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 6781 - 6810 of 13574

Full-Text Articles in Computer Engineering

The Effect Of Snowfall And Icing On The Sustainability Of The Power Output Of A Grid-Connected Photovoltaic System In Konya, Turkey, Mehmet Ali̇ Anadol, Erman Erhan Jan 2019

The Effect Of Snowfall And Icing On The Sustainability Of The Power Output Of A Grid-Connected Photovoltaic System In Konya, Turkey, Mehmet Ali̇ Anadol, Erman Erhan

Turkish Journal of Electrical Engineering and Computer Sciences

When the module surface is covered with various factors such as snow and icing which prevent the solar irradiance from reaching the photovoltaic cells, the power production of the system and its performance decrease. The purpose of this study is to determine the energy production losses of a grid-connected photovoltaic plant due to snowfall and icing. The effect of snowfall and icing has been examined on a photovoltaic system consisting of a hybrid inverter with two separate maximum power point tracking inputs and 36 monocrystalline modules, which are mounted on the supporting system horizontally in the south direction and at …

Go to article

A Transmission Optimization Algorithm For Smart Load Controllers, Ohyoung Song Jan 2019

A Transmission Optimization Algorithm For Smart Load Controllers, Ohyoung Song

Turkish Journal of Electrical Engineering and Computer Sciences

This paper introduces a transmission optimization algorithm for wireless transmissions between smart load controllers and a corresponding gateway in wireless personal area networks, where smart load controllers connect several electrical appliances through their corresponding load interfaces, measure the power consumption from each electrical appliance connected to the load controller, and control on/off switching through its load interface. The aim of this paper is to reduce the traffic load of power consumption data in electrical appliances used in the building area network and the smart grid network. The proposed algorithm allows the smart load controller to efficiently reduce traffic load even …

Go to article

Dynamic Radar Cross-Section Characteristic Analysis Of Wind Turbine Based On Scaled Model Experimental, Bo Tang, Hao Chen, Li Huang, Fa Ting Yuan, Peng Feng Jan 2019

Dynamic Radar Cross-Section Characteristic Analysis Of Wind Turbine Based On Scaled Model Experimental, Bo Tang, Hao Chen, Li Huang, Fa Ting Yuan, Peng Feng

Turkish Journal of Electrical Engineering and Computer Sciences

Accurately acquiring and analyzing the dynamic radar cross-section (RCS) of wind turbine have a great significance to solve the reradiation interference between wind farms and radar stations. Since the results of high-frequency approximation algorithm are only applicable to the qualitative analysis of electromagnetic scattering, it is almost impossible to accurately acquire the dynamic RCS of wind turbine in actual engineering cases. To this end, we proposed to acquire the dynamic RCS of wind turbine based on the scaled model experimental measurement in a large anechoic chamber. The key techniques of setting up the scaled model as well as the experimental …

Go to article

Survey Of Network Embedding Techniques For Social Networks, Pranav Nerurkar, Madhav Chandane, Sunil Bhirud Jan 2019

Survey Of Network Embedding Techniques For Social Networks, Pranav Nerurkar, Madhav Chandane, Sunil Bhirud

Turkish Journal of Electrical Engineering and Computer Sciences

High dimensionality of data is a challenging scenario in the current era as the digital transformation of the society is in process. This problem is particularly complex in social networks as in such systems, it is coupled with other challenges such as interdependency of data points and heterogeneity of data sources. To overcome such disadvantages and aid in creation of downstream applications for social network analysis, network embedding techniques have been proposed. These techniques, in themselves, are not important but are the backbone of various network-based applications. Due to the scientific interest in this domain there has been a mushrooming …

Go to article

Improving Side Lobe Level Of X-Band Microstrip Rotman Lens Utilizing Nonuniform Distribution Of Output Ports, Ehsan Zareian Jahromi, Raheleh Basiri, Parvin Salehi, Hamidreza Karami Jan 2019

Improving Side Lobe Level Of X-Band Microstrip Rotman Lens Utilizing Nonuniform Distribution Of Output Ports, Ehsan Zareian Jahromi, Raheleh Basiri, Parvin Salehi, Hamidreza Karami

Turkish Journal of Electrical Engineering and Computer Sciences

A new microstrip Rotman lens with enhanced side lobe level (SLL) is proposed for X-band applications. A proper nonuniform distribution of the initial width of output ports is considered to improve the SLL. The benefit of SLL improvement is not based on using additional attenuators or amplifiers at the output ports. Moreover, an analytical background is presented to investigate the resulting SLL of the proposed structure. The advantage of SLL enhancement is obtained at all noncorner scan angles considering 10 GHz operating frequency. As the middle input port is excited, more than 3 dB of SLL enhancement is achieved at …

Go to article

Iterative Sensitivity Matrix-Based Magnetic Resonance Conductivity Tensor Imaging, Evren Deği̇rmenci̇ Jan 2019

Iterative Sensitivity Matrix-Based Magnetic Resonance Conductivity Tensor Imaging, Evren Deği̇rmenci̇

Turkish Journal of Electrical Engineering and Computer Sciences

Magnetic resonance conductivity tensor imaging (MRCTI) reconstructs high-resolution anisotropic conductivity images, which are proved to have critical importance in radio-oncological imaging as well as source localization fields. In the MRCTI technique, linearly independent current injections are applied to the region to be imaged and resulting magnetic flux densities are measured using magnetic resonance imaging techniques. In this study, a novel iterative reconstruction algorithm based on a sensitivity matrix approach is proposed and tested using both simulated and experimental measurements. Obtained results show that the proposed technique can reconstruct anisotropic conductivity images with high and position-independent spatial resolution in addition to …

Go to article

A Compact Wide-Slot Uwb Antennawith Reconfigurable And Sharp Dual-Band Notches For Underlay Cognitive Radioapplications, Falih Alnahwi, Abdulghafor Abdulhameed, Husham Swadi, Abdulkareem Abdullah Jan 2019

A Compact Wide-Slot Uwb Antennawith Reconfigurable And Sharp Dual-Band Notches For Underlay Cognitive Radioapplications, Falih Alnahwi, Abdulghafor Abdulhameed, Husham Swadi, Abdulkareem Abdullah

Turkish Journal of Electrical Engineering and Computer Sciences

This paper presents a compact wide-slot ultrawide-band (UWB) antenna with reconfigurable and sharp dual-band notches compatible with the underlay cognitive radio systems. The antenna slot and tuning stub are reshaped in such a way that the proposed antenna operating bandwidth extends along the frequency band specified for UWB applications (3.1-10.6 GHz). In spite of their sharpness, the generated band notches perfectly cancel the interference with the entire 5 GHz wireless local area network (WLAN) frequency band (5.15-5.725 GHz) and that of the military X-band satellite communications downlink (7.25-7.745 GHz). The WLAN band notch is presented by attaching a pair of …

Go to article

A Novel And Unified Approach For Averaged Channel Capacity And Averagedeffective Capacity Analyses Of Diversity Combining And Multihop Transmissionschemes In Flat Fading Environments, Ferkan Yilmaz, Mohamed-Slim Alouini Jan 2019

A Novel And Unified Approach For Averaged Channel Capacity And Averagedeffective Capacity Analyses Of Diversity Combining And Multihop Transmissionschemes In Flat Fading Environments, Ferkan Yilmaz, Mohamed-Slim Alouini

Turkish Journal of Electrical Engineering and Computer Sciences

n this paper, we introduce an Lp -norm aggregation to present a signal-to-noise ratio expression unified not only for such diversity combining schemes as equal-gain combining, maximal-ratio combining, and selection combining, but also for such transmission techniques as multihop transmission. Accordingly, we propose two moment-generating function-based approaches that both respectively unify the exact analyses of the averaged channel capacity and averaged effective capacity over generalized fading channels with respect to the diversity combining and multihop transmission schemes. Finally, the mathematical formalism is illustrated by numerical special cases and verified by simulations.

Go to article

Pipelined Adders For Ultralow-Power Wearables, Mansi Jhamb, Tejaswini Dhall, Tamish Verma, Hinduja Puri Jan 2019

Pipelined Adders For Ultralow-Power Wearables, Mansi Jhamb, Tejaswini Dhall, Tamish Verma, Hinduja Puri

Turkish Journal of Electrical Engineering and Computer Sciences

For continuous real-time monitoring of personal health, wearable devices are indispensable. The constraintsof cost, power consumption, and limited device dimensions are the critical issues which need to be handled carefullywhile designing these battery-powered devices. The wearables employ high-end processors dedicated for complex signalprocessing. The core of every digital signal processor is its data path. The arithmetic units like adders constitute thecore of data path and addressing unit. This work proposes a novel low-complexity asynchronous pipelined adder. Theproposed design guarantees great savings in power and latency, which makes it a suitable candidate for low-power high-speed sophisticated wearables. The proposed design consumes …

Go to article

Contribution Of Artificial Proprioception On A Dynamic Finger Flexion Task, Mehdi Hojatmadani, Evren Samur Jan 2019

Contribution Of Artificial Proprioception On A Dynamic Finger Flexion Task, Mehdi Hojatmadani, Evren Samur

Turkish Journal of Electrical Engineering and Computer Sciences

There has been a considerable effort to provide sensory feedback for myoelectric prostheses. Among the solutions provided in the literature, sensory substitution is an easy and cost-effective way to provide feedback through different sensory modalities at different locations on the body. In this study, we evaluate the effect of sensory substitution of force and position feedback on a two-degree-of-freedom dynamic finger flexion task. For this purpose, a new methodology and an experimental setup are developed. The experimental methodology is based on the "strength-dexterity test", working on the principle of buckling of compression springs. The experimental setup comprises a haptic interface, …

Go to article

Power Electronic Controller With Time Sharing Switching Strategy For Grid Connected Pv Systems, Maria Jenisha Charles, Ammasaigounden Nanjappagounder, Binu Ben Jose Dharmaian Retnam Jan 2019

Power Electronic Controller With Time Sharing Switching Strategy For Grid Connected Pv Systems, Maria Jenisha Charles, Ammasaigounden Nanjappagounder, Binu Ben Jose Dharmaian Retnam

Turkish Journal of Electrical Engineering and Computer Sciences

The design and implementation of a high-efficiency two-stage power electronic controller for feeding power from a photovoltaic (PV) array to the load/utility grid is proposed. The PV array is connected to the load/utility grid through a boost converter and an inverter. The boost converter is controlled by sinusoidal pulse width modulation (SPWM) pulses so as to get a clamped quasi-sinusoidal waveform at the DC link. The inverter converts the clamped quasi-DC voltage into AC voltage using the SPWM controller. At any time only one switch operates at high frequency, thus yielding reduction in the switching losses of the converters. The …

Go to article

Convex Polygon Triangulation Based On Planted Trivalent Binary Tree\\ And Ballot Problem, Muzafer Saracevic, Aybeyan Seli̇mi̇ Jan 2019

Convex Polygon Triangulation Based On Planted Trivalent Binary Tree\\ And Ballot Problem, Muzafer Saracevic, Aybeyan Seli̇mi̇

Turkish Journal of Electrical Engineering and Computer Sciences

This paper presents a new technique of generation of convex polygon triangulation based on planted trivalent binary tree and ballot notation. The properties of the Catalan numbers were examined and their decomposition and application in developing the hierarchy and triangulation trees were analyzed. The method of storage and processing of triangulation was constructed on the basis of movements through the polygon. This method was derived from vertices and leaves of the planted trivalent binary tree. The research subject of the paper is analysis and comparison of a constructed method for solving of convex polygon triangulation problem with other methods and …

Go to article

Improving Anomaly Detection In Bgp Time-Series Data By New Guide Features And Moderated Feature Selection Algorithm, Mahmoud Hashem, Ahmed Bashandy, Samir Shaheen Jan 2019

Improving Anomaly Detection In Bgp Time-Series Data By New Guide Features And Moderated Feature Selection Algorithm, Mahmoud Hashem, Ahmed Bashandy, Samir Shaheen

Turkish Journal of Electrical Engineering and Computer Sciences

The Internet infrastructure relies on the Border Gateway Protocol (BGP) to provide essential routing information where abnormal routing behavior impairs global Internet connectivity and stability. Hence, employing anomaly detection algorithms is important for improving the performance of BGP routing protocol. In this paper, we propose two algorithms; the first is the guide feature generator (GFG), which generates guide features from traditional features in BGP time-series data using moving regression in combination with smoothed moving average. The second is a modified random forest feature selection algorithm which is employed to automatically select the most dominant features (ASMDF). Our mechanism shows that …

Go to article

Detection Of Hemorrhage In Retinal Images Using Linear Classifiers And Iterative Thresholding Approaches Based On Firefly And Particle Swarm Optimization Algorithms, Kemal Adem, Mahmut Heki̇m, Seli̇m Demi̇r Jan 2019

Detection Of Hemorrhage In Retinal Images Using Linear Classifiers And Iterative Thresholding Approaches Based On Firefly And Particle Swarm Optimization Algorithms, Kemal Adem, Mahmut Heki̇m, Seli̇m Demi̇r

Turkish Journal of Electrical Engineering and Computer Sciences

We propose a novel iterative thresholding approach based on firefly and particle swarm optimization to be used for the detection of hemorrhages, one of the signs of diabetic retinopathy disease. This approach consists of the enhancement of the image using basic preprocessing methods, the segmentation of vessels with the help of Gabor and Top-hat transformation for the removal of the vessels from the image, the determination of the number of regions with hemorrhages and pixel counts in these regions using firefly algorithm (FFA) and particle swarm optimization algorithm (PSOA)-based iterative thresholding, and the detection of hemorrhages with the help of …

Go to article

Accurate And Compact Stochastic Computations By Exploiting Correlation, Hamdan Abdellatef, Mohamed Khalil Hani, Nasir Shaikh-Husin Jan 2019

Accurate And Compact Stochastic Computations By Exploiting Correlation, Hamdan Abdellatef, Mohamed Khalil Hani, Nasir Shaikh-Husin

Turkish Journal of Electrical Engineering and Computer Sciences

Recent studies have shown, contrary to what was previously believed, that by exploiting correlation in stochastic computing (SC) designs, more accurate SC circuits with low area cost can be realized. However, if these basic SC circuits or blocks are cascaded in series to form a large complex system, correlation between stochastic numbers (SNs) from one block to the next would be lost; thus, inaccuracies are introduced. In this study, we propose correlating circuits to be used in building complex correlated SC systems. One of the circuits is the correlator that restores lost correlations between two SNs due to previous processing. …

Go to article

Boltzmann Analysis Of Electron Swarm Parameters In Chf3+Cf4 Mixtures, Hidir Düzkaya, Süleyman Sungur Tezcan Jan 2019

Boltzmann Analysis Of Electron Swarm Parameters In Chf3+Cf4 Mixtures, Hidir Düzkaya, Süleyman Sungur Tezcan

Turkish Journal of Electrical Engineering and Computer Sciences

The electron drift velocity, mean energy, ionization, attachment, effective ionization coefficient, limit electrical field, and synergism of pure CHF3 (fluoroform), pure CF4 (tetrafluoromethane), and CHF3+CF4 gas mixtures are calculated by Boltzmann equation analysis in a wide range of density normalized electrical fields (E/N). The finite difference method is used to solve the two-term approximation of the Boltzmann equation under steady-state Townsend conditions. To our knowledge, no previous electron swarm parameters of these mixtures have been published. At constant E/N values, the electron mean energies and drift velocities increase with decreasing CHF3 content. The addition of CF4 into the mixture increases …

Go to article

Synchronization And Antisynchronization Protocol Design Of Chaotic Nonlinear Gyros: An Adaptive Integral Sliding Mode Approach, Fazal Ur Rahman, Qudrat Khan, Rini Akmeliawati Jan 2019

Synchronization And Antisynchronization Protocol Design Of Chaotic Nonlinear Gyros: An Adaptive Integral Sliding Mode Approach, Fazal Ur Rahman, Qudrat Khan, Rini Akmeliawati

Turkish Journal of Electrical Engineering and Computer Sciences

A novel control protocol design, via integral sliding mode control with parameter update laws, for synchronization and desynchronization of a chaotic nonlinear gyro with unknown parameters is the focus of this work. The error dynamics of the actual system are substructured into nominal and uncertain parts to employ adaptive integral sliding mode (AISM) control. The uncertain parameters are estimated via devised adaptive laws. Then the disagreement dynamics are guided to origin via AISM control. The stabilizing controller is also designed in terms of nominal control along with a compensating component. The control and the parameter update laws are constructed to …

Go to article

Exploring Cyber-Physical Systems, Misbah Uddin Mohammed Jan 2019

Exploring Cyber-Physical Systems, Misbah Uddin Mohammed

Graduate Research Theses & Dissertations

The advances in IOT, Computer Vision, AI and Machine Learning have made these technologies ubiquitous to our daily lives. From Smart Phones to Connected Vehicles, Cyber Physical systems have been interspersed into everything we interact in today’s world. The aim or this thesis was to explore these advances in Cyber Physical Systems and analyze the different sectors they were affecting. We then hand-picked certain domains and explored further by carrying out practical projects using some of the latest software and hardware resources available. Technologies like Amazon Alexa services, NVIDIA Jetson boards, TensorFlow, OpenCV, NodeJS were heavily employed in our various …

Go to article

Personal Universes: A Solution To The Multi-Agent Value Alignment Problem, Roman V. Yampolskiy Jan 2019

Personal Universes: A Solution To The Multi-Agent Value Alignment Problem, Roman V. Yampolskiy

Faculty and Staff Scholarship

AI Safety researchers attempting to align values of highly capable intelligent systems with those of humanity face a number of challenges including personal value extraction, multi-agent value merger and finally in-silico encoding. State-of-the-art research in value alignment shows difficulties in every stage in this process, but merger of incompatible preferences is a particularly difficult challenge to overcome. In this paper we assume that the value extraction problem will be solved and propose a possible way to implement an AI solution which optimally aligns with individual preferences of each user. We conclude by analyzing benefits and limitations of the proposed approach.

Go to article

An Explainable Autoencoder For Collaborative Filtering Recommendation, Pegah Sagheb Haghighi, Olurotimi Seton, Olfa Nasraoui Jan 2019

An Explainable Autoencoder For Collaborative Filtering Recommendation, Pegah Sagheb Haghighi, Olurotimi Seton, Olfa Nasraoui

Faculty and Staff Scholarship

Autoencoders are a common building block of Deep Learning architectures, where they are mainly used for representation learning. They have also been successfully used in Collaborative Filtering (CF) recommender systems to predict missing ratings. Unfortunately, like all black box machine learning models, they are unable to explain their outputs. Hence, while predictions from an Autoencoderbased recommender system might be accurate, it might not be clear to the user why a recommendation was generated. In this work, we design an explainable recommendation system using an Autoencoder model whose predictions can be explained using the neighborhood based explanation style. Our preliminary work …

Go to article

Sec-Lib: Protecting Scholarly Digital Libraries From Infected Papers Using Active Machine Learning Framework, Nir Nissim, Aviad Cohen, Jian Wu, Andrea Lanzi, Lior Rokach, Yuval Elovici, Lee Giles Jan 2019

Sec-Lib: Protecting Scholarly Digital Libraries From Infected Papers Using Active Machine Learning Framework, Nir Nissim, Aviad Cohen, Jian Wu, Andrea Lanzi, Lior Rokach, Yuval Elovici, Lee Giles

Computer Science Faculty Publications

Researchers from academia and the corporate-sector rely on scholarly digital libraries to access articles. Attackers take advantage of innocent users who consider the articles' files safe and thus open PDF-files with little concern. In addition, researchers consider scholarly libraries a reliable, trusted, and untainted corpus of papers. For these reasons, scholarly digital libraries are an attractive-target and inadvertently support the proliferation of cyber-attacks launched via malicious PDF-files. In this study, we present related vulnerabilities and malware distribution approaches that exploit the vulnerabilities of scholarly digital libraries. We evaluated over two-million scholarly papers in the CiteSeerX library and found the library …

Go to article

Dedicated Hardware For Machine/Deep Learning: Domain Specific Architectures, Angel Izael Solis Jan 2019

Dedicated Hardware For Machine/Deep Learning: Domain Specific Architectures, Angel Izael Solis

Open Access Theses & Dissertations

Artificial intelligence has come a very long way from being a mere spectacle on the silver screen in the 1920s [Hml18]. As artificial intelligence continues to evolve, and we begin to develop more sophisticated Artificial Neural Networks, the need for specialized and more efficient machines (less computational strain while maintaining the same performance results) becomes increasingly evident. Though these “new” techniques, such as Multilayer Perceptron’s, Convolutional Neural Networks and Recurrent Neural Networks, may seem as if they are on the cutting edge of technology, many of these ideas are over 60 years old! However, many of these earlier models, at …

Go to article

Inception: Virtual Space In Memory Space In Real Space, Peter Casey, Rebecca Lindsay-Decusati, Ibrahim Baggili, Frank Breitinger Jan 2019

Inception: Virtual Space In Memory Space In Real Space, Peter Casey, Rebecca Lindsay-Decusati, Ibrahim Baggili, Frank Breitinger

Electrical & Computer Engineering and Computer Science Faculty Publications

Virtual Reality (VR) has become a reality. With the technology's increased use cases, comes its misuse. Malware affecting the Virtual Environment (VE) may prevent an investigator from ascertaining virtual information from a physical scene, or from traditional “dead” analysis. Following the trend of antiforensics, evidence of an attack may only be found in memory, along with many other volatile data points. Our work provides the primary account for the memory forensics of Immersive VR systems, and in specific the HTC Vive. Our approach is capable of reconstituting artifacts from memory that are relevant to the VE, and is also capable …

Go to article

Thai Spelling Correction And Word Normalization On Social Text Using A Two-Stage Pipeline With Neural Contextual Attention, Anuruth Lertpiya Jan 2019

Thai Spelling Correction And Word Normalization On Social Text Using A Two-Stage Pipeline With Neural Contextual Attention, Anuruth Lertpiya

Chulalongkorn University Theses and Dissertations (Chula ETD)

Text correction systems (e.g., spell checkers) have been used to improve the quality of computerized text by detecting and correcting errors. However, the task of performing spelling correction and word normalization (text correction) for Thai social media text has remained largely unexplored. In this thesis, we investigated how current text correction systems perform on correcting errors and word variances in Thai social texts and propose a method designed for this task. We have found that currently available Thai text correction systems are insufficiently robust for correcting spelling errors and word variances, while the text correctors designed for English grammatical error …

Go to article

Quantum Comparator Circuit On Superconducting Quantum Computer, Naphan Benchasattabuse Jan 2019

Quantum Comparator Circuit On Superconducting Quantum Computer, Naphan Benchasattabuse

Chulalongkorn University Theses and Dissertations (Chula ETD)

In this thesis, we present an optimised quantum comparator circuit based on Cuccaro's ripple-carry quantum adder using relative phase techniques from Maslov's multiple control Toffoli optimisation. We extend the cost function from simply counting C-Not and Toffoli gate to Qiskit cost which defines arbitrary single qubit gate cost as unity and C-Not as the only two qubit gate cost as ten. We report the comparison result between our comparator circuit with previous comparator circuits from literature using optimal Toffoli implementation with Qiskit cost, C-Not count, and circuit depth. We also report our experiment of implementing a two-bit comparator on IBM …

Go to article

A Peer-To-Peer Protocol For Prioritized Software Updates On Wireless Sensor Networks, Natchanon Nuntanirund Jan 2019

A Peer-To-Peer Protocol For Prioritized Software Updates On Wireless Sensor Networks, Natchanon Nuntanirund

Chulalongkorn University Theses and Dissertations (Chula ETD)

Software updating is essential for devices in wireless sensor networks for adding new features, improving performance, or patching vulnerabilities. But since some deployed devices are unable to be accessed directly, data dissemination protocol is used for distributing the update to those devices. However, each software updating may have different priority, for instance, an update that adds an optional feature does not have to be applied as fast as an update that patches severe vulnerabilities. This research presents a reliable data dissemination protocol which is configurable for energy-speed trade-off deriving some concepts from BitTorrent such as Handshaking, Segmented File Transfer, and …

Go to article

Semantic Segmentation On Remotely Sensed Images Using Deep Convolutional Encoder-Decoder Neural Network, Teerapong Panboonyuen Jan 2019

Semantic Segmentation On Remotely Sensed Images Using Deep Convolutional Encoder-Decoder Neural Network, Teerapong Panboonyuen

Chulalongkorn University Theses and Dissertations (Chula ETD)

One of the fundamental tasks in remote sensing is the semantic segmentation of the aerial and satellite images. It plays a vital role in applications, such as agriculture planning, map updates, route optimization, and navigation. The state-of-the-art model is the Deep Convolutional Encoder-Decoder (DCED). However, the accuracy is still limited since the architecture is not designed for recovering low-level features, e.g., river, low vegetation on remotely sensed images, and the training data in this domain are deficient. In this dissertation, we aim to propose the semantic segmentation architecture in five aspects, designed explicitly for the remotely sensed field. First, we …

Go to article

Semi-Supervised Deep Learning With Malignet For Bone Lesion Instance Segmentation Using Bone Scintigraphy, Terapap Apiparakoon Jan 2019

Semi-Supervised Deep Learning With Malignet For Bone Lesion Instance Segmentation Using Bone Scintigraphy, Terapap Apiparakoon

Chulalongkorn University Theses and Dissertations (Chula ETD)

One challenge in applying deep learning to medical imaging is the lack of labeled data. Although large amounts of clinical data are available, acquiring labeled image data is difficult, especially for bone scintigraphy (i.e., 2D bone imaging) images. Bone scintigraphy images are generally noisy, and ground-truth or gold standard information from surgical or pathological reports may not be available. We propose a novel neural network model that can segment abnormal hotspots and classify bone cancer metastases in the chest area in a semi-supervised manner. Our proposed model, called MaligNet, is an instance segmentation model that incorporates ladder networks to harness …

Go to article

การประเมินการส่งผ่านข้อมูลส่วนตัวของเเอปพลิเคชันโดยวิเคราะห์จากนโยบายความเป็นส่วนตัว, เมธัส นาคเสนีย์ Jan 2019

การประเมินการส่งผ่านข้อมูลส่วนตัวของเเอปพลิเคชันโดยวิเคราะห์จากนโยบายความเป็นส่วนตัว, เมธัส นาคเสนีย์

Chulalongkorn University Theses and Dissertations (Chula ETD)

โมไบล์เเอปพลิเคชันในปัจจุบันได้ขอเข้าถึงข้อมูลของผู้ใช้บริการเพื่อที่จะนำข้อมูลเหล่านี้ไปพัฒนาการให้บริการ เช่น ข้อมูลส่วนตัว อีเมล ซึ่งการนำข้อมูลเหล่านี้ไปใช้มีทั้งจุดประสงค์ในการใช้ข้อมูลในทางที่ดีเเละไม่ดี จึงเป็นเรื่องที่ผู้ใช้บริการควรตระหนักถึง ทั้งนี้ผู้ใช้บริการสามารถตรวจสอบรายละเอียดการนำข้อมูลไปใช้จากเเหล่งที่สามารถเข้าถึงได้ง่าย ได้เเก่ นโยบายความเป็นส่วนตัว เเต่เนื่องจากนโยบายความเป็นส่วนตัวมีข้อความที่ยาวเเละทำความเข้าใจได้ยาก ผู้ใช้บริการอาจพลาดส่วนสำคัญจากการอ่านนโยบายความเป็นส่วนตัวได้ ดังนั้นวิทยานิพนธ์นี้จึงได้ตั้งข้อสมมุติฐานเพื่อทำการพิสูจน์สมมุติฐานว่าการประเมินการส่งผ่านข้อมูลส่วนตัวของเเอปพลิเคชันสามารถวิเคราะห์ได้จากข้อความในนโยบายความเป็นส่วนตัวหรือไม่ โดยการใช้การเรียนรู้ด้วยเครื่องเข้ามาช่วยเพื่อที่จะประเมินการส่งผ่านของข้อมูลส่วนตัวเเทนการอ่านจากนโยบายความเป็นส่วนตัว

Go to article

เครื่องมือวิเคราะห์แบบรวมสำหรับการแปรผันของจำนวนชุดดีเอ็นเอบนลำดับเอ็กโซม, เสาวภาค จันทร์วิกูล Jan 2019

เครื่องมือวิเคราะห์แบบรวมสำหรับการแปรผันของจำนวนชุดดีเอ็นเอบนลำดับเอ็กโซม, เสาวภาค จันทร์วิกูล

Chulalongkorn University Theses and Dissertations (Chula ETD)

การศึกษาการแปรผันของจำนวนชุดดีเอ็นเอบนลำดับเอ็กโซม หรือที่เรียกว่าการศึกษาซีเอ็นวีบนเอ็กโซม เป็นหนึ่งในการศึกษาการแปรผันเชิงโครงสร้างของสารพันธุกรรมที่ได้รับความนิยมในปัจจุบัน การศึกษานี้สามารถช่วยนักวิจัยให้เข้าใจวิวัฒนาการของมนุษย์ การวินิจฉัยโรค และการตอบสนองต่อยาที่ใช้รักษาโรคได้ แต่ในขณะเดียวกันการศึกษานี้ก็เป็นเรื่องที่ท้าทายเนื่องจากกระบวนการเพื่อให้ได้มาซึ่งเอ็กโซมมาพร้อมกับค่าผลบวกเท็จสูงมาก และเมื่อนำเอ็กโซมที่มีค่าผลบวกเท็จสูงนี้มาตรวจจับหาการแปรผันของจำนวนชุดดีเอ็นเอบนลำดับเอ็กโซมก็ยิ่งก่อให้เกิดค่าผลบวกเท็จสูงยิ่งขึ้น อีกทั้งการแปรผันนี้ยังมีคุณลักษณะที่หลากหลายทำให้นักวิจัยไม่สามารถสร้างเครื่องมือตรวจจับที่ครอบคลุมคุณลักษณะทั้งหมดได้ นักวิจัยได้พยายามจัดการกับปัญหานี้ด้วยการสร้างเครื่องมือตรวจจับการแปรผันจำนวนมากที่มีลักษณะการทำงานที่แตกต่างกัน อย่างไรก็ตามยังไม่มีเครื่องมือตรวจจับการแปรผันเครื่องมือใดสามารถแก้ปัญหานี้ได้ อีกทั้งเครื่องมือตรวจจับการแปรผันส่วนใหญ่ขาดความสะดวก และความยืดหยุ่นในการใช้งาน เช่น ผู้ใช้ต้องติดตั้งเครื่องมือตรวจจับการแปรผันผ่านทางคอมมานไลน์ เครื่องมือตรวจจับไม่ให้คำอธิบายประกอบให้กับการแปรผันที่ตรวจจับได้ และไม่เปิดเผยข้อมูลที่ใช้ในการประมวลผล เป็นต้น จากปัญหาดังกล่าวผู้วิจัยจึงสร้างเครื่องมือตรวจจับการแปรผันของจำนวนชุดดีเอ็นเอบนลำดับเอ็กโซมแบบบูรณาการในรูปแบบเว็บแอปพลิเคชันซึ่งง่ายต่อการติดตั้งที่ชื่อว่า “อินซีเอ็นวี” เครื่องมือนี้สามารถรวมผลลัพธ์จากเครื่องมือตรวจจับซีเอ็นวีหลายเครื่องมือเพื่อเพิ่มความแม่นยำในการตรวจจับการแปรผัน หาความสัมพันธ์ของการแปรผันจากหลายตัวอย่างเพื่อช่วยในการวินิจฉัยโรค และจำกัดความเป็นไปได้ในการค้นพบการแปรผันตำแหน่งใหม่ที่ยังไม่เคยถูกรายงานในฐานข้อมูลการแปรผันทางพันธุกรรม เป็นต้น

Go to article

First Prev Next Last