Detection Of Bga Solder Defects From X-Ray Images Using Deep Neural Network,
2020
TÜBİTAK
Detection Of Bga Solder Defects From X-Ray Images Using Deep Neural Network, Ceren Türer Akdeni̇z, Zümray Ölmez, Tamer Ölmez
Turkish Journal of Electrical Engineering and Computer Sciences
In the literature it is observed that complex image processing operations are used in the classification of Ball Grid Array (BGA) X-ray images, however high classification results were not achieved. In recent years, it has been shown that deep learning methods are very successful especially in classification problems. In this study, a new deep neural network (DNN) model is proposed to classify the BGA X-ray images. The proposed DNN model contains feature extractor layers and a minimum distance classifier. Since the proposed network consists of less number of layers (4 convolution layers and 1 fully connected layer), determination of the …
Image Denoising Using Deep Convolutional Autoencoder With Feature Pyramids,
2020
TÜBİTAK
Image Denoising Using Deep Convolutional Autoencoder With Feature Pyramids, Ekrem Çeti̇nkaya, Mustafa Furkan Kiraç
Turkish Journal of Electrical Engineering and Computer Sciences
Image denoising is 1 of the fundamental problems in the image processing field since it is the preliminary step for many computer vision applications. Various approaches have been used for image denoising throughout the years from spatial filtering to model-based approaches. Having outperformed all traditional methods, neural-network-based discriminative methods have gained popularity in recent years. However, most of these methods still struggle to achieve flexibility against various noise levels and types. In this paper, a deep convolutional autoencoder combined with a variant of feature pyramid network is proposed for image denoising. Simulated data generated by Blender software along with corrupted …
Connectivity Considerations For Mission Planning Of A Search And Rescue Drone Team,
2020
TÜBİTAK
Connectivity Considerations For Mission Planning Of A Search And Rescue Drone Team, Evşen Yanmaz Adam
Turkish Journal of Electrical Engineering and Computer Sciences
In this paper, we analyze the mission success performance and mission times of centralized, distributed, and hybrid path-planning methods for a drone team whose mission is to find a target and inform the ground control. We propose two methods that integrate connectivity into the search mission path decisions. We observe that even though the coverage path-planning leads to lower search times, when target connectivity is also required, schemes that incorporate end--end connectivity into path planning result in at least 50 % better mission times for small communication ranges and lower number of drones. Our results also indicate that methods to …
On A Yearly Basis Prediction Of Soil Water Content Utilizing Sar Data: A Machinelearning And Feature Selection Approach,
2020
TÜBİTAK
On A Yearly Basis Prediction Of Soil Water Content Utilizing Sar Data: A Machinelearning And Feature Selection Approach, Emrullah Acar, Mehmet Si̇raç Özerdem
Turkish Journal of Electrical Engineering and Computer Sciences
Soil water content (SWC) performs an important role in many areas including agriculture, drought cases, usage of water resources, hydrology, crop diseases and aerology. However, the measurement of the SWC over large terrains with standard computational techniques is very hard. In order to overcome this situation, remote sensing tools are preferred, which can produce much more successful results in less time than standard calculation techniques. Among all remote sensing tools, synthetic aperture radar (SAR) has a significant impact on determining SWC over large terrains. The main objective of this study is to predict SWC on a yearly basis over the …
Real-Time Anomaly Detection And Mitigation Using Streaming Telemetry In Sdn,
2020
TÜBİTAK
Real-Time Anomaly Detection And Mitigation Using Streaming Telemetry In Sdn, Çağdaş Kurt, Osman Ayhan Erdem
Turkish Journal of Electrical Engineering and Computer Sciences
Measurement and monitoring are crucial for various network tasks such as traffic engineering, anomaly detection, and intrusion prevention. The success of critical capabilities such as anomaly detection and prevention depends on whether the utilized network measurement method is able to provide granular, near real-time, low-overhead measurement data or not. In addition to the measurement method, the anomaly detection and mitigation algorithm is also essential for recognizing normal and abnormal traffic patterns in such a huge amount of measured data with high accuracy and low latency. Software-defined networking is an emerging concept to enable programmable and efficient measurement functions for these …
An Electrothermal Current Prediction Method For Overload Protection Of Miniaturecircuit Breakers,
2020
TÜBİTAK
An Electrothermal Current Prediction Method For Overload Protection Of Miniaturecircuit Breakers, Sen Lyu, Ming Zong
Turkish Journal of Electrical Engineering and Computer Sciences
Traditional miniature circuit breakers (MCBs) cannot meet the requirement for the intelligence of distributing apparatuses in a smart grid. The intellectualization of MCBs is restricted due to the lack of appropriate current measurement methods. Thus, an electrothermal current prediction method is proposed based on the derived relationship between root-mean-square (RMS) current and steady-state temperature rise. A fast acquisition algorithm is used to obtain the required temperature rise before thermal equilibrium to highly reduce the total time consumption. The presented prediction method is found immunized against the ambient temperature. The theory is validated with experiments using a thermostat. The tested steady-state …
Low-Profile Folded Dipole Uhf Rfid Tag Antenna With Outer Strip Lines Formetal Mounting Application,
2020
TÜBİTAK
Low-Profile Folded Dipole Uhf Rfid Tag Antenna With Outer Strip Lines Formetal Mounting Application, Fuad Erman, Effariza Hanafi, Eng-Hock Lim, Wan Amirul Wan Mohd Mahyiddin, Sulaiman Wadi Harun, Mohamad Sofian Abu Talip, Rawan Soboh, Hassan Umair
Turkish Journal of Electrical Engineering and Computer Sciences
A metal mountable UHF RFID tag antenna with a low-profile folded dipole structure is proposed. It is fabricated on a single layer of polytetrafluoroethylene (PTFE) dielectric laminate. It is composed of two symmetrical C-shape resonators integrated with the outer strip lines. The IC chip's terminals are connected directly to the center of the C-shaped resonators. The outer strip lines are integrated with the C-shaped resonators, which function to lower the reflection coefficient so as to match the IC chip impedance. In particular, the outer strip lines increase the inductive reactance of the antenna impedance in order to realize IC chip …
Mutant Selection By Using Fourier Expansion,
2020
TÜBİTAK
Mutant Selection By Using Fourier Expansion, Savaş Takan, Tolga Ayav
Turkish Journal of Electrical Engineering and Computer Sciences
Mutation analysis is a widely used technique to evaluate the effectiveness of test cases in both hardware and software testing. The original model is mutated systematically under certain fault assumptions and test cases are checked against the mutants created to see whether the test cases can detect the faults or not. Mutation analysis is usually a computationally intensive task, particularly in finite state machine (FSM) testing due to a possibly huge amount of mutants. Random selection could be a practical reduction method under the assumption that each mutant is identical in terms of the probability of occurrence of its associating …
A Supervised Learning Approach For Detecting Erroneoussamples In Embeddings,
2020
TÜBİTAK
A Supervised Learning Approach For Detecting Erroneoussamples In Embeddings, Görkem Saygili
Turkish Journal of Electrical Engineering and Computer Sciences
Visualizing multidimensional data has been a crucial task in recent years regarding the growing amount of data from various sources. To achieve this, dimensionality reduction algorithms have been used to reduce the number of dimensions for visualization of the data on a screen. However, these algorithms may fail to faithfully represent high dimensional data in lower dimensions and eventually lead to erroneous visualizations. In this work, we propose an error detection algorithm for dimensionality reduction algorithms based on recently developed error prediction algorithms for medical image registration. The proposed algorithm matches the neighborhoods of high and low dimensional data with …
Distribution Network Reconfiguration Based On Artificial Networkreconfiguration For Variable Load Profile,
2020
TÜBİTAK
Distribution Network Reconfiguration Based On Artificial Networkreconfiguration For Variable Load Profile, Hesham Hanie Youssef, Hazlie Bin Mokhlis, Mohamad Sofian Abu Talip, Mohammad Alsamman, Munir Azam Muhammad, Nurulafiqah Nadzirah Mansor
Turkish Journal of Electrical Engineering and Computer Sciences
Network reconfiguration is a process to change the open-switches in distribution system for a minimum power loss. In the past, metaheuristic techniques were applied widely for network reconfiguration with consideration of a fixed loading profile. When the loading changes, the current configuration may not be the optimal one. Thus, the technique needs to be executed to find a new optimal configuration based on the latest loading. The process is time-consuming since metaheuristic techniques commonly require high computational times and produces inconsistent results. Therefore, this paper proposes a network reconfiguration technique based on artificial neural network (ANN) for variable loading conditions. …
A Novel Grouping Proof Authentication Protocol For Lightweight Devices:Gpapxr+,
2020
TÜBİTAK
A Novel Grouping Proof Authentication Protocol For Lightweight Devices:Gpapxr+, Ömer Aydin, Gökhan Dalkiliç, Cem Kösemen
Turkish Journal of Electrical Engineering and Computer Sciences
Radio frequency identification (RFID) tags that meet EPC Gen2 standards are used in many fields such as supply chain operations. The number of the RFID tags, smart cards, wireless sensor nodes, and Internet of things devices is increasing day by day and the areas where they are used are expanding. These devices are very limited in terms of the resources they have. For this reason, many security mechanisms developed for existing computer systems cannot be used for these devices. In order to ensure secure communication, it is necessary to provide authentication process between these lightweight devices and the devices they …
Exploring The Parameter Space Of Human Activity Recognition With Mobile Devices,
2020
TÜBİTAK
Exploring The Parameter Space Of Human Activity Recognition With Mobile Devices, Berrenur Saylam, Muhammad Shoaib, Özlem Durmaz İncel
Turkish Journal of Electrical Engineering and Computer Sciences
Motion sensors available on smart phones make it possible to recognize human activities. Accelerometer, gyroscope, magnetometer, and their various combinations are used to classify, particularly, locomotion activities, ranging from walking to biking. In most of the studies, the focus is on the collection of data and on the analysis of the impact of different parameters on the recognition performance. The parameter space includes the types of sensors used, features, classification algorithms, and position/orientation of the mobile device. In most of the studies, the impact of some of these parameters is partially analyzed; however, in this work, we investigate the parameter …
Optimization Of Real-Time Wireless Sensor Based Big Data With Deep Autoencoder Network: A Tourism Sector Application With Distributed Computing, Beki̇r Aksoy, Utku Kose
Turkish Journal of Electrical Engineering and Computer Sciences
Internet usage has increased rapidly with the development of information communication technologies. The increase in internet usage led to the growth of data volumes on the internet and the emergence of the big data concept. Therefore, it has become even more important to analyze the data and make it meaningful. In this study, 690 million queries and approximately 5.9 quadrillion data collected daily from different servers were recorded on the Redis servers by using real-time big data analysis method and load balance structure for a company operating in the tourism sector. Here, wireless networks were used as a triggering factor …
Efficient Turkish Tweet Classification System For Crisis Response,
2020
TÜBİTAK
Efficient Turkish Tweet Classification System For Crisis Response, Saed Alqaraleh, Merve Işik
Turkish Journal of Electrical Engineering and Computer Sciences
This paper presents a convolutional neural networks Turkish tweet classification system for crisis response. This system has the ability to classify the present information before or during any crisis. In addition, a preprocessing model was also implemented and integrated as a part of the developed system. This paper presents the first ever Turkish tweet dataset for crisis response, which can be widely used and improve similar studies. This dataset has been carefully preprocessed, annotated, and well organized. It is suitable to be used by all the well-known natural language processing tools. Extensive experimental work, using our produced Turkish tweet dataset …
Influence Of Varying Magnet Pole-Arcs And Step-Skew On Permanent Magnet Ac Synchronous Motor Performance,
2020
TÜBİTAK
Influence Of Varying Magnet Pole-Arcs And Step-Skew On Permanent Magnet Ac Synchronous Motor Performance, Meti̇n Aydin, Oğuzhan Ocak, Yücel Demi̇r
Turkish Journal of Electrical Engineering and Computer Sciences
Minimization or elimination of cogging torque is a significant issue in permanent magnet (PM) motor design process. There are some design techniques to reduce or eliminate this unwanted torque components in PM motors. This paper focuses on two different design techniques, varying magnet pole-arc and step-skew, to reduce cogging torque component in radial flux PM synchronous motors. Different design points which consider pulsating torque components and back-EMF harmonics are obtained via finite element analysis (FEA) for a low power industrial PM motor. A prototype motor is manufactured for one of the desired designs and is tested experimentally. Good agreement is …
A New Smart Networking Architecture For Container Network Functions,
2020
TÜBİTAK
A New Smart Networking Architecture For Container Network Functions, Gülsüm Atici, Pinar Bölük
Turkish Journal of Electrical Engineering and Computer Sciences
5G slices have challenging application demands from a wide variety of fields including high bandwidth, low latency and reliability. The requirements of the container network functions which are used in telecommunications are different from any other cloud native IT applications as they are used for data plane packet processing functions, together with control, signalling and media processing which have critical processing requirements. This study aims to discover high performing container networking solution by considering traffic loads and application types. The behaviour of several container cluster networking solutions -- Flannel, Weave, Libnetwork, Open Virtual Networking for Open vSwitch and Calico -- …
Techno-Economic Analysis Of Diethyl Ether Production Via Catalytic Dehydration Of Ethanol,
2020
Faculty of Engineering
Techno-Economic Analysis Of Diethyl Ether Production Via Catalytic Dehydration Of Ethanol, Boonraksa Chaiapha
Chulalongkorn University Theses and Dissertations (Chula ETD)
The major source of energy comes from non-renewable fuels, which have a non-sustainability and negative impact on the environment. Thus, there is change to renewable fuels as bioethanol. Diethyl ether (DEE) is a part of bioethanol. However, the increase of electric vehicles (EV) may decrease ethanol demand for biofuel in the future. Thus, it will be interesting in adding value to ethanol via the catalytic dehydration to produce DEE by conduct techno-economic analysis. Further, there is comparison on different concentrations of ethanol (93% and 95% ethanol) that affect DEE production. For simulation part, the DEE capacity of 3,600 tons/year is …
Characteristics Improvement Of Quantum Dot Semiconductor Optical Amplifier For Access Network,
2020
Faculty of Engineering
Characteristics Improvement Of Quantum Dot Semiconductor Optical Amplifier For Access Network, Budsara Boriboon
Chulalongkorn University Theses and Dissertations (Chula ETD)
This thesis presents the characteristics improvement and performance evaluation of Quantum Dot Semiconductor Optical Amplifier (QD SOA) in an access network. There are 3 parts: 1) improvement of internal quantum efficiency, 2) increase of chip gain and 3) implementation of QD SOA in 40 Gb/s access network. The first part, Rapid Thermal Annealing (RTA) is applied to improve internal quantum efficiency to be 1.4 times higher than without RTA and low optical loss. The second part, strain compensation technique is applied to increase the chip gain of QD SOA. Considering the design of Quantum Dot Laser Diode with optimized stacked …
A Robust System For Core Thai Natural Language Processing Technologies,
2020
Faculty of Engineering
A Robust System For Core Thai Natural Language Processing Technologies, Can Udomcharoenchaikit
Chulalongkorn University Theses and Dissertations (Chula ETD)
As the amount of unstructured textual data grows, it becomes increasingly important to build an intelligent system that can process it. Natural Language Processing (NLP) is a technology that allows a computer to exploit human languages to perform tasks. Deep learning models have shown excellent results across fundamental tasks in NLP, such as word segmentation, part-of-speech tagging, and named-entity recognition. However, in many situations, these proposed methods fail to perform well. For an NLP system to be robust, it must address issues such as out-of-vocabulary and spelling-mistakes. This thesis's research goal is to develop NLP models that can handle malformed …
Semi-Supervised Thai Sentence Segmentation Using Local And Distant Word Representations,
2020
Faculty of Engineering
Semi-Supervised Thai Sentence Segmentation Using Local And Distant Word Representations, Chanatip Saetia
Chulalongkorn University Theses and Dissertations (Chula ETD)
A sentence is typically treated as the minimal syntactic unit used for extracting valuable information from a longer piece of text. However, in written Thai, there are no explicit sentence markers. We proposed a deep learning model for the task of sentence segmentation that includes three main contributions. First, we integrate n-gram embedding as a local representation to capture word groups near sentence boundaries. Second, to focus on the keywords of dependent clauses, we combine the model with a distant representation obtained from self-attention modules. Finally, due to the scarcity of labeled data, for which annotation is difficult and time-consuming, …
