforcement Learning For Active Noise Control, Seyed Amir Hoseini Sabzevari, Majid Moavenian

Turkish Journal of Electrical Engineering and Computer Sciences

Active noise control (ANC) systems are used to reduce the sound noise level by generating antinoise signals. M-Estimators are widely employed in ANC systems for updating the adaptive FIR filter taps used as the system controller. Observing the state-of-the-art M-estimators design shows that there is a need for further improvements. In this paper, a feedback ANC based on the reinforcement learning (RL) method is proposed. The sensitivity of the constant parameter in the RL method is checked. The effectiveness of the proposed method is proven by comparing the results with previous feedforward studies through computer simulations.