Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Classification (66)
- Deep learning (61)
- Machine learning (60)
- Optimization (60)
- Genetic algorithm (57)
-
- Particle swarm optimization (49)
- Artificial neural network (34)
- Support vector machine (34)
- Feature extraction (32)
- Wireless sensor networks (31)
- Feature selection (28)
- Power quality (27)
- Artificial neural networks (26)
- Fuzzy logic (26)
- Distributed generation (25)
- Induction motor (24)
- Clustering (21)
- Convolutional neural network (20)
- Support vector machines (20)
- Convolutional neural networks (19)
- Image processing (18)
- Neural networks (18)
- Energy efficiency (17)
- Neural network (17)
- Reliability (17)
- Sliding mode control (17)
- Electric vehicle (16)
- Natural language processing (16)
- Renewable energy (16)
- Artificial bee colony (15)
Articles 1171 - 1200 of 3020
Full-Text Articles in Physical Sciences and Mathematics
Diagnosis Of Reverse Osmosis Desalination Water System Using Bond Graph Approach, Abderrahmene Sallami, Dhia Mzoughi, Abdelkader Mami
Diagnosis Of Reverse Osmosis Desalination Water System Using Bond Graph Approach, Abderrahmene Sallami, Dhia Mzoughi, Abdelkader Mami
Turkish Journal of Electrical Engineering and Computer Sciences
Industrial systems have become quite complicated. It is therefore necessary to look for a reliable supervision system to properly treat the information and make the appropriate decision to stop the system or leave it in operation. Supervision of automated systems goes to the heart of the matter. This paper concerns the design of a new methodology for diagnosis based on bond graph modeling. We apply a diagnostic method by Luenberger observer using the bond graph approach on a desalination unit. Tests are carried out on the water input pressure delivered by the pump and the output flow rates of the …
Model Predictive Control Of A Dual Induction Motor Drive Fed By A Single Voltage Source Inverter, Muhammad Abbas Abbasi, Abdul Rashid Bin Husain
Model Predictive Control Of A Dual Induction Motor Drive Fed By A Single Voltage Source Inverter, Muhammad Abbas Abbasi, Abdul Rashid Bin Husain
Turkish Journal of Electrical Engineering and Computer Sciences
In dual induction motor control applications, averaging of controlled variables, mean circuit models, or master/slave strategies are used, which lead to unbalanced and unstable operation of the overall drive system. An improved finite control set predictive torque control (FCS-PTC) method is proposed for the parallel operation of two induction motors. The optimization cost function of the controller is shown to meet multiple objectives simultaneously, eliminating the use of averaging techniques and without leading to unbalanced conditions. The simulation results are compared with direct torque control (DTC) for dual induction motors. As compared to DTC, model predictive control shows low torque …
Özyeğin Biopsy Robot: System Integration Architecture And Motion Compensation Of A Moving Target, Awais Ahmad, Özkan Bebek
Özyeğin Biopsy Robot: System Integration Architecture And Motion Compensation Of A Moving Target, Awais Ahmad, Özkan Bebek
Turkish Journal of Electrical Engineering and Computer Sciences
This paper presents the complete system architecture of a robotic biopsy system for real-time operations. The system has individual functional blocks working simultaneously including a 5 DoF parallel robot, ultrasound (US) imaging machine, two robotic manipulators, and a motion capturing system. Details of the real-time functionality of the robotic system components working with spatial and computational synchronization are presented. This paper also deals with a scenario in which the target tissue is moving due to the breathing of the patient. The motion of the needle tip and the target is tracked using US images as feedback. Two types of control …
Anomaly Detection Through Keystroke And Tap Dynamics Implemented Via Machine Learning Algorithms, Hani Jawed, Zara Ziad, Muhammad Mubashir Khan, Maheen Asrar
Anomaly Detection Through Keystroke And Tap Dynamics Implemented Via Machine Learning Algorithms, Hani Jawed, Zara Ziad, Muhammad Mubashir Khan, Maheen Asrar
Turkish Journal of Electrical Engineering and Computer Sciences
In our world of growing machine intelligence and increasing security risks, there is a dire need for authentication to be liberated from password dependency and restrictions. This paper discusses the implementation of keystroke biometrics to enhance security using machine-learning algorithms on both Windows and Android. Our research analyzes a user's behavior for authorization purposes by capturing the user's typing pattern. The system extracts several features from the user's typing pattern to apply unary classification for user behavior analysis so that we can detect unauthorized users. Our system implements machine learning on tap dynamics in Android, allowing both training and prediction …
Reliable Data Gathering In The Internet Of Things Using Artificial Bee Colony, Samad Najjar-Ghabel, Shamim Yousefi, Leili Farzinvash
Reliable Data Gathering In The Internet Of Things Using Artificial Bee Colony, Samad Najjar-Ghabel, Shamim Yousefi, Leili Farzinvash
Turkish Journal of Electrical Engineering and Computer Sciences
The Internet of Things (IoT) technology enables physical devices to communicate with each other for preparing, gathering, and sharing hazard warnings or critical information without human intervention. With respect to emergency applications of IoT technology, an essential issue is to provide an efficient and robust scheme for data gathering. The proposed solution in the existing approaches is to construct a spanning tree over the IoT devices and collect data using the tree. The shortcoming of these algorithms is that they do not take into account the probability of device mobility or failure. In such cases, the spanning tree is split, …
Compact Microstrip Lowpass Filter With Ultrasharp Response Using A Square-Loaded Modified T-Shaped Resonator, Ali Pirasteh, Saeed Roshani, Sobhan Roshani
Compact Microstrip Lowpass Filter With Ultrasharp Response Using A Square-Loaded Modified T-Shaped Resonator, Ali Pirasteh, Saeed Roshani, Sobhan Roshani
Turkish Journal of Electrical Engineering and Computer Sciences
A miniaturized lowpass filter (LPF) with ultrasharp response, good figure of merit (FOM), and simple structure is proposed. The designed structure is fabricated and measured with a 2.9 GHz cut-off frequency. The proposed LPF consists of high impedance lines that are loaded by three similar resonators and two uniform suppressing cells. The filter size is only 0.08~$\times $~0.23~$\lambda $g, which indicates small circuit size. The proposed design exhibits good features, such as an ultrasharp roll-off rate of about 1609 dB/GHz and a good FOM of 162,820. The insertion loss of the proposed LPF is less than 0.14 dB in the …
Simulation Of Infinite Periodic Graphene Planar Grating In The Thz Range By The Method Of Singular Integral Equations, Mstislav Kaliberda, Leonid Lytvynenko, Sergey Pogarsky
Simulation Of Infinite Periodic Graphene Planar Grating In The Thz Range By The Method Of Singular Integral Equations, Mstislav Kaliberda, Leonid Lytvynenko, Sergey Pogarsky
Turkish Journal of Electrical Engineering and Computer Sciences
Plane wave diffraction by the infinite periodic planar graphene grating and infinite grating above a perfectly conducting plane in the THz range is considered. The mathematical model is based on the graphene surface impedance and the method of singular integral equations. A comparison with finite grating is made. Reflectance, transmittance, and absorbance are studied as a function of graphene and grating parameters.
A Model Of Qos Differentiation Burst Assembly With Padding For Improving The Performance Of Obs Networks, Viet Minh Nhat Vo, Van Hoa Le, Hoang Son Nguyen, Manh Thanh Le
A Model Of Qos Differentiation Burst Assembly With Padding For Improving The Performance Of Obs Networks, Viet Minh Nhat Vo, Van Hoa Le, Hoang Son Nguyen, Manh Thanh Le
Turkish Journal of Electrical Engineering and Computer Sciences
Burst assembly is an operation at the ingress node of optical burst switching (OBS) networks that aggregates incoming packets from various access networks into larger carriers, called bursts. Depending on the density of incoming packets and the preset time or length thresholds, the completed bursts may have various lengths, but they must be at least equal to a minimum value ($B_{\min})$ to facilitate the switching in existing physical optical switches. If a completed burst is smaller than $B_{\min}$, it should be padded by padded bytes and it results in bandwidth utilization inefficiency. One solution to the problem is increasing the …
Grid-Connected Quasi-Z-Source Inverter With Battery, Umesh Shinde, Sagar Kottagattu, Sumant Kadwane, Snehal Gawande
Grid-Connected Quasi-Z-Source Inverter With Battery, Umesh Shinde, Sagar Kottagattu, Sumant Kadwane, Snehal Gawande
Turkish Journal of Electrical Engineering and Computer Sciences
Grid-connected inverters are now increasingly used in distributed microgrid and smart-grid applications. The advantages of a quasi-Z-source inverter (QZSI), like single-stage operation, lower component rating, continuous input current, and common DC rail, led to an investigation of this converter for grid-connected applications. This paper presents a grid-connected QZSI with both AC and DC side controls. A new battery-charging configuration is also suggested across the capacitor through which the DC side control loop is regulated. Fast dynamic response and reduced harmonics are demonstrated through simulation and experimental results.
Sar Image Denoising Based On Patch Ordering In Nonsubsample Shearlet Domain, Shuaiqi Liu, Qi Hu, Pengfei Li, Jie Zhao, Zhihui Zhu
Sar Image Denoising Based On Patch Ordering In Nonsubsample Shearlet Domain, Shuaiqi Liu, Qi Hu, Pengfei Li, Jie Zhao, Zhihui Zhu
Turkish Journal of Electrical Engineering and Computer Sciences
Synthetic aperture radar (SAR) has been extensively adopted in a variety of fields, e.g., agriculture and marine fields. In this regard, the improvement of SAR image quality has aroused a wide concern worldwide. In recent years, image processing based on local patches has been very popular and proven feasible. In this paper, a novel SAR image denoising algorithm is proposed in the NSST domain on the basis of patch ordering. First, the shearlet transform is applied to logarithmic transformation of the noisy SAR image. Second, the coefficients of the shearlet are denoised respectively by combining patch ordering and 1D filtering. …
Novel Low-Loss Microstrip Triplexer Using Coupled Lines And Step Impedance Cells For 4g And Wimax Applications, Abbas Rezaei, Leila Noori
Novel Low-Loss Microstrip Triplexer Using Coupled Lines And Step Impedance Cells For 4g And Wimax Applications, Abbas Rezaei, Leila Noori
Turkish Journal of Electrical Engineering and Computer Sciences
In this paper, a new microstrip triplexer with flexible resonance frequencies is designed based on the properties of coupled lines, steps, and spiral cells. It operates at 2.67 GHz for 4G LTE and at 3.1 GHz and 3.43 GHz for IEEE 802.16 WiMAX. The close resonance frequencies make it suitable for frequency division duplex applications. In order to improve insertion loss, the LC equivalent circuit of the proposed resonator is analyzed. Moreover, careful alignment of the coupled lines and step impedance structures is performed to improve the insertion and return losses so that they are 0.72/0.63/0.81 dB and 24.5/24/24.7 dB, …
Study On Variability Smoothing Benefits Of Wind Farm Cluster, Xuemei Dai, Kaifeng Zhang, Jian Geng, Qianqian Liu, Ying Wang, Yuan Kun, Yahui Qiao, Yonghui Liu
Study On Variability Smoothing Benefits Of Wind Farm Cluster, Xuemei Dai, Kaifeng Zhang, Jian Geng, Qianqian Liu, Ying Wang, Yuan Kun, Yahui Qiao, Yonghui Liu
Turkish Journal of Electrical Engineering and Computer Sciences
Smoothing effect is an important characteristic of large scale wind power. In this paper we analyze the smoothing effect from the prospect of output variability. Specifically, the aggregated output variability of a wind farm cluster may be significantly lower than that of an independent wind farm, and this phenomenon is referred to as the variability smoothing effect. In order to quantitatively analyze the variability smoothing effect, this paper introduces the concept of variability costs and evaluates the variability costs of each wind farm and overall wind farm cluster based on an optimal scheduling model. It is found that the variability …
Automated Citation Sentiment Analysis Using High Order N-Grams: A Preliminary Investigation, Muhammad Touseef Ikram, Muhammad Tanvir Afzal, Naveed Anwer Butt
Automated Citation Sentiment Analysis Using High Order N-Grams: A Preliminary Investigation, Muhammad Touseef Ikram, Muhammad Tanvir Afzal, Naveed Anwer Butt
Turkish Journal of Electrical Engineering and Computer Sciences
Scientific papers hold an association with previous research contributions (i.e. books, journals or conference papers, and web resources) in the form of citations. Citations are deemed as a link or relatedness of the previous work to the cited work. The nature of the cited material could be supportive (positive), contrastive (negative), or objective (neutral). Extraction of the author's sentiment towards the cited scientific articles is an emerging research discipline due to various linguistic differences between the citation sentences and other domains of sentiment analysis. In this paper, we propose a technique for the identification of the sentiment of the citing …
Performance Analysis Of Distributed Fiber Raman Amplifiers Employing Higher Order Pumping Schemes In Optical Transmission Systems, Kulwinder Singh Malhi, Manjeet Singh Patterh, Manjit Singh Bhamrah
Performance Analysis Of Distributed Fiber Raman Amplifiers Employing Higher Order Pumping Schemes In Optical Transmission Systems, Kulwinder Singh Malhi, Manjeet Singh Patterh, Manjit Singh Bhamrah
Turkish Journal of Electrical Engineering and Computer Sciences
Performance of fiber Raman amplifier is explored with special emphasis on higher order pumping configurations for wavelength division multiplexed optical transmission systems. The amplification analysis is done in terms of equivalent noise figure (ENF), optical signal-to-noise ratio (OSNR), and double Rayleigh backscattering (DRBS) noise powers. The investigations reveal that at 36 dB on--off gain, ENF improvement of 1 dB (using second order pumping) and of 2 dB (using third order pumping configuration) can be achieved. On similar lines, by varying input optical power and fiber length, OSNR and DRBS are reported for the higher order of pumping configurations. Overall, the …
Ionolab-Map: An Automatic Spatial Interpolation Algorithm For Total Electron Content, Muhammet Necat Devi̇ren, Feza Arikan
Ionolab-Map: An Automatic Spatial Interpolation Algorithm For Total Electron Content, Muhammet Necat Devi̇ren, Feza Arikan
Turkish Journal of Electrical Engineering and Computer Sciences
Investigation of the variability of total electron content (TEC) is one of the most important parameters of the observation and monitoring of space weather, which is the main cause of signal disturbance in space-based communication, positioning, and navigation systems. TEC is defined as the total number of electrons on a ray path. The Global Positioning System (GPS) provides a cost-effective solution for the estimation of TEC. Due to various physical and operational disturbances, TEC may have temporal and spatial domain gaps. Global ionospheric maps (GIMs) provide worldwide TEC with 1- to 2-h temporal resolution and $2.5^{\circ}\, \times 5^{\circ}$ spatial resolution …
Cache-Timing Attacks Without A Profiling Phase, Ali̇ Can Atici, Cemal Yilmaz, Erkay Savaş
Cache-Timing Attacks Without A Profiling Phase, Ali̇ Can Atici, Cemal Yilmaz, Erkay Savaş
Turkish Journal of Electrical Engineering and Computer Sciences
Theoretically secure cryptographic algorithms can be vulnerable to attacks due to their implementation flaws. Bernstein's attack is a well-known cache-timing attack that uses execution times as the side-channel. The major drawback of this attack is that it needs an identical target machine to perform its profiling phase where the attacker models the cache timing-behavior of the target machine. This assumption makes the attack unrealistic in many circumstances. In this work, we present an effective method to eliminate the profiling phase. We propose a methodology to model the cache timing-behavior of the target machine by trying hypothetical cache behaviors exhaustively. Our …
Presenting A Method To Perform Cyber Maneuvers, Mohammad Shakibazad, Alijabar Rashidi
Presenting A Method To Perform Cyber Maneuvers, Mohammad Shakibazad, Alijabar Rashidi
Turkish Journal of Electrical Engineering and Computer Sciences
Performing cyber maneuvers in an operational environment is not easy. We need a cyber-situational awareness framework to perform its maneuvers to protect the cyberspace and to cope with its attacks. The battlefield provided has essential information for detecting cybercrime events. The present study resolved the challenges of implementing these maneuvers through dynamic simulation of the cyber battlefield. The cyber battlefield contains detailed information on cyberspace elements, including the vulnerability knowledge repository, the tangible and intangible components of the cyberspace allowing maneuvering, penetration testing, injection attacks, tracking attacks, visualization, evaluation of the impact of cyberattacks, and risk evaluation. By injecting attacks …
Reducing Power System Model Dimensions Based On Linearization For Static Analysis, Farid Karbalaei, Maryam Jebreilzadeh, Hamidreza Shahbazi
Reducing Power System Model Dimensions Based On Linearization For Static Analysis, Farid Karbalaei, Maryam Jebreilzadeh, Hamidreza Shahbazi
Turkish Journal of Electrical Engineering and Computer Sciences
A reliable solution for determining the effect of a group of contingencies on a power system is to simulate all of them through load flow. It is impossible to simulate any detailed cases through a complete AC load flow solution because of the high number of possible contingencies. For this reason, system dimension reduction methods, which are based on an equivalent of one part of a system, are being used. In this paper we compare our previously proposed network equivalent method with the 2 well-known equivalent methods of Ward and Ward-PV in terms of solving speed and accuracy. The proposed …
An Automatic Extraction Algorithm Of High Voltage Transmission Lines From Airborne Lidar Point Cloud Data, Xiaojun Shen, Chuan Qian, Yong Du, Xinle Yu, Rui Zhang
An Automatic Extraction Algorithm Of High Voltage Transmission Lines From Airborne Lidar Point Cloud Data, Xiaojun Shen, Chuan Qian, Yong Du, Xinle Yu, Rui Zhang
Turkish Journal of Electrical Engineering and Computer Sciences
To improve the effectiveness and generality of existing methods of high voltage (HV) transmission lines extraction, this paper proposes a novel automatic extraction method of HV transmission lines using airborne LIDAR point cloud data by incorporating the geography of transmission corridors and the distribution characteristics of airborne LIDAR point cloud data. The proposed method results in the separation of ground objects by using a differentiation height threshold segmentation algorithm based on subspace features, which divide long-distance space into several small-distance space sets to improve the generality of the algorithm. A height density segmentation algorithm is used to locate transmission towers …
Optimal Coordination Of Overcurrent Protection In The Presence Of Sfcl And Distributed Generation, Saeed Asgharigovar, Heresh Seyedi, Shahram Parchehbaf Dibazari
Optimal Coordination Of Overcurrent Protection In The Presence Of Sfcl And Distributed Generation, Saeed Asgharigovar, Heresh Seyedi, Shahram Parchehbaf Dibazari
Turkish Journal of Electrical Engineering and Computer Sciences
As power demand is increased, power generation and especially distributed generation (DG) are being developed. Therefore, power distribution systems become increasingly complicated and short circuit level in distribution grids is being augmented. Thereby, installation of a superconducting fault current limiter (SFCL) is a logical solution to decrease the fault current level in a distribution network. Preventing distribution system degradation by high fault currents, lower equipment ratings, and economic issues are the advantages of SFCL in distribution grids. However, SFCL installation causes delayed operation of the existing overcurrent protection and requires recoordination of the relays. In addition, disconnecting the SFCL from …
Application Of Domination Integrity Of Graphs In Pmu Placement In Electric Power Networks, Mariappan Saravanan, Ramalingam Sujatha, Raman Sundareswaran, Muthu Selvan Balasubramanian
Application Of Domination Integrity Of Graphs In Pmu Placement In Electric Power Networks, Mariappan Saravanan, Ramalingam Sujatha, Raman Sundareswaran, Muthu Selvan Balasubramanian
Turkish Journal of Electrical Engineering and Computer Sciences
In this paper, we propose the application of the concept of power domination integrity to an electric power network. A phasor measurement unit (PMU) is used to analyze and control the power system by measuring voltage phase in electrical nodes and transmission lines. Due to the high cost of PMUs, it is necessary to minimize the number of PMUs such that the depth of observability is ensured. Placing PMUs in a network can be formulated as a graph theoretic problem of finding the minimum number of nodes (PMUs) in a graph that has a maximum number of links with other …
Research On Power-Frequency Electromagnetic Interference Model Of Multicore Twisted Signal Cable Of High-Speed Railway, Bowen Zhang, Jiangjian Xie, Zhixin Wang, Jin Yang, Hao Yan
Research On Power-Frequency Electromagnetic Interference Model Of Multicore Twisted Signal Cable Of High-Speed Railway, Bowen Zhang, Jiangjian Xie, Zhixin Wang, Jin Yang, Hao Yan
Turkish Journal of Electrical Engineering and Computer Sciences
With the increase in the traction power of high-speed railways, the power-frequency electromagnetic interference of traction current to the signal cables becomes increasingly more severe. In this paper, the calculation model of the magnetic interference to signal cable was established on the MATLAB/Simulink platform based on the multiconductor transmission line theory. This model took SPTYWPL03-8B 8-core twist signal cable as an example and the power-frequency interference of external current to the signal cable was analyzed theoretically. In addition, experiments on electromagnetic interference of double-ended and single-ended signal cables were performed to validate the simulation model. Experiments showed that the relative …
Real-Time Power System Dynamic Security Assessment Based On Advanced Feature Selection For Decision Tree Classifiers, Qusay Al-Gubri, Mohd Aifaa Mohd Ariff
Real-Time Power System Dynamic Security Assessment Based On Advanced Feature Selection For Decision Tree Classifiers, Qusay Al-Gubri, Mohd Aifaa Mohd Ariff
Turkish Journal of Electrical Engineering and Computer Sciences
This paper proposes a novel algorithm based on an advanced feature selection technique for the decision tree (DT) classifier to assess the dynamic security in a power system. The proposed methodology utilizes symmetrical uncertainty (SU) to reduce the data redundancy in a dataset for DT classifier-based dynamic security assessment (DSA) tools. The results show that SU reduces the dimension of the dataset used for DSA significantly. Subsequently, the approach improves the performance of the DT classifier. The effectiveness of the proposed technique is demonstrated on the modified IEEE 30-bus test system model. The results show that the DT classifier with …
A Novel Single-Inductor Eight-Channel Light-Emitting Diode Driver For Low Power Display Backlight Applications, Magesh Kannan Parthasarathy, Nagarajan Ganesan
A Novel Single-Inductor Eight-Channel Light-Emitting Diode Driver For Low Power Display Backlight Applications, Magesh Kannan Parthasarathy, Nagarajan Ganesan
Turkish Journal of Electrical Engineering and Computer Sciences
A novel decoder-based single-inductor eight-channel light-emitting diode (LED) driver circuit for low power display backlight applications has been proposed. Uniform brightness in the display provides better picture clarity, which can be achieved by providing uniform DC currents to all channels in the backlight arrangement. Existing systems use individual current regulators for each channel, which fails to provide uniform current to individual channels. Instead, uniform current is provided to all eight channels in the proposed system as the same current is distributed to all channels using time-multiplexing by a 3 $\times $ 8 decoder and a 3-bit binary up-counter. A digital …
Sf6 Gas-Insulated 50-Kva Distribution Transformer Design, Okan Özgönenel, David Thomas, Ünal Kurt
Sf6 Gas-Insulated 50-Kva Distribution Transformer Design, Okan Özgönenel, David Thomas, Ünal Kurt
Turkish Journal of Electrical Engineering and Computer Sciences
There are increasing environmental concerns such that governments are pressured to cooperate with international concurrences. One of the most harmful contaminants is mineral oil when it infiltrates the soil. Although it is a good material in the act of insulating in distribution/power transformers, it presents some environmental hazards and safety disadvantages. For this reason, gas-insulated transformers are considered particularly for hazardous locations. An oil-insulated distribution transformer of 50 kVA, 34.5/0.4 kV, and 50 Hz is investigated and converted to SF6 gas-insulated transformer in this study. The suggested distribution transformer model with SF6 insulated has many benefits, such as being explosion-proof …
Region Characteristics-Based Fusion Of Spatial And Transform Domain Image Denoising Methods, Rajiv Verma, Rajoo Pandey
Region Characteristics-Based Fusion Of Spatial And Transform Domain Image Denoising Methods, Rajiv Verma, Rajoo Pandey
Turkish Journal of Electrical Engineering and Computer Sciences
Nonlocal means (NLM)- and wavelet-based image denoising methods have drawn much attention in image processing due to their effectiveness and simplicity. The performance of these algorithms varies according to region characteristics in an image. For example, NLM performs well for smooth regions due to deployment of redundancy available in images, whereas wavelet-based approaches may preserve key image features by controlling the degree of threshold for shrinking the noisy coefficients. This paper presents a simple novel approach that estimates an original image by simply taking the weighted average of the denoised images pixel values obtained by NLM and wavelet thresholding schemes …
Adaptive Bit-Plane Selection-Based Low Complexity Motion Estimation For Screen Content Coding, Ramazan Duvar, Oğuzhan Urhan
Adaptive Bit-Plane Selection-Based Low Complexity Motion Estimation For Screen Content Coding, Ramazan Duvar, Oğuzhan Urhan
Turkish Journal of Electrical Engineering and Computer Sciences
Screen content video coding has become an emerging research topic with the spread of applications such as cloud gaming, screen/desktop virtualization, and mobile or external display interfacing. Screen content videos have different features compared to conventional camcorder-captured scenes. In this work, a novel low bit-depth representation-based motion estimation approach is proposed to exploit screen content specific features to improve coding efficiency. The proposed approach is based on an adaptive selection of Gray-coded bit-planes in order to generate low bit-depth representation of original screen content frames. The experimental results show that the motion estimation performance of the proposed approach is significantly …
Large Vocabulary Recognition For Online Turkish Handwriting With Sublexical Units, Esma Fatima Bi̇lgi̇n Taşdemi̇r, Ayşe Berri̇n Yanikoğlu Yeşi̇lyurt
Large Vocabulary Recognition For Online Turkish Handwriting With Sublexical Units, Esma Fatima Bi̇lgi̇n Taşdemi̇r, Ayşe Berri̇n Yanikoğlu Yeşi̇lyurt
Turkish Journal of Electrical Engineering and Computer Sciences
We present a system for large vocabulary recognition of online Turkish handwriting, using hidden Markov models. While using a traditional approach for the recognizer, we have identified and developed solutions for the main problems specific to Turkish handwriting recognition. % First, since large amounts of Turkish handwriting samples are not available, the system is trained and optimized using the large UNIPEN dataset of English handwriting, before extending it to Turkish using a small Turkish dataset. % The delayed strokes, which pose a significant source of variation in writing order due to the large number of diacritical marks in Turkish, are …
A Low-Complexity Rare-Based 2-D Doa Estimation Algorithm For A Mixture Of Circular And Strictly Noncircular Sources, Kashif Shabir, Tarek Hasan Al Mahmud, Rui Zheng, Zhongfu Ye
A Low-Complexity Rare-Based 2-D Doa Estimation Algorithm For A Mixture Of Circular And Strictly Noncircular Sources, Kashif Shabir, Tarek Hasan Al Mahmud, Rui Zheng, Zhongfu Ye
Turkish Journal of Electrical Engineering and Computer Sciences
A new rank reduction (RARE)-based two-dimensional (2-D) direction of arrival (DOA) estimation algorithm is proposed considering a mixture of circular and strictly noncircular sources. To enhance array aperture, a geometry of three uniform linear arrays is considered and then treated as displaced arrays from a virtual array using a simple linear transformation. The received data and the conjugated counterpart are combined together, exploiting the noncircular property. Both sources can be estimated separately by designing and exploiting the distinctive nature of circular and noncircular steering vectors. However, a 2-D spectrum search would lead to a high computational complexity burden. To reduce …
Deep Learning Based Brain Tumor Classification And Detection System, Ali̇ Ari, Davut Hanbay
Deep Learning Based Brain Tumor Classification And Detection System, Ali̇ Ari, Davut Hanbay
Turkish Journal of Electrical Engineering and Computer Sciences
The brain cancer treatment process depends on the physician's experience and knowledge. For this reason, using an automated tumor detection system is extremely important to aid radiologists and physicians to detect brain tumors. The proposed method has three stages, which are preprocessing, the extreme learning machine local receptive fields (ELM-LRF) based tumor classification, and image processing based tumor region extraction. At first, nonlocal means and local smoothing methods were used to remove possible noises. In the second stage, cranial magnetic resonance (MR) images were classified as benign or malignant by using ELM-LRF. In the third stage, the tumors were segmented. …