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

Computer Sciences Commons™

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

Discipline
Institution
Keyword
Publication Year
Publication
Publication Type
File Type

Articles 19951 - 19980 of 63167

Full-Text Articles in Computer Sciences

แบบจำลองการเรียนรู้เชิงลึกสำหรับการจำแนกประเภทภาพแบบละเอียด, สรนันท์ พยัตศุภร Jan 2021

แบบจำลองการเรียนรู้เชิงลึกสำหรับการจำแนกประเภทภาพแบบละเอียด, สรนันท์ พยัตศุภร

Chulalongkorn University Theses and Dissertations (Chula ETD)

การจำแนกประเภทภาพแบบละเอียดเป็นปัญหาการจำแนกประเภทภาพที่อยู่ในหมวดหมู่หลักเดียวกัน เช่น ชนิดของนก, รุ่นของรถยนต์และรุ่นของเครื่องบิน โดยปัญหาหลักของการจำแนกประเภทภาพแบบละเอียดคือมีความผันผวนภายในประเภทและความเหมือนระหว่างประเภทสูง ทำให้งานวิจัยส่วนใหญ่มุ่งเน้นไปที่การระบุตำแหน่งของวัตถุหรือชิ้นส่วนสำคัญของภาพด้วยการออกแบบโครงสร้างแบบจำลองที่มีความซับซ้อนเพื่อแก้ปัญหาดังกล่าว ในงานวิจัยนี้ได้นำเสนอวิธีการเพิ่มประสิทธิภาพของความแม่นยำในการจำแนกประเภทซึ่งประกอบด้วยแบบจำลองสองระดับที่ทำหน้าที่แยกกันในการระบุตำแหน่งและจำแนกประเภท โดยการระบุตำแหน่งวัตถุทำหน้าที่หาพื้นที่ในรูปภาพที่มีวัตถุอยู่ด้วยสมมติฐานพื้นที่ต่อเนื่องที่มีขนาดใหญ่ที่สุดบนการรวมของผังฟีเจอร์ ซึ่งสกัดมาจากหลังจากคอนโวลูชันนิวรอลเน็ตเวิร์ค หลังจากนั้นในขั้นตอนการจำแนกประเภท ได้ปรับปรุงฟังก์ชันสูญเสียค่าสูงสุดอย่างอ่อนด้วยการเพิ่มมาจินเชิงมุมปรับค่าได้ในค่ามุมระหว่างฟีเจอร์เวกเตอร์และเวกเตอร์ศูนย์กลางประจำแต่ละประเภทในระหว่างการฝึกสอนแบบจำลอง วิธีการในงานวิจัยนี้สามารถฝึกสอนแบบจำลองได้แบบเอ็นทูเอ็นโดยไม่ต้องใช้กล่องขอบเขตในการฝึกสอนเพิ่มเติม ทั้งนี้ผลการทดลองแสดงให้เห็นว่า เทคนิคที่งานวิจัยนี้นำมาใช้มีประสิทธฺภาพที่ดีบนชุดข้อมูลสามชุดที่มีการใช้อย่างกว้างขวางในการทดลองเกี่ยวกับการจำประแนกประเภทภาพแบบละเอียด

Go to article

โมเดลควอนตัมโครงข่ายประสาทเทียมสำหรับปัญหาการถดถอย, สุรพันธุ์ เหล่าคนดี Jan 2021

โมเดลควอนตัมโครงข่ายประสาทเทียมสำหรับปัญหาการถดถอย, สุรพันธุ์ เหล่าคนดี

Chulalongkorn University Theses and Dissertations (Chula ETD)

ควอนตัมคอมพิวเตอร์ได้แสดงให้เห็นถึงความสามารถที่เหนือกว่าคอมพิวเตอร์แบบคลาสสิคในการแก้ไขปัญหาบางประเภทด้วยการใช้กฎของกลศาสตร์ควอนตัมและด้วยการรวมเอาความรู้ทางด้านการเรียนรู้ของเครื่องและควอนตัมคอมพิวเตอร์ทำให้เกิดองค์ความรู้ใหม่ที่เรียกว่าการเรียนรู้ของเครื่องแบบควอนตัม ควอนตัมโครงข่ายประสาทเทียมเป็นหนึ่งในรูปแบบของการใช้ความรู้ของการเรียนรู้ของเครื่องและคอมพิวเตอร์ควอนตัมด้วยการดัดแปลงความคิดจากการทำโครงข่ายประสาทเทียมแบบคลาสสิคและการใช้ควอนตัมเกทแบบปรับค่าได้มาเป็นค่าน้ำหนักของโครงข่ายประสาทเทียม ในงานวิจัยนี้ได้นำเสนอการประยุกต์ใช้ควอนตัมโครงข่ายประสาทเทียมด้วยข้อมูลจากโลกจริงเพื่อแก้ไขปัญหาการถดถอยเพื่อทำนายจำนวนโทเคนที่ใช้ในระบบประมูลรายวิชา โดยการทดลองจะถูกทำบนเครื่องจำลองคอมพิวเตอร์ควอนตัมของไอบีเอ็ม(Qiskit) ผลลัพธ์ของการทดลองได้แสดงให้เห็นว่าควอนตัมโครงข่ายประสาทเทียมสามารถบรรลุผลที่ดีในการทำนายเมื่อเปรียบเทียบกับโครงข่ายประสาทเทียมแบบคลาสสิคโดยโมเดลที่ดีที่สุดมีค่ารากที่สองของค่าเฉลี่ยความผิดพลาดกำลังสอง(RMSE) ที่ 6.38% วิธีการนี้ทำให้เกิดการเปิดกว้างสำหรับโอกาสที่จะสำรวจผลประโยชน์ของการเรียนรู้ของเครื่องแบบควอนตัมในการทำวิจัยในอนาคต

Go to article

การประยุกต์การวิเคราะห์เครือข่ายสังคมเพื่อปรับปรุงกระบวนการทดสอบซอฟต์แวร์, พรรณธิภา บุญมาพบ Jan 2021

การประยุกต์การวิเคราะห์เครือข่ายสังคมเพื่อปรับปรุงกระบวนการทดสอบซอฟต์แวร์, พรรณธิภา บุญมาพบ

Chulalongkorn University Theses and Dissertations (Chula ETD)

Jira Software เป็นโซลูชันการจัดการโครงการแบบอไจล์ ซึ่งเดิมออกแบบมาให้เป็นเครื่องมือในการติดตามข้อบกพร่องและปัญหาที่เกิดขึ้นภายในโครงการ การค้นหาปัญหาหรือข้อมูลข้อบกพร่องสามารถทำได้โดยใช้ Jira Query Language (JQL) อย่างไรก็ตาม การสืบค้นปัญหาหรือข้อบกพร่องจากแหล่งที่เก็บข้อมูลจะคืนค่าข้อมูลที่เฉพาะเจาะจงมาอย่างง่ายและธรรมดาทั่วไป ในงานวิจัยนี้ ได้นำเสนอแนวทางการสร้างภาพข้อมูลเครือข่ายเพื่อเปิดเผยความสัมพันธ์และการสื่อสารระหว่างตัวบทบาท เช่น คุณสมบัติของซอฟต์แวร์ ข้อบกพร่อง และบุคลากร โดยเทคนิคการวิเคราะห์เครือข่ายโซเชียลใช้สำหรับวิเคราะห์ข้อบกพร่องที่รวบรวมจากโครงการซอฟต์แวร์ภายในธนาคาร และ Gephi ถูกใช้เป็นเครื่องมือในการสร้างเครือข่ายของบทบาทที่ระบุเป็นโหนดและการเชื่อมโยงของโหนดเหล่านั้น ซึ่งแนวทางของการวิเคราะห์เครือข่ายภาพนั้นใช้ได้จริงและให้ข้อมูลเชิงลึกในการวิเคราะห์ข้อบกพร่องที่จำเป็นสำหรับกระบวนการพัฒนาซอฟต์แวร์ในเชิงรุก

Go to article

Prioritization Of Mutation Test Case Generation With Centrality Measures, ศุภชัย ทรัพย์มาก Jan 2021

Prioritization Of Mutation Test Case Generation With Centrality Measures, ศุภชัย ทรัพย์มาก

Chulalongkorn University Theses and Dissertations (Chula ETD)

การทดสอบการกลายพันธุ์สามารถนำไปใช้กับการประเมินคุณภาพของกรณีทดสอบได้ การจัดลำดับความสำคัญของการสร้างการทดสอบการกลายพันธุ์เป็นองค์ประกอบที่สำคัญของแนวปฏิบัติทางอุตสาหกรรมที่จะมีส่วนช่วยในการประเมินกรณีทดสอบ โดยทั่วไปแล้ว อุตสาหกรรมจะส่งมอบผลิตภัณฑ์ภายใต้เงื่อนไขของเวลาสู่ตลาด ดังนั้นจึงต้องเสียสละงานทดสอบซอฟต์แวร์อย่างหลีกเลี่ยงไม่ได้ แม้ว่าจะต้องใช้กรณีทดสอบจำนวนมากสำหรับการตรวจสอบซอฟต์แวร์ การใช้การวัดศูนย์กลางเครือข่ายสังคม เพื่อจัดลำดับความสำคัญของการสร้างการทดสอบการกลายพันธุ์ ซอร์สโค้ดที่มีค่าเพจแรงก์สูงสุด จะถูกเน้นก่อนเมื่อพัฒนากรณีทดสอบ เนื่องจากโมดูลเหล่านี้เสี่ยงต่อข้อบกพร่องหรือความผิดปกติซึ่งอาจทำให้เกิดข้อบกพร่องที่ตามมาในโมดูลที่เกี่ยวข้องอื่นๆ นอกจากนี้ แนวทางดังกล่าวจะช่วยระบุกรณีทดสอบที่ลดได้ในชุดทดสอบ โดยยังคงรักษาเกณฑ์เดียวกันกับจำนวนกรณีทดสอบเดิม

Go to article

Equations Of State For Warm Dense Carbon From Quantum Espresso, Derek J. Schauss Jan 2021

Equations Of State For Warm Dense Carbon From Quantum Espresso, Derek J. Schauss

Theses and Dissertations

Warm dense plasma is the matter that exists, roughly, in the range of 10,000 to 10,000,000 Kelvin and has solid-like densities, typically between 0.1 and 10 grams per centimeter. Warm dense fluids like hydrogen, helium, and carbon are believed to make up the interiors of many planets, white dwarfs, and other stars in our universe. The existence of warm dense matter (WDM) on Earth, however, is very rare, as it can only be created with high-energy sources like a nuclear explosion. In such an event, theoretical and computational models that accurately predict the response of certain materials are thus very …

Go to article

K-Nearest Neighbors Density-Based Clustering, Avory C. Bryant Jan 2021

K-Nearest Neighbors Density-Based Clustering, Avory C. Bryant

Theses and Dissertations

Traditional density-based clustering approaches rely on a distance-based parameter to define data connectivity and density. However, an appropriate value of this parameter can be difficult to determine as it is highly dependent on the underlying distribution of the data. In particular, distribution parameters affect the scale of inter-group distances (e.g., variance); this dependence leads to a well-known inability to simultaneously detect clusters at varying levels of density. In this work, connectivity and density are defined according to the rank-order induced by the distance metric (i.e., invariant to the expected scale of the distances). Connectivity by k-nearest neighbors and density by …

Go to article

A Deep Learning U-Net For Detecting And Segmenting Liver Tumors, Vidhya Cardozo Jan 2021

A Deep Learning U-Net For Detecting And Segmenting Liver Tumors, Vidhya Cardozo

Theses and Dissertations

Visualization of liver tumors on simulation CT scans is challenging even with contrast-enhancement, due to the sensitivity of the contrast enhancement to the timing of the CT acquisition. Image registration to magnetic resonance imaging (MRI) can be helpful for delineation, but differences in patient position, liver shape and volume, and the lack of anatomical landmarks between the two image sets makes the task difficult. This study develops a U-Net based neural network for automated liver and tumor segmentation for purposes of radiotherapy treatment planning. Non-contrast simulation based abdominal CT axial scans of 52 patients with primary liver tumors were utilized. …

Go to article

Password-Less Two-Factor Authentication Using Scannable Barcodes On A Mobile Device, Grant M. Callant Ii Jan 2021

Password-Less Two-Factor Authentication Using Scannable Barcodes On A Mobile Device, Grant M. Callant Ii

EWU Masters Thesis Collection

Currently, passwords are the default method used to authenticate users. As hardware continues to advance in speed, breaking these passwords becomes easier. The traditional solution to this problem is ever increasing password complexity and two-factor authentication. However, users become strained under overly complex login systems and often circumvent them. Two-factor authentication also adds to this complexity and many forms of two-factor authentication are inherently insecure. In answer to these problems, this project proposes a password-less multi-factor authentication system, which leverages the tried-and-proven existing technologies, asymmetric cryptography, digital signatures, and biometric authentication. Simulated user testing shows promising results, suggesting that registration …

Go to article

Swill-Tac: Skill-Oriented Dynamic Task Allocation With Willingness For Complex Job In Crowdsourcing, Riya Samanta, Soumya K. Ghosh, Sajal K. Das Jan 2021

Swill-Tac: Skill-Oriented Dynamic Task Allocation With Willingness For Complex Job In Crowdsourcing, Riya Samanta, Soumya K. Ghosh, Sajal K. Das

Computer Science Faculty Research & Creative Works

Allocating tasks to the best-fit candidates is a classical problem in crowdsourcing (CS). Most of the existing approaches assume that the task and candidate knowledge is known in advance and ignore the effect of enrolled candidates' willingness on the CS system's selection decision. For instance, an unwilling candidate assigned to a task may quit without completing it, thus depreciating the utility of the CS platform. In practice, a task or candidate may arrive or leave the CS system dynamically. Moreover, a complex task may be broken into smaller sub-tasks, each requiring a variety of computations and expertise. To overcome these …

Go to article

Novel Fast Terminal Sliding Mode Controller With Current Constraint Forpermanent-Magnet Synchronous Motor, Yao Fang, Huifang Kong, Daoyuan Ding Jan 2021

Novel Fast Terminal Sliding Mode Controller With Current Constraint Forpermanent-Magnet Synchronous Motor, Yao Fang, Huifang Kong, Daoyuan Ding

Turkish Journal of Electrical Engineering and Computer Sciences

Under the noncascade structure, the balance between q-axis current constraint and dynamic performance in permanent-magnet synchronous motor system has become a critical problem. On the one hand, large transient current is required to provide high torque to achieve fast dynamic performance. On the other hand, current constraint becomes a state constraint problem, instead of governing q-axis reference current in the cascade structure directly. Aiming at this issue, a novel fast terminal sliding mode control (FTSMC)-based controller with current constraint is developed in this paper. The novelty of this scheme is related to the proposed penalty function based on interior point …

Go to article

Joint Optimization Of Target Wake Time Mechanism And Scheduling For Ieee802.11ax, Mehmet Karaca Jan 2021

Joint Optimization Of Target Wake Time Mechanism And Scheduling For Ieee802.11ax, Mehmet Karaca

Turkish Journal of Electrical Engineering and Computer Sciences

IEEE 802.11ax as the newest wireless local area networks (WLANs) standard brings enormous improvements in network throughput, coverage and energy efficiency in densely populated areas. Unlike previous IEEE 802.11 WLAN standards where power saving mechanisms have a limited capability and flexibility, 802.11ax comes with a different mechanism called target wake time (TWT) where stations (STAs) wake up only after each TWT interval and different STAs can wake up at different time instance depending on their application requirements. As an example, for a periodic data arrival occurring in IoT applications, STA can wake up by following the data period and go …

Go to article

Impact Of Hybrid Power Generation On Voltage, Losses, And Electricity Cost Indistribution Networks, Yavuz Ateş, Tayfur Gökçek, Ahmet Yi̇ği̇t Arabul Jan 2021

Impact Of Hybrid Power Generation On Voltage, Losses, And Electricity Cost Indistribution Networks, Yavuz Ateş, Tayfur Gökçek, Ahmet Yi̇ği̇t Arabul

Turkish Journal of Electrical Engineering and Computer Sciences

Energy and its capacity has emerged as one of the biggest distribution challenges all over the world. The existing grid becomes insufficient along with the expansion of the consumption. Therefore, the number of distributed generation (DG) in distribution networks increases and it allows us to sell back the extra energy. However, the efficiency of energy must be maintained into optimal values from the grid to the end-users. In spite of a lot of advantages of DG units, there are some disadvantages like fluctuations in voltage, increments of power losses, wrong protection coordination, harmonic and energy quality issues etc.. If the …

Go to article

Analysis And Simulation Of Efficiency Optimized Ipm Drives In Constant Torqueregion With Reduced Computational Burden, Mi̇kai̇l Koç, Selçuk Emi̇roğlu, Bünyami̇n Tamyürek Jan 2021

Analysis And Simulation Of Efficiency Optimized Ipm Drives In Constant Torqueregion With Reduced Computational Burden, Mi̇kai̇l Koç, Selçuk Emi̇roğlu, Bünyami̇n Tamyürek

Turkish Journal of Electrical Engineering and Computer Sciences

Moving from internal combustion engine based towards electric based transportation is crucial for wide societies as they facilitate the use of green energy technologies such as wind and solar. Interior mounted permanent magnet (IPM) machines, also known as salient brushless alternating current (AC) machines, are commonly employed in traction applications as they have superior features, such as high efficiency operation, high torque, and power densities. The efficiency optimization in IPM drives is achieved by obtaining and operating at accurate and unique current angle for a certain electromagnetic torque demand. In conventional drives, the optimum current angle is obtained by online …

Go to article

Determination Of Pneumonia In X-Ray Chest Images By Using Convolutionalneural Network, Özlem Polat, Zümray Ölmez, Tamer Ölmez Jan 2021

Determination Of Pneumonia In X-Ray Chest Images By Using Convolutionalneural Network, Özlem Polat, Zümray Ölmez, Tamer Ölmez

Turkish Journal of Electrical Engineering and Computer Sciences

Pneumonia is one of the major diseases that cause a lot of deaths all over the world. Determining pneumonia from chest X-ray (CXR) images is an extremely difficult and important image processing problem. The discrimination of whether pneumonia is of bacterium or virus origin has also become more important during the pandemic. Automatic determination of the presence and origin of pneumonia is crucial for speeding up the treatment process and increasing the patient's survival rate. In this study, a convolutional neural network (CNN) framework is proposed for detection of pneumonia from CXR images. Two different binary CNNs and a triple …

Go to article

Power-Based Modelling And Control: Experimental Results On A Cart-Pole Doubleinverted Pendulum, Tuğçe Yaren, Selçuk Ki̇zi̇r Jan 2021

Power-Based Modelling And Control: Experimental Results On A Cart-Pole Doubleinverted Pendulum, Tuğçe Yaren, Selçuk Ki̇zi̇r

Turkish Journal of Electrical Engineering and Computer Sciences

This paper is concerned with the modeling framework based on power and control for a mechanical system that has nonlinear, unstable, and under-actuated characteristic features, based on an analogy, which is developed by using the Brayton and Moser's (BM) equations between mechanical and electrical systems. The analogy is based on a mixed-potential function generalized for BM. The mixed-potential function for a cart - pole double inverted pendulum (CPDIP) system is used as a new building block for modeling, analysis, and controller design. The analogy allows for the exact transfer of results from electrical circuit synthesis and analysis to the mechanical …

Go to article

Control Synthesis For Parametric Timed Automata Under Reachability, Ebru Aydin Göl Jan 2021

Control Synthesis For Parametric Timed Automata Under Reachability, Ebru Aydin Göl

Turkish Journal of Electrical Engineering and Computer Sciences

Timed automata is a fundamental modeling formalism for real-time systems. During the design of such real-time systems, often the system information is incomplete, and design choices can vary. These uncertainties can be integrated to the model via parameters and labelled transitions. Then, the design can be completed by tuning the parameters and restricting the transitions via controller synthesis. These problems, namely parameter synthesis and controller synthesis, are studied separately in the literature. Herein, these are combined to generate an automaton satisfying the given specification by both parameter tuning and controller synthesis, thus exploring all design choices. First, it is shown …

Go to article

Information Retrieval-Based Bug Localization Approach With Adaptive Attributeweighting, Mustafa Erşahi̇n, Semi̇h Utku, Deni̇z Kilinç, Buket Erşahi̇n Jan 2021

Information Retrieval-Based Bug Localization Approach With Adaptive Attributeweighting, Mustafa Erşahi̇n, Semi̇h Utku, Deni̇z Kilinç, Buket Erşahi̇n

Turkish Journal of Electrical Engineering and Computer Sciences

Software quality assurance is one of the crucial factors for the success of software projects. Bug fixing has an essential role in software quality assurance, and bug localization (BL) is the first step of this process. BL is difficult and time-consuming since the developers should understand the flow, coding structure, and the logic of the program. Information retrieval-based bug localization (IRBL) uses the information of bug reports and source code to locate the section of code in which the bug occurs. It is difficult to apply other tools because of the diversity of software development languages, design patterns, and development …

Go to article

Novel Ofdm Transmission Scheme Using Generalized Prefix With Subcarrierindex Modulation, Yusuf Acar Jan 2021

Novel Ofdm Transmission Scheme Using Generalized Prefix With Subcarrierindex Modulation, Yusuf Acar

Turkish Journal of Electrical Engineering and Computer Sciences

The cyclic prefix (CP) is a prefix technique widely used in orthogonal frequency division multiplexing (OFDM) systems in order to eliminate the intersymbol interference (ISI) caused by the dispersion of wireless channels. However, CP reduces the number of symbols that can be transmitted in one OFDM symbol. Therefore, CP is one of the bottlenecks of OFDM systems limiting their spectral efficiency (SE). This limitation on the SE of the classical CP-based OFDM system is the main motivation for this work to introduce a novel method. In this paper, the design of a new CP structure, which is based on the …

Go to article

Determining Overfitting And Underfitting In Generative Adversarial Networksusing Fréchet Distance, Enes Eken Jan 2021

Determining Overfitting And Underfitting In Generative Adversarial Networksusing Fréchet Distance, Enes Eken

Turkish Journal of Electrical Engineering and Computer Sciences

Generative adversarial networks (GANs) can be used in a wide range of applications where drawing samples from a data probability distribution without explicitly representing it is essential. Unlike the deep convolutional neural networks (CNNs) trained for mapping an input to one of the multiple outputs, monitoring the overfitting and underfitting in GANs is not trivial since they are not classifying but generating a data. While training set and validation set accuracy give a direct sense of success in terms of overfitting and underfitting for CNNs during the training process, evaluating the GANs mainly depends on the visual inspection of the …

Go to article

A Case Study On Player Selection And Team Formation In Football With Machinelearning, Di̇dem Abi̇di̇n Jan 2021

A Case Study On Player Selection And Team Formation In Football With Machinelearning, Di̇dem Abi̇di̇n

Turkish Journal of Electrical Engineering and Computer Sciences

Machine learning has been widely used in different domains to extract information from raw data. Sports is one of the popular domains for researchers to work on recently. Although score prediction for matches is the most preferred application area for artificial intelligence, player selection, and team formation is also an application area worth working on. There are some studies in the literature about player selection and team formation which are examined in this study. The study has two important contributions: First one is to apply seven different machine learning algorithms on our dataset to find the best player combination for …

Go to article

Analysis Of Optical Gyroscopes With Vertically Stacked Ring Resonators, Dooyoung Hah Jan 2021

Analysis Of Optical Gyroscopes With Vertically Stacked Ring Resonators, Dooyoung Hah

Turkish Journal of Electrical Engineering and Computer Sciences

Without any moving part, optical gyroscopes exhibit superior reliability and accuracy in comparison to mechanical sensors. Microring-resonator-based optical gyroscopes emerged as alternatives for bulky conventional Sagnac interferometer sensors, especially attractive for applications with limited footprints. Previously, it has been reported that planar incorporation of multiple resonators does not bring about improvement in sensitivity for a given area because the increase in Sagnac phase accumulation does not outrun the increase of area. Therefore, it was naturally suggested to consider vertical stacking of ring resonators because then, the resonators can share the same footprint. In this work, sensitivity performances of such configurations …

Go to article

Adaptation Of Metaheuristic Algorithms To Improve Training Performance Of Aneszsl Model, Şi̇fa Özsari, Mehmet Serdar Güzel, Gazi̇ Erkan Bostanci, Ayhan Aydin Jan 2021

Adaptation Of Metaheuristic Algorithms To Improve Training Performance Of Aneszsl Model, Şi̇fa Özsari, Mehmet Serdar Güzel, Gazi̇ Erkan Bostanci, Ayhan Aydin

Turkish Journal of Electrical Engineering and Computer Sciences

Zero-shot learning (ZSL) is a recent promising learning approach that is similar to human vision systems. ZSL essentially allows machines to categorize objects without requiring labeled training data. In principle, ZSL proposes a novel recognition model by specifying merely the attributes of the category. Recently, several sophisticated approaches have been introduced to address the challenges regarding this problem. Embarrassingly simple approach to zeroshot learning (ESZSL) is one of the critical of those approaches that basically proposes a simple but efficient linear code solution. However, the performance of the ESZSL model mainly depends on parameter selection. Metaheuristic algorithms are considered as …

Go to article

A New Approach: Semisupervised Ordinal Classification, Ferda Ünal, Derya Bi̇rant, Özlem Şeker Jan 2021

A New Approach: Semisupervised Ordinal Classification, Ferda Ünal, Derya Bi̇rant, Özlem Şeker

Turkish Journal of Electrical Engineering and Computer Sciences

Semisupervised learning is a type of machine learning technique that constructs a classifier by learning from a small collection of labeled samples and a large collection of unlabeled ones. Although some progress has been made in this research area, the existing semisupervised methods provide a nominal classification task. However, semisupervised learning for ordinal classification is yet to be explored. To bridge the gap, this study combines two concepts ?semisupervised learning? and "ordinal classification" for the categorical class labels for the first time and introduces a new concept of "semisupervised ordinal classification". This paper proposes a new algorithm for semisupervised learning …

Go to article

A Blockchain-Based Authentication Protocol For Cooperative Vehicular Ad Hoc Network, A. F. M. S. Akhter, Mohiuddin Ahmed, A. F. M. S. Shah, Adnan Anwar, A. S. M. Kayes, Ahmet Zengin Jan 2021

A Blockchain-Based Authentication Protocol For Cooperative Vehicular Ad Hoc Network, A. F. M. S. Akhter, Mohiuddin Ahmed, A. F. M. S. Shah, Adnan Anwar, A. S. M. Kayes, Ahmet Zengin

Research outputs 2014 to 2021

The efficiency of cooperative communication protocols to increase the reliability and range of transmission for Vehicular Ad hoc Network (VANET) is proven, but identity verification and communication security are required to be ensured. Though it is difficult to maintain strong network connections between vehicles because of there high mobility, with the help of cooperative communication, it is possible to increase the communication efficiency, minimise delay, packet loss, and Packet Dropping Rate (PDR). However, cooperating with unknown or unauthorized vehicles could result in information theft, privacy leakage, vulnerable to different security attacks, etc. In this paper, a blockchain based secure and …

Go to article

An Investigation Into The Efficacy Of Url Content Filtering Systems, Brett Ronald Turner Jan 2021

An Investigation Into The Efficacy Of Url Content Filtering Systems, Brett Ronald Turner

Theses: Doctorates and Masters

Content filters are used to restrict to restrict minors from accessing to online content deemed inappropriate. While much research and evaluation has been done on the efficiency of content filters, there is little in the way of empirical research as to their efficacy. The accessing of inappropriate material by minors, and the role content filtering systems can play in preventing the accessing of inappropriate material, is largely assumed with little or no evidence. This thesis investigates if a content filter implemented with the stated aim of restricting specific Internet content from high school students achieved the goal of stopping students …

Go to article

Affordance Learning For Visual-Semantic Perception, Chau Nguyen Duc Minh Jan 2021

Affordance Learning For Visual-Semantic Perception, Chau Nguyen Duc Minh

Theses: Doctorates and Masters

Affordance Learning is linked to the study of interactions between robots and objects, including how robots perceive objects by scene understanding. This area has been popular in the Psychology, which has recently come to influence Computer Vision. In this way, Computer Vision has borrowed the concept of affordance from Psychology in order to develop Visual-Semantic recognition systems, and to develop the capabilities of robots to interact with objects, in particular. However, existing systems of Affordance Learning are still limited to detecting and segmenting object affordances, which is called Affordance Segmentation. Further, these systems are not designed to develop specific abilities …

Go to article

A Defensive Strategy For Detecting Targeted Adversarial Poisoning Attacks In Machine Learning Trained Malware Detection Models, Adrian Michael Wood Jan 2021

A Defensive Strategy For Detecting Targeted Adversarial Poisoning Attacks In Machine Learning Trained Malware Detection Models, Adrian Michael Wood

Theses: Doctorates and Masters

Machine learning is a subset of Artificial Intelligence which is utilised in a variety of different fields to increase productivity, reduce overheads, and simplify the work process through training machines to automatically perform a task. Machine learning has been implemented in many different fields such as medical science, information technology, finance, and cyber security. Machine learning algorithms build models which identify patterns within data, which when applied to new data, can map the input to an output with a high degree of accuracy. To build the machine learning model, a dataset comprised of appropriate examples is divided into training and …

Go to article

An Energy-Efficient And Secure Data Inference Framework For Internet Of Health Things: A Pilot Study, James Jin Kang, Mahdi Dibaei, Gang Luo, Wencheng Yang, Paul Haskell-Dowland, Xi Zheng Jan 2021

An Energy-Efficient And Secure Data Inference Framework For Internet Of Health Things: A Pilot Study, James Jin Kang, Mahdi Dibaei, Gang Luo, Wencheng Yang, Paul Haskell-Dowland, Xi Zheng

Research outputs 2014 to 2021

© 2021 by the authors. Licensee MDPI, Basel, Switzerland. Privacy protection in electronic healthcare applications is an important consideration, due to the sensitive nature of personal health data. Internet of Health Things (IoHT) networks that are used within a healthcare setting have unique challenges and security requirements (integrity, authentication, privacy, and availability) that must also be balanced with the need to maintain efficiency in order to conserve battery power, which can be a significant limitation in IoHT devices and networks. Data are usually transferred without undergoing filtering or optimization, and this traffic can overload sensors and cause rapid battery consumption …

Go to article

A Secured Privacy-Preserving Multi-Level Blockchain Framework For Cluster Based Vanet, A. F.M.Suaib Akhter, Mohiuddin Ahmed, A. F.M.Shahen Shah, Adnan Anwar, Ahmet Zengin Jan 2021

A Secured Privacy-Preserving Multi-Level Blockchain Framework For Cluster Based Vanet, A. F.M.Suaib Akhter, Mohiuddin Ahmed, A. F.M.Shahen Shah, Adnan Anwar, Ahmet Zengin

Research outputs 2014 to 2021

© 2021 by the authors. Licensee MDPI, Basel, Switzerland. Existing research shows that Cluster-based Medium Access Control (CB-MAC) protocols perform well in controlling and managing Vehicular Ad hoc Network (VANET), but requires ensuring improved security and privacy preserving authentication mechanism. To this end, we propose a multi-level blockchain-based privacy-preserving authentication protocol. The paper thoroughly explains the formation of the authentication centers, vehicles registration, and key generation processes. In the proposed architecture, a global authentication center (GAC) is responsible for storing all vehicle information, while Local Authentication Center (LAC) maintains a blockchain to enable quick handover between internal clusters of vehicle. …

Go to article

A Secured Message Transmission Protocol For Vehicular Ad Hoc Networks, A. F. M. Suaib Akhter, A. F. M. Shahen Shah, Mohiuddin Ahmed, Nour Moustafa, Unal Çavuşoğlu, Ahmet Zengin Jan 2021

A Secured Message Transmission Protocol For Vehicular Ad Hoc Networks, A. F. M. Suaib Akhter, A. F. M. Shahen Shah, Mohiuddin Ahmed, Nour Moustafa, Unal Çavuşoğlu, Ahmet Zengin

Research outputs 2014 to 2021

Vehicular Ad hoc Networks (VANETs) become a very crucial addition in the Intelligent Transportation System (ITS). It is challenging for a VANET system to provide security services and parallelly maintain high throughput by utilizing limited resources. To overcome these challenges, we propose a blockchain-based Secured Cluster-based MAC (SCB-MAC) protocol. The nearby vehicles heading towards the same direction will form a cluster and each of the clusters has its blockchain to store and distribute the safety messages. The message which contains emergency information and requires Strict Delay Requirement (SDR) for transmission are called safety messages (SM). Cluster Members (CMs) sign SMs …

Go to article

First Prev Next Last