Computer Sciences Commons^™

Data-Driven Personalized Applications In Networks, Chuankai An

Dartmouth College Ph.D Dissertations

A network models relationships. For a network that either encodes or supports internal information sharing activities, a better understanding of the network may enable data-driven applications (e.g., social network based recommendation), and boost both descriptive and predictive modeling of information flow in itself. In a multi-faceted manner, we propose in this thesis to contribute to several challenges that arise in the development of personalized applications in the general area of information and networks: 1) articulation of new patterns (and associated metrics) for individual user behavior and network structure; 2) exploitation of new forms of feature vector representations derived from large …

Stylized 2d Fabrication Of Non-Photorealistic Images, Athina Panotopoulou

Dartmouth College Ph.D Dissertations

A current trend in computer graphics is the use of programmable tools that allow non-experts to engage in the design of physical prototypes. Within fabrication, one area of research focuses on non-photorealistic images which are stylized to depict a particular aesthetic quality or convey key information. In cases where authenticity is demanded or the images need to be manipulated, fabrication is necessary. Non-photorealistic image fabrication involves two challenges: identifying and abstracting key information during design and considering material restrictions during fabrication. This thesis showcases two examples for fabricating new types of non-photorealistic images, the first involving watercolors, and the second …

Stream Clustering And Visualization Of Geotagged Text Data For Crisis Management, Nathaniel C. Crossman

Browse all Theses and Dissertations

In the last decade, the advent of social media and microblogging services have inevitably changed our world. These services produce vast amounts of streaming data, and one of the most important ways of analyzing and discovering interesting trends in the streaming data is through clustering. In clustering streaming data, it is desirable to perform a single pass over incoming data, such that we do not need to process old data again, and the clustering model should evolve over time not to lose any important feature statistics of the data. In this research, we have developed a new clustering system that …

An Adversarial Framework For Deep 3d Target Template Generation, Walter E. Waldow

Browse all Theses and Dissertations

This paper presents a framework for the generation of 3D models. This is an important problem for many reasons. For example, 3D models are important for systems that are involved in target recognition. These systems use 3D models to train up accuracy on identifying real world object. Traditional means of gathering 3D models have limitations that the generation of 3D models can help overcome. The framework uses a novel generative adversarial network (GAN) that learns latent representations of two dimensional views of a model to bootstrap the network’s ability to learn to generate three dimensional objects. The novel architecture is …

Quantitative Susceptibility Mapping (Qsm) Reconstruction From Mri Phase Data, Sara Gharabaghi

Browse all Theses and Dissertations

Quantitative susceptibility mapping (QSM) is a powerful technique that reveals changes in the underlying tissue susceptibility distribution. It can be used to measure the concentrations of iron and calcium in the brain both of which are linked with numerous neurodegenerative diseases. However, reconstructing the QSM image from the MRI phase data is an ill-posed inverse problem. Different methods have been proposed to overcome this difficulty. Still, the reconstructed QSM images suffer from streaking artifacts and underestimate the measured susceptibility of deep gray matter, veins, and other high susceptibility regions. This thesis proposes a structurally constrained Susceptibility Weighted Imaging and Mapping …

Development Of Real-Time Systems For Supporting Collaborations In Distributed Human And Machine Teams, Aishwarya Bositty

Browse all Theses and Dissertations

Real-time distributed systems constitute computing nodes that are connected by a network and coordinate with one another to accomplish a cooperative task, combining the responsiveness, fault-tolerance and geographic independence to support time-constrained collaborative applications, including distributed Human-Machine Teaming. In this thesis research the viability of real-time distributed collaborative technologies is demonstrated through the design, development and validation of prototype systems that support two human-machine teaming scenarios namely, ACE-IMS (Affirmation Cue based Interruption Management Systems) and ReadMI (Real-time Assessment of Dialogue in Motivational Interview). ACE-IMS demonstrates how a combination of AI capabilities and the cloud and mobile computing infrastructure can be …

Stream Clustering And Visualization Of Geotagged Text Data For Crisis Management, Nathaniel C. Crossman

Browse all Theses and Dissertations

In the last decade, the advent of social media and microblogging services have inevitably changed our world. These services produce vast amounts of streaming data, and one of the most important ways of analyzing and discovering interesting trends in the streaming data is through clustering. In clustering streaming data, it is desirable to perform a single pass over incoming data, such that we do not need to process old data again, and the clustering model should evolve over time not to lose any important feature statistics of the data. In this research, we have developed a new clustering system that …

Facilitating Cross-Chain Cryptocurrency Exchanges: An Inquiry Into Blockchain Technology And Interoperability With An Emphasis On Cryptocurrency Arbitrage, Samuel Grone

Senior Honors Theses and Projects

Since the introduction and proliferation of the blockchain-based cryptocurrency Bitcoin, alternative cryptocurrencies also based on blockchain technology have exploded in number. It was once believed that one, or very few, cryptocurrencies would eventually dominate the market and drive out competitors. This assumption, however, was incorrect. Thousands of cryptocurrencies exist concurrently. The vast number of cryptocurrencies leads to a problem—what if the cryptocurrency that an individual possesses does not meet their current needs as well as another cryptocurrency might? The attempt to solve this problem has led to the rise of many cryptocurrency exchanges and exchange schemes. In this paper, we …

Managing Inventory: A Study Of Databases And Database Management Systems, Jemal M. Jemal

Senior Independent Study Theses

Databases play an important role in the storage and manipulation of data. Databases and database management systems allow for fast and efficient data querying that has recently become increasingly important in most companies and organizations. This paper introduces a few of the different types of database management systems that are in widespread use today. It introduces some important terminology related to databases and database management systems. This paper also briefly discusses web user interfaces, highlighting important user interface design principles. Finally, an inventory management system is implemented for a local stationery store and is integrated with a web application to …

Polyacrylamide In Glycerol Solutions From An Atomistic Perspective Of The Energetics, Structure, And Dynamics, Scott D. Hopkins, Gideon K. Gogovi, Eric Weisel, Robert A. Handler, Estela Blaisten-Barojas

VMASC Publications

All-atom molecular dynamics is used to investigate the structural, energetic, and dynamical properties of polyacrylamide (PAM) oligomers of different lengths solvated in pure glycerol, a 90:10 glycerol–water mixture, and pure water. We predict that the oligomers’ globular structure is obtained only when the modeling strategy considers the solvent as a continuous background. Meanwhile, for all-atom modeled solvents, the glycerol solutions display a strong tendency of trapping the oligomers in instantaneous elongated random coiled structures that remain locked-in over tens of nanoseconds. In pure water, the oligomers acquire considerably shorter random coiled structures of increased flexibility. The all-atom force field, generalized …

A Blockchain Simulator For Evaluating Consensus Algorithms In Diverse Networking Environments, Peter Foytik, Sachin Shetty, Sarada Prasad Gochhayat, Eranga Herath, Deepak Tosh, Laurent Njilla

VMASC Publications

The massive scale, heterogeneity and distributed nature of Internet-of-Things (IoT) presents challenges in realizing a practical and effective security solution. Blockchain empowered platforms and technologies have been proposed to address aspects of this challenge. In order to realize a practical Blockchain deployment for IoT, there is a need for a testing and evaluation platform to evaluate performance and security of Blockchain applications and systems. In this paper, we present a Blockchain simulator that evaluates the consensus algorithms in a realistic and configurable network environment. Though, there are several Blockchain evaluation platforms, they are either wedded to a specific consensus protocol …

Measuring Decentrality In Blockchain Based Systems, Sarada Prasad Gochhayat, Sachin Shetty, Ravi Mukkamala, Peter Foytik, Georges A. Kamhoua, Laurent Njilla

VMASC Publications

Blockchain promises to provide a distributed and decentralized means of trust among untrusted users. However, in recent years, a shift from decentrality to centrality has been observed in the most accepted Blockchain system, i.e., Bitcoin. This shift has motivated researchers to identify the cause of decentrality, quantify decentrality and analyze the impact of decentrality. In this work, we take a holistic approach to identify and quantify decentrality in Blockchain based systems. First, we identify the emergence of centrality in three layers of Blockchain based systems, namely governance layer, network layer and storage layer. Then, we quantify decentrality in these layers …

Repositories For Taxonomic Data: Where We Are And What Is Missing, Aurélian Miralles, Teddy Bruy, Katherine Wolcott, Mark D. Scherz, Dominik Begerow, Bank Beszteri, Michael Bonkowski, Janine Felden, Birgit Gemeinholzer, Frank Glaw, Frank Oliver Glöckner, Oliver Hawlitschek, Ivaylo Kostadinov, Tim W. Nattkemper, Christian Printzen, Jasmin Renz, Nataliya Rybalka, Marc Stadler, Tanja Weibulat, Thomas Wilke, Susanne S. Renner, Miguel Vences

Harold W. Manter Laboratory of Parasitology: Library Materials

Natural history collections are leading successful large-scale projects of specimen digitization (images, metadata, DNA barcodes), thereby transforming taxonomy into a big data science. Yet, little effort has been directed towards safeguarding and subsequently mobilizing the considerable amount of original data generated during the process of naming 15,000–20,000 species every year. From the perspective of alpha-taxonomists, we provide a review of the properties and diversity of taxonomic data, assess their volume and use, and establish criteria for optimizing data repositories. We surveyed 4,113 alpha-taxonomic studies in representative journals for 2002, 2010, and 2018, and found an increasing yet comparatively limited use …

Comparative Evaluation Of Machine Learning Models For Groundwater Quality Assessment, Shine Bedi, Ashok Samal, Chittaranjan Ray, Daniel D. Snow

School of Computing: Faculty Publications

Contamination from pesticides and nitrate in groundwater is a significant threat to water quality in general and agriculturally intensive regions in particular. Three widely used machine learning models, namely, artificial neural networks (ANN), support vector machines (SVM), and extreme gradient boosting (XGB), were evaluated for their efficacy in predicting contamination levels using sparse data with non-linear relationships. The predictive ability of the models was assessed using a dataset consisting of 303 wells across 12 Midwestern states in the USA. Multiple hydrogeologic, water quality, and land use features were chosen as the independent variables, and classes were based on measured concentration …

Quantum Computing: Principles And Applications, Yoshito Kanamori, Seong-Moo Yoo

Journal of International Technology and Information Management

The development of quantum computers over the past few years is probably one of the significant advancements in the history of quantum computing. D-Wave quantum computer has been available for more than eight years. IBM has made its quantum computer accessible via its cloud service. Also, Microsoft, Google, Intel, and NASA have been heavily investing in the development of quantum computers and their applications. The quantum computer seems to be no longer just for physicists and computer scientists but also for information system researchers. This paper introduces the basic concepts of quantum computing and describes well-known quantum applications for non-physicists. …

Comparison Of Object Detection And Patch-Based Classification Deep Learning Models On Mid- To Late-Season Weed Detection In Uav Imagery, Arun Narenthiran Veeranampalayam Sivakumar, Jiating Li, Stephen Scott, Eric T. Psota, Amit J. Jhala, Joe D. Luck, Yeyin Shi

Department of Agricultural and Biological Systems Engineering: Faculty Publications

Mid- to late-season weeds that escape from the routine early-season weed management threaten agricultural production by creating a large number of seeds for several future growing seasons. Rapid and accurate detection of weed patches in field is the first step of site-specific weed management. In this study, object detection-based convolutional neural network models were trained and evaluated over low-altitude unmanned aerial vehicle (UAV) imagery for mid- to late-season weed detection in soybean fields. The performance of two object detection models, Faster RCNN and the Single Shot Detector (SSD), were evaluated and compared in terms of weed detection performance using mean …

Structure-Priority Image Restoration Through Genetic Algorithm Optimization, Zhaoxia Wang, Haibo Pen, Ting Yang, Quan Wang

Research Collection School Of Computing and Information Systems

With the significant increase in the use of image information, image restoration has been gaining much attention by researchers. Restoring the structural information as well as the textural information of a damaged image to produce visually plausible restorations is a challenging task. Genetic algorithm (GA) and its variants have been applied in many fields due to their global optimization capabilities. However, the applications of GA to the image restoration domain still remain an emerging discipline. It is still challenging and difficult to restore a damaged image by leveraging GA optimization. To address this problem, this paper proposes a novel GA-based …

An Exact Single-Agent Task Selection Algorithm For The Crowdsourced Logistics, Chung-Kyun Han, Shih-Fen Cheng

Research Collection School Of Computing and Information Systems

The trend of moving online in the retail industry has created great pressure for the logistics industry to catch up both in terms of volume and response time. On one hand, volume is fluctuating at greater magnitude, making peaks higher; on the other hand, customers are also expecting shorter response time. As a result, logistics service providers are pressured to expand and keep up with the demands. Expanding fleet capacity, however, is not sustainable as capacity built for the peak seasons would be mostly vacant during ordinary days. One promising solution is to engage crowdsourced workers, who are not employed …

An Intra-Severity Classification And Adaptation Technique To Improve Dysarthric Speech Recognition Accuracy, Al-Qatab Bassam Ali Qasem

Student Works (2020-2029)

Dysarthria is a motor speech impairment at the neurological and/or muscular levels that caused difficulty in pronouncing words clearly. Automatic speech recognition (ASR) system is increasingly applied as assistive technology to aid an individual with physical disability particularly the speech impaired community such as dysarthria speakers. However, the development of an effective ASR system is hindered by the data sparsity, either in the coverage of the language or the size of the existing speech databases. The speaker adaptation (SA) technique is one of the solutions to overcome the data sparsity issue of ASR for dysarthric speakers. Our proposed method introduces …

Development Of Authentication-Based Captcha Mechanism On Touch Screen Environment, Nilobon Nanglae

Chulalongkorn University Theses and Dissertations (Chula ETD)

CAPTCHA is a simple security test that was introduced to distinguish among humans and bots for decades. CAPTCHAs have been widely used on commercial sites, such as email service, and social networking sites, for protecting the system from automated software attackers. However, various techniques have been invented to break CAPTCHA, and one of these techniques is the 3rd party attacks. So, the design of CAPTCHA is unable to distinguish between human users and illegitimate human attackers. Thus, this research proposed a new type of CAPTCHA that is individually generated for an individual user. The proposed technique merges between biometrics and …

A Comprehensive Analysis Of Smart Ship Systems And Underlying Cybersecurity Issues, Dennis Bothur

Theses : Honours

The maritime domain benefits greatly from advanced technology and ubiquitous connectivity. From “smart” sensors to “augmented reality”, the opportunities to save costs and improve safety are endless. The aim of this dissertation is to study the capabilities of smart ship systems in the context of Internet-of-Things and analyse the potential cybersecurity risks and challenges that smart technologies may introduce into this accelerating digital economy.

The first part of this work investigates the architecture of a “Smart Ship System” and the primary subsystems, including the integrated bridge, navigation and communication systems, networking, operational systems, and sensor networks. The mapping of the …

การวินิจฉัยโรคพาร์กินสันโดยใช้การเรียนรู้ของเครื่อง, หัสพล ธัมมิกรัตน์

Chulalongkorn University Theses and Dissertations (Chula ETD)

วิทยานิพนธ์นี้นำเสนอวิธีการวินิจฉัยโรคพาร์กินสันด้วยการใช้การเรียนรู้ของเครื่องสำหรับการตรวจพบโรคพาร์กินสันในระยะเริ่มต้น โดยใช้โครงข่ายประสาทเทียมแบบวนซ้ำชนิดพิเศษ Long Short-Term Memory กับข้อมูลโรคพาร์กินสันที่ได้รับจากผู้เชี่ยวชาญของโรงพยาบาลจุฬาลงกรณ์ โดยข้อมูลที่ใช้ประกอบไปด้วยข้อมูลจากเซ็นเซอร์และคีย์บอร์ดจากการเก็บข้อมูลจากผู้ร่วมทดสอบซึ่งมีทั้งกลุ่มควบคุมและผู้ป่วยจำนวนหนึ่งผ่านตัวควบคุมที่เก็บข้อมูลคีย์บอร์ดและเซ็นเซอร์ ซึ่งข้อมูลเซ็นเซอร์มีค่าตัวแปรความเร่งและมุม ข้อมูลคีย์บอร์ดคือการกดคีย์บอร์ดเป็นตัวอักษรพร้อมทั้งเวลาการกดคีย์บอร์ด การวิจัยนี้ทำเพื่อช่วยการวินิจฉัยแยกแยะระหว่างอาการสั่นหรือมีปัญหาทางการควบคุมการเครื่องไหวของผู้ป่วยโรคอื่นและผู้ป่วยโรคพาร์กินสัน การวิจัยนี้ได้ใช้การเรียนรู้ของเครื่องเพื่อคัดกรองผู้ป่วยเบื้องต้นแทนการใช้แพทย์ผู้เชี่ยวชาญทางโรคพาร์กินสันสำหรับแพทย์แผนกผู้ป่วยนอกในวินิจฉัยการคัดกรองผู้ป่วยที่มีอาการใกล้เคียงอย่างการเคลื่อนไหว และความผิดปกติของระบบประสาทและสมอง ผลการวินิจฉัยพบว่าการเรียนรู้เครื่องสามารถตรวจพบการวินิจฉัยโรคพาร์กินสัน ได้ร้อยละความถูกต้องที่ 88.78 เปอร์เซ็นต์

การผสมความรู้ทางวิทยาศาสตร์ก่อนหน้าเข้ากับการเรียนรู้เชิงลึกสำหรับพยากรณ์ปริมาณฝนในระยะสั้นจากภาพถ่ายเรดาร์, ภัทรพงษ์ ด่านพูนกิจ

Chulalongkorn University Theses and Dissertations (Chula ETD)

การทำนายปริมาณน้ำฝนในระยะสั้นมีจุดมุ่งหมายเพื่อทำนายปริมาณน้ำฝนในอนาคตอันใกล้อย่างถูกต้องเพื่อนำไปใช้ประโยชน์ต่อในงานต่างๆ วิธีการดั้งเดิมทำนายผลโดยจำลองกระบวนการทางฟิสิกส์ที่ซับซ้อนหรือใช้การประมาณค่านอกช่วง โมเดลเชิงลึกที่ใช้ส่วนมากนั้นมักประสบความสำเร็จเพียงระดับหนึ่งเท่านั้นเนื่องจากความซับซ้อนของปัญหา ดังนั้นวิทยานิพนธ์นี้จึงเสนอวิธีการที่ผสมผสานระหว่างวิธีการทางวิทยาศาสตร์กับโมเดลเชิงลึกเพื่อใช้ประโยชน์จากทั้งสองศาสตร์ในการทำนาย โมเดลที่เสนอนี้มีโครงสร้างพื้นฐานบนวิธีการประมาณค่าเรดาร์นอกช่วงซึ่งเป็นวิธีการทางวิทยาศาสตร์ที่ทันสมัย โดยผู้วิจัยได้ทำการผสมผสานโดยแทนที่ส่วนย่อยของวิธีการนี้ที่ทำหน้าที่คำนวณสนามการเคลื่อนไหวด้วยโมเดลเชิงลึกที่เป็นโมเดลแบบรูปตัวยู ในขณะคงส่วนหลังที่ใช้เทคนิคการบิดเบือนไว้เพื่อทำหน้าที่ประมาณค่านอกช่วง ในการทดลองผู้วิจัยได้สร้างชุดข้อมูลจำลองที่ลอกเลียนคุณสมบัติสำคัญจากภาพถ่ายเรดาร์และทำการทดลองทั้งบนชุดข้อมูลจำลองดังกล่าวและชุดข้อมูลภาพถ่ายเรดาร์ที่ประกอบด้วยเหตุการณ์สภาพอากาศรุนแรง 7 กรณี นอกจากนี้ได้ทดลองใช้เทคนิคเปลี่ยนแปลงน้ำหนักของค่าสูญเสียเพื่อให้โมเดลมีประสิทธิภาพการทำนายฝนตกหนักสูงขึ้น จากผลการทดลองพบว่าวิธีการแบบผสมผสานที่เสนอให้ประสิทธิภาพที่ดีกว่าวิธีการมาตรฐานในกรณีส่วนมากบนชุดข้อมูลทั้งคู่

Red Blood Cell Segmentation And Classification From Microscopic Images Using Machine Learning, Korranat Naruenatthanaset

Chulalongkorn University Theses and Dissertations (Chula ETD)

Red blood cell morphology analysis plays an essential role in diagnosing many diseases caused by RBC disorders. This manual inspection is a long process and requires practice and experience. Since recent computer vision and image processing in the medical imaging area can provide efficient tools, it can help hematologists to automatically analyze images from a microscope in a reduced time and cost. This research presents a new method to segment and classify RBCs from blood smear images. The process started from data collection, which a new application was created for precisely labeling. The normalization was done to reduce the color …

Digital Platform Development For Performance Monitoring System In Oil And Gas Exploration And Production, Tanthai Poopaiboon

Chulalongkorn University Theses and Dissertations (Chula ETD)

The paper provides a case study to enhance the Performance Management System for Oil and Gas Exploration and Production industry. Although the system was designed for the Oil and Gas Exploration and Production industry, the paper could be applied effectively for other industries because the modern organisation mainly utilised the Key Performance Indicator (KPI) to reflect its performance. So, the paper could be applied to most organisations with minor modifications. The Advanced Performance Management System was developed systematically powered by digital transformation according to research methodology framework, including research, analysis, project development, and result measurement. The research stage is studying …

“Sorry I Didn’T Hear You.” The Ethics Of Voice Computing And Ai In High Risk Mental Health Populations, Fazal Khan, Christopher Villongco

Scholarly Works

This article examines the ethical and policy implications of using voice computing and artificial intelligence to screen for mental health conditions in low income and minority populations. Mental health is unequally distributed among these groups, which is further exacerbated by increased barriers to psychiatric care. Advancements in voice computing and artificial intelligence promise increased screening and more sensitive diagnostic assessments. Machine learning algorithms have the capacity to identify vocal features that can screen those with depression. However, in order to screen for mental health pathology, computer algorithms must first be able to account for the fundamental differences in vocal characteristics …

Multimodal Data Integration For Real-Time Indoor Navigation Using A Smartphone, Yaohua Chang

Dissertations and Theses

We propose an integrated solution of indoor navigation using a smartphone, especially for assisting people with special needs, such as the blind and visually impaired (BVI) individuals. The system consists of three components: hybrid modeling, real-time navigation, and client-server architecture. In the hybrid modeling component, the hybrid model of a building is created region by region and is organized in a graph structure with nodes as destinations and landmarks, and edges as traversal paths between nodes. A Wi-Fi/cellular-data connectivity map, a beacon signal strength map, a 3D visual model (with destinations and landmarks annotated) are collected while a modeler walks …

V-Slam And Sensor Fusion For Ground Robots, Ejup Hoxha

Dissertations and Theses

In underground, underwater and indoor environments, a robot has to rely solely on its on-board sensors to sense and understand its surroundings. This is the main reason why SLAM gained the popularity it has today. In recent years, we have seen excellent improvement on accuracy of localization using cameras and combinations of different sensors, especially camera-IMU (VIO) fusion. Incorporating more sensors leads to improvement of accuracy,but also robustness of SLAM. However, while testing SLAM in our ground robots, we have seen a decrease in performance quality when using the same algorithms on flying vehicles.We have an additional sensor for ground …

Reducing Payment-Card Fraud, Chares R. Ross

Walden Dissertations and Doctoral Studies

Critical public data in the United States are vulnerable to theft, creating severe financial and legal implications for payment-card acceptors. When security analysts and managers who work for payment card processing organizations implement strategies to reduce or eliminate payment-card fraud, they protect their organizations, consumers, and the local and national economy. Grounded in Cressey’s fraud theory, the purpose of this qualitative single case study was to explore strategies business owners and card processors use to reduce or eliminate payment-card fraud. The participants were 3 data security analysts and 1 manager working for an international payment card processing organization with 10 …

Relationship Between Specific Security Concerns And Cio Intention To Adopt Cloud, Johnathan Francis Van Houten

Walden Dissertations and Doctoral Studies

Cloud computing adoption rates have not grown commensurate with several well-known and substantially tangible benefits such as horizontal distribution and reduced cost, the latter both in terms of infrastructure and specialized personnel. The lack of adoption presents a challenge to both service providers from a sales perspective and service consumers from a usability focus. The purpose of this quantitative correlational study utilizing the technological, organizational, and environmental framework was to examine the relationship between shared technology (ST), malicious insiders (MI), account hijacking, data leakage, data protection, service partner trust (SP), regulatory concerns and the key decision-makers intention to adopt cloud …