Other Computer Sciences Commons^™

Detecting And Mapping Real-Time Influenza-Like Illness Using Twitter Stream Data, Elisha D. Brunette

EWU Masters Thesis Collection

Influenza has been identified by the World Health Organization as a global issue that could be more effectively served through an accelerated and widely-accessible public health surveillance tracking process. The ability to map and predict influenza outbreaks in a real-time heat map would be invaluable to health care systems to prepare for influenza outbreaks. In this study, the Twitter stream data is filtered to identify potential influenza-like illness (ILI) cases. Then the tracking of real-time influenza cases is further explored and analyzed through various machine-learning models. Among seven learning models developed to identify ILI tweets, the ELMo deep neural network …

Browsing Via Sonification, Taylor C. Cutlip

Graduate Theses, Dissertations, and Problem Reports (ETD)

Based on unexpected results in her previous research, Dr. Frances Van Scoy became inspired to develop a tool that allows the user to navigate spaces using auditory instead of visual cues to detect objects or anomalies in a given space in an effort to overcome the encountered obstacles. This problem report details the work of one of her grad students in exploring different open source software for developing the tool as well as research into gestures and other considerations when furthering this research into the third dimension at a future date.

Evaluation And Understandability Of Face Image Quality Assessment, Mohammad I. Nouyed

Graduate Theses, Dissertations, and Problem Reports (ETD)

Face image quality assessment (FIQA) has been an area of interest to researchers as a way to improve the face recognition accuracy. By filtering out the low quality images we can reduce various difficulties faced in unconstrained face recognition, such as, failure in face or facial landmark detection or low presence of useful facial information. In last decade or so, researchers have proposed different methods to assess the face image quality, spanning from fusion of quality measures to using learning based methods. Different approaches have their own strength and weaknesses. But, it is hard to perform a comparative assessment of …

Predicting Post-Procedural Complications Using Neural Networks On Mimic-Iii Data, Namratha Mohan

LSU Master's Theses

The primary focus of this paper is the creation of a Machine Learning based algorithm for the analysis of large health based data sets. Our input was extracted from MIMIC-III, a large Health Record database of more than 40,000 patients. The main question was to predict if a patient will have complications during certain specified procedures performed in the hospital. These events are denoted by the icd9 code 996 in the individuals' health record. The output of our predictive model is a binary variable which outputs the value 1 if the patient is diagnosed with the specific complication or 0 …

Proposing An Optimized Algorithm For Consolidating Electric-Powered Shared Scooters Into Hubs For Efficiently Managing Their Charging And Maintenance Operations, Ojen Goshtasb

Master's Projects

The use of vehicles other than ones containing combustion engines have been adopted significantly over the past few years and the direction it’s taking seems to be the future of urban transportation. The hottest vehicle of choice currently is the electric scooter. They are small and portable, fast, and less costly compared to getting in a cab from Lyft or Uber to get around town. The goal of this paper is to make a proposal to drive the creation of a safe, efficient system for these scooters’ management. This must be beneficial to all parties involved; the rider, non-riders, and …

The Evolution Of Computational Propaganda: Trends, Threats, And Implications Now And In The Future, Holly Schnader

Senior Honors Projects, 2010-2019

Computational propaganda involves the use of selected narratives, social networks, and complex algorithms in order to develop and conduct influence operations (Woolley and Howard, 2017). In recent years the use of computational propaganda as an arm of cyberwarfare has increased in frequency. I aim to explore this topic to further understand the underlying forces behind the implementation of this tactic and then conduct a futures analysis to best determine how this topic will change over time. Additionally, I hope to gain insights on the implications of the current and potential future trends that computational propaganda has.

My preliminary assessment shows …

Variations On A Theme: Using Amino Acid Sequences To Generate Music, Aaron Kosmatin

Master's Projects

In this project, we explore using a musical space to represent the properties of amino acids. We consider previous mappings and explore the limitations of these mappings. In this exploration, we will propose a new method of mapping into musical spaces that extends the properties that can be represented. For this work, we will use amino acid sequences as our example mapping. The amino acid properties we will use include mass, charge, structure, and hydrophobicity. Finally, we will show how the different musical properties can be compared for similarity.

Intra-Exchange Cryptocurrency Arbitrage Bot, Eric Han

Master's Projects

Cryptocurrencies are defined as a digital currency in which encryption techniques are utilized to regulate generation of units of currency and verify the transfer of funds, independent of a central governing body such as a bank. Due to the large number of cryptocurrencies currently available, there inherently exists many price discrepancies due to market inefficiencies. Market inefficiencies occur when the price of assets do not reflect their true value. In fact, these types of pricing discrepancies exist in other financial markets, including fiat currency exchanges and stock exchanges. However, these discrepancies are more significant in the cryptocurrency domain due to …

Using Deep Learning To Forecast Spatiotemporal Crime Patterns, Shuzhan Fan

LSU Doctoral Dissertations

The distributional patterns of crime occurrences are closely related to their spatial, temporal, and environmental contexts. It has been a hot topic for researchers and crime analysts to discover such complex relationships in order to forecast crime, both spatially and temporally. Many factors play a role in the occurrences of crimes. Conventional crime forecasting research has primarily relied on historical crime records and socioeconomic data, while ignoring the rich social media and other environmental context data. The large volume of data requires a more appropriate forecasting framework with the ability to take in massive multimodal data and possibly achieve better …

A Transfer Learning Approach For Sentiment Classification., Omar Abdelwahab

Electronic Theses and Dissertations

The idea of developing machine learning systems or Artificial Intelligence agents that would learn from different tasks and be able to accumulate that knowledge with time so that it functions successfully on a new task that it has not seen before is an idea and a research area that is still being explored. In this work, we will lay out an algorithm that allows a machine learning system or an AI agent to learn from k different domains then uses some or no data from the new task for the system to perform strongly on that new task. In order …

Relationships Between Social Network Characteristics, Alcohol Use, And Alcohol-Related Consequences In A Large Network Of First-Year College Students: How Do Peer Drinking Norms Fit In?, Graham T. Diguiseppi, Matthew K. Meisel, Sara G. Balestrieri, Miles Q. Ott, Melissa A. Clark, Nancy P. Barnett

Statistical and Data Sciences: Faculty Publications

A burgeoning area of research is using social network analysis to investigate college students' substance use behaviors. However, little research has incorporated students' perceived peer drinking norms into these analyses. The present study investigated the association between social network characteristics, alcohol use, and alcohol-related consequences among first-year college students (N 1,342; 81% of the first-year class) at one university. The moderating role of descriptive norms was also examined. Network characteristics and descriptive norms were derived from participants' nominations of up to 10 other students who were important to them; individual network characteristics included popularity (indegree), network expansiveness (outdegree), relationship reciprocity, …

Using Dna For Data Storage: Encoding And Decoding Algorithm Development, Kelsey Suyehira

Boise State University Theses and Dissertations

The recent explosion of digital data has created an increasing need for improved data storage architectures with the ability to store large amounts of data over extensive periods of time. DNA as a data storage solution shows promise with a thousand times greater increase in information density and information retention times ranging from hundreds to thousands of years. This thesis explores the challenges and potential approaches in developing an encoding and decoding algorithm for use in a DNA data storage architecture. When encoding binary data into sequences representing DNA strands, the algorithms should account for biological constraints representing the idiosyncrasies …

Cleaver: Classification Of Everyday Activities Via Ensemble Recognizers, Samantha Hsu

Master's Theses

Physical activity can have immediate and long-term benefits on health and reduce the risk for chronic diseases. Valid measures of physical activity are needed in order to improve our understanding of the exact relationship between physical activity and health. Activity monitors have become a standard for measuring physical activity; accelerometers in particular are widely used in research and consumer products because they are objective, inexpensive, and practical. Previous studies have experimented with different monitor placements and classification methods. However, the majority of these methods were developed using data collected in controlled, laboratory-based settings, which is not reliably representative of real …

Multidimensional Feature Engineering For Post-Translational Modification Prediction Problems, Norman Mapes Jr.

Doctoral Dissertations

Protein sequence data has been produced at an astounding speed. This creates an opportunity to characterize these proteins for the treatment of illness. A crucial characterization of proteins is their post translational modifications (PTM). There are 20 amino acids coded by DNA after coding (translation) nearly every protein is modified at an amino acid level. We focus on three specific PTMs. First is the bonding formed between two cysteine amino acids, thus introducing a loop to the straight chain of a protein. Second, we predict which cysteines can generally be modified (oxidized). Finally, we predict which lysine amino acids are …

Constrained K-Means Clustering Validation Study, Nicholas Mcdaniel, Stephen Burgess, Jeremy Evert

Student Research

Machine Learning (ML) is a growing topic within Computer Science with applications in many fields. One open problem in ML is data separation, or data clustering. Our project is a validation study of, “Constrained K-means Clustering with Background Knowledge" by Wagstaff et. al. Our data validates the finding by Wagstaff et. al., which shows that a modified k-means clustering approach can outperform more general unsupervised learning algorithms when some domain information about the problem is available. Our data suggests that k-means clustering augmented with domain information can be a time efficient means for segmenting data sets. Our validation study focused …

Validation Study Of Image Recognition Algorithms, Jacob Miller, Jeremy Evert

Student Research

Developments in machine learning in recent years have created opportunities that previously never existed. One such field with an explosion of opportunity is image recognition, also known as computer vision; the process in which a machine analyzes a digital image.

In order for a machine to ‘see’ as a human does, it must break down the image in a process called image segmentation. The way the machine goes about doing this is important, and many algorithms exist to determine just how a machine will decide to group the pixels in an image.

This research is a validation study of related …

Project Management Madness: 3 Key Programs For Communication, Personal Tasks And Large Projects, Rachel S. Evans

Presentations

No matter what member of a team you are, be it content editor, web designer, database manager or systems administrator, getting things done and meeting goals depends largely on how you communicate with one another, handle your time and effectively collaborate on small and big projects. This session will use our own team's preferred platforms to show specific examples of how we are managing our taskflow across three different programs to tackle business as usual, short and long term work, and major special projects.

The three programs that will be compared for pros, cons, and their integration with one another …

A Multi-Task Approach To Incremental Dialogue State Tracking, Anh Duong Trinh, Robert J. Ross, John D. Kelleher

Conference papers

Incrementality is a fundamental feature of language in real world use. To this point, however, the vast majority of work in automated dialogue processing has focused on language as turn based. In this paper we explore the challenge of incremental dialogue state tracking through the development and analysis of a multi-task approach to incremental dialogue state tracking. We present the design of our incremental dialogue state tracker in detail and provide evaluation against the well known Dialogue State Tracking Challenge 2 (DSTC2) dataset. In addition to a standard evaluation of the tracker, we also provide an analysis of the Incrementality …

Leveling The Playing Field: Supporting Neurodiversity Via Virtual Realities, Louanne E. Boyd, Kendra Day, Natalia Stewart, Kaitlyn Abdo, Kathleen Lamkin, Erik J. Linstead

Mathematics, Physics, and Computer Science Faculty Articles and Research

Neurodiversity is a term that encapsulates the diverse expression of human neurology. By thinking in broad terms about neurological development, we can become focused on delivering a diverse set of design features to meet the needs of the human condition. In this work, we move toward developing virtual environments that support variations in sensory processing. If we understand that people have differences in sensory perception that result in their own unique sensory traits, many of which are clustered by diagnostic labels such as Autism Spectrum Disorder (ASD), Sensory Processing Disorder, Attention-Deficit/Hyperactivity Disorder, Rett syndrome, dyslexia, and so on, then we …

How We Done It Good: Research Through Design As A Legitimate Methodology For Librarianship, Rachel Ivy Clarke

School of Information Studies - Faculty Scholarship

“How we done it good” publications—a genre concerning project-based approaches that describe how (and sometimes why) something was done—are often rebuked in the library research community for lacking traditional scientific validity, reliability, and generalizability. While scientific methodologies may be a common approach to research and inquiry, they are not the only methodological paradigms. This research posits that the “how we done it good” paradigm in librarianship reflects a valid and legitimate approach to research. By drawing on the concept of research through design, this study shows how these “how we done it good” projects reflect design methodologies which draw …