Real Time Learning Level Assessment Using Eye Tracking, 2017 Florida Atlantic University
Real Time Learning Level Assessment Using Eye Tracking, Saurin S. Parikh, Hari Kalva
E-Learning is emerging as a convenient and effective learning tool. However, the challenge with eLearning is the lack of effective tools to assess levels of learning. Ability to predict difficult content in real time enables eLearning systems to dynamically provide supplementary content to meet learners’ needs. Recent developments have made possible low-cost eye trackers, which enables a new class of applications based on eye response. In comparison to past attempts using bio-metrics in learning assessments, with eye tracking, we can have access to the exact stimulus that is causing the response. A key aspect of the proposed approach is the ...
Classification Of Images Based On Pixels That Represent A Small Part Of The Scene. A Case Applied To Microaneurysms In Fundus Retina Images, Pablo F. Ordonez, Pablo F. Ordonez
Master of Science in Computer Science Theses
Convolutional Neural Networks (CNNs), the state of the art in image classification, have proven to be as effective as an ophthalmologist, when detecting Referable Diabetic Retinopathy (RDR). Having a size of less than 1\% of the total image, microaneurysms are early lesions in DR that are difficult to classify. The purpose of this thesis is to improve the accuracy of detection of microaneurysms using a model that includes two CNNs with different input image sizes, 60x60 and 420x420 pixels. These models were trained using the Kaggle and Messidor datasets and tested independently against the Kaggle dataset, showing a sensitivity of ...
Hospital Readmission And Social Risk Factors Identified From Physician Notes, 2017 University of Pennsylvania
Hospital Readmission And Social Risk Factors Identified From Physician Notes, Amol Navathe, Feiran Zhong, Victor J. Lei, Frank Y. Chang, Margarita Sordo, Maxim Topaz, Shamkant B. Navathe, Roberto A. Rocha, Li Zhou
No abstract provided.
A Study Of Activation Functions For Neural Networks, 2017 University of Arkansas, Fayetteville
A Study Of Activation Functions For Neural Networks, Meenakshi Manavazhahan
Computer Science and Computer Engineering Undergraduate Honors Theses
Artificial neural networks are function-approximating models that can improve themselves with experience. In order to work effectively, they rely on a nonlinearity, or activation function, to transform the values between each layer. One question that remains unanswered is, “Which non-linearity is optimal for learning with a particular dataset?” This thesis seeks to answer this question with the MNIST dataset, a popular dataset of handwritten digits, and vowel dataset, a dataset of vowel sounds. In order to answer this question effectively, it must simultaneously determine near-optimal values for several other meta-parameters, including the network topology, the optimization algorithm, and the number ...
Cusigns: A Dynamic Solution For Digital Signage, 2017 Cedarville University
Cusigns: A Dynamic Solution For Digital Signage, Jonathan Easterday, Wesley Kelly, Todd Landis, Nicole D. Perez
The Research and Scholarship Symposium
Cedarville University has computer monitors located throughout campus in order to show advertisements and important information to students, faculty, and staff. The slides shown on these displays are scheduled using Concerto: web-based software which manages digital signage. Though the Concerto software is currently used to manage digital signage, Cedarville University’s IT department desires features which Concerto does not provide, including the ability to play videos, a better slide randomization algorithm, emergency broadcasting features, and an intuitive user interface. We have created a new solution for digital signage called CUSigns with the goal of providing the existing functionality of Concerto ...
"Horse," A Composition For Solo Snare Drum And Live Electronics, 2017 Georgia State University
"Horse," A Composition For Solo Snare Drum And Live Electronics, Zachary Benator
Georgia State Undergraduate Research Conference
No abstract provided.
A Usability Study For Electronic Flight Bag (Efb) Flight Planning Applications On Tablet Devices For Ab-Initio Pilots, 2017 Seneca College of Applied Arts and Technology
A Usability Study For Electronic Flight Bag (Efb) Flight Planning Applications On Tablet Devices For Ab-Initio Pilots, Jeff Schwartzentruber
International Journal of Aviation, Aeronautics, and Aerospace
The proliferation of mobile technology has prompted the use of tablet devices in the cockpit and during ground operations in general aviation. Due to the increase in affordable and reliable hardware (i.e. iPads etc.), the development of pilot-specific software has led to the creation of a commercial-of-the-shelf (COTS), electronic flight bag (EFB) market. EFBs have many advantages, such as reducing the space requirements for flight documents, enabling faster searching and indexing of files, providing useful tools for flight planning, and providing automatic updates. The increase in availability of mobile technology and flight applications has allowed general aviation enthusiast and ...
Propagating Degrees Of Truth On An Argumentation Framework: An Abstract Account Of Fuzzy Argumentation, 2017 Dublin Institute of Technology
Propagating Degrees Of Truth On An Argumentation Framework: An Abstract Account Of Fuzzy Argumentation, Pierpaolo Dondio
This paper proposes a computational framework to reason with conflicting and gradual evidence. The framework is a synthesis of Dung’s seminal work in argumentation semantics with multi-valued logic. Abstract grounded semantics is used to identify the conditions under which a conclusion can be accepted, while multi-valued logic operators are used to quantify the degree of truth of such conditions. We propose a truth-compositional recursive computation based on the notion of irrelevant arguments, and we discuss examples using the major multi-valued logics: Godel’s, Zadeh’s and Łukasiewicz's logic.
Cyber Security Risks In Public High Schools, 2017 CUNY John Jay College
Cyber Security Risks In Public High Schools, Ion Goran
Today, just like other organizations, schools are vulnerable to cyber-attacks. This vulnerability has vividly revealed itself in recent years, with the number of attacks on public schools increasing and taking ever-changing forms. Today, the student’s grades, disciplinary notes, learning diagnoses, phone numbers, addresses, and another identifying information is all at risk of being exposed. Moreover, poor network security poses a dire threat to parents of school children whose personal records contain sensitive or dangerous information. The practical implications of these attacks require intervention or remedy to increase cyber security. Cyberattacks may take place when storage facilities or infected devices ...
How Mobile Payment Is Changing The World, 2017 Western Oregon University
How Mobile Payment Is Changing The World, Jin Huang
Student Theses, Papers and Projects (Computer Science)
People prefer to carry a smartphone which is more convenient than physical credit or debit cards in daily life, and mobile payment is the next step for the business world. This paper introduces several payment methods, such as mobile payment, NFC payment, QR-Code payment, and online banking. The paper researches how such payment methods change the trade and finance field, and their advantages and disadvantages. It describes the influences on the different market players. The study also investigates security, user experience, and business experience of mobile payment, to illustrate how the mobile payment replaces traditional payment methods. Finally, the best ...
Cloud Computing: Current And Future Impact On Organizations, 2017 Western Oregon University
Cloud Computing: Current And Future Impact On Organizations, Yiyun Zhu
Student Theses, Papers and Projects (Computer Science)
This project focuses on the business application of cloud computing, both at present and in the future. This investigation aims to assist business users of cloud computing services to improve the perception of cloud computing, to assess the value of their cloud computing service relationships, and to assist in selecting appropriate cloud computing services. This project bases its information on the existing cloud computing technology to clarify the technical aspects of current cloud services and companies. It presents the key elements of conception of cloud computing, its definitions, main service models, and implementation types. Ultimately, this paper analyzes the cons ...
A Hierarchical Learning Model For Extracting Public Health Data From Social Media, 2017 University of Nebraska at Omaha
A Hierarchical Learning Model For Extracting Public Health Data From Social Media, Elham Rastegari
Student Research and Creative Activity Fair
In decision making processes, particularly when it comes to health-related decisions, each relevant piece of information is important. This is particularly important when it comes to health conditions for which there remains a high degree of non-determinism as far as diagnosis and treatment. Online social media, are places in which people feel free to share their opinions about numerous topics, including public health issues and how individuals have responded to different types of treatments associated with diseases. social media could represent a secondary source that can be used as a supplement to other data sources. This would allow individuals as ...
Evergreen: A Senior Project, 2017 California Polytechnic State University, San Luis Obispo
Evergreen: A Senior Project, Ashley Grover
No abstract provided.
Android Mobile Application For Hospital Executives, 2017 California State University - San Bernardino
Android Mobile Application For Hospital Executives, Vihitha Nalagatla
Electronic Theses, Projects, and Dissertations
Hospitals are the largest and most complex organizations where health care is provided. Safe and effective patient care services in hospitals depend on the efficient decisions made by hospital executives. The main task of hospital executives is to ensure the hospital can provide high quality patient care and services. “Android Mobile Application For Hospital Executives” is an Android application used for displaying hospital performance metrics on a daily basis. This application allows hospital executives to review and monitor hospital operational data with ease of access and in a portable manner. Thus, reducing the effort of the hospital executives to perform ...
Bim Assisted Design Process Automation For Pre-Engineered Buildings (Peb), 2017 The University of Western Ontario
Bim Assisted Design Process Automation For Pre-Engineered Buildings (Peb), Mohammad Delavar
Electronic Thesis and Dissertation Repository
The effective adoption and implementation of Building Information Modeling (BIM) is still challenging for the construction industry. However, studies and reports show a significant increase in the rate of BIM implementation and adoption in mainstream construction activities over the last five years. In contrast, Pre-Engineered Building (PEB) construction, a specialized construction system which provides a very efficient approach for construction of primarily industrial buildings, has not seen the same uptake in BIM implementation and adoption. The thesis reviews the benefits and the main applications of BIM for the PEB industry as well as challenges of its practical implementation. To facilitate ...
Explorations Into Machine Learning Techniques For Precipitation Nowcasting, 2017 University of Massachusetts - Amherst
Explorations Into Machine Learning Techniques For Precipitation Nowcasting, Aditya Nagarajan
Masters Theses May 2014 - current
Recent advances in cloud-based big-data technologies now makes data driven solutions feasible for increasing numbers of scientific computing applications. One such data driven solution approach is machine learning where patterns in large data sets are brought to the surface by finding complex mathematical relationships within the data. Nowcasting or short-term prediction of rainfall in a given region is an important problem in meteorology. In this thesis we explore the nowcasting problem through a data driven approach by formulating it as a machine learning problem.
State-of-the-art nowcasting systems today are based on numerical models which describe the physical processes leading to ...
Gymfo: A Gym Finding Ios App Using Google Maps Api, 2017 The University of Akron
Gymfo: A Gym Finding Ios App Using Google Maps Api, Clay A. Wyers
Honors Research Projects
This project explores iOS mobile app development. I developed a gym finding app in Swift, using Google Maps APIs,and called it Gymfo. Other technologies were studied as well, including the cloud computing service Microsoft Azure. Through this project I learned the basics of XCode and Swift, Google APIs, and sending and receiving HTTP requests. The final product is an iOS app that allows users to search for nearby gyms and displays the results on an interactive map.
Image Processing And Understanding Based On Graph Similarity Testing: Algorithm Design And Software Development, 2017 University of Massachusetts - Amherst
Image Processing And Understanding Based On Graph Similarity Testing: Algorithm Design And Software Development, Jieqi Kang
Doctoral Dissertations May 2014 - current
Image processing and understanding is a key task in the human visual system. Among all related topics, content based image retrieval and classification is the most typical and important problem. Successful image retrieval/classification models require an effective fundamental step of image representation and feature extraction. While traditional methods are not capable of capturing all structural information on the image, using graph to represent the image is not only biologically plausible but also has certain advantages.
Graphs have been widely used in image related applications. Traditional graph-based image analysis models include pixel-based graph-cut techniques for image segmentation, low-level and high-level ...
Generating A Normalized Database Using Class Normalization, 2017 University of North Florida
Generating A Normalized Database Using Class Normalization, Daniel Sushil Sudhindaran
UNF Theses and Dissertations
Relational databases are the most popular databases used by enterprise applications to store persistent data to this day. It gives a lot of flexibility and efficiency. A process called database normalization helps make sure that the database is free from redundancies and update anomalies. In a Database-First approach to software development, the database is designed first, and then an Object-Relational Mapping (ORM) tool is used to generate the programming classes (data layer) to interact with the database. Finally, the business logic code is written to interact with the data layer to persist the business data to the database. However, in ...
Autonomous Driving Platform Performance Analysis, 2017 University of New Hampshire, Durham
Autonomous Driving Platform Performance Analysis, Charles R. Rickarby
Honors Theses and Capstones
Through data analysis of various plots and figures it will be possible to determine the best control parameters to get the best performance out of the autonomous driving platform. This data, presented in this thesis, will show quantitatively what the best control strategies are through comparison of different versions of the platform.