Middle Tennessee State University
JEWLScholar @MTSU (Middle Tennessee State University)Not a member yet
7964 research outputs found
Sort by
Deep Data Driven Neural Networks for Learning Dynamics Of COVID-19 Epidemic Models
No full textWe present three deep-learning methods to analyze different COVID-19 epidemic models. The first method, an epidemiology-informed neural network, is developed to learn the model parameters and dynamics of a deterministic vaccine efficacy model. Data-driven simulations and error metrics confirm that vaccinating more people curtails the spread of the disease. Data-driven simulations of a hybrid approach comprising residual and recurrent neural networks show that the ResNet-GRU hybrid is superior.
In the second method, we learn the dynamics of the stochastic vaccine efficacy model by developing a stochastic epidemiology-informed neural network (SEINN). This method involves discretizing the system of stochastic differential equations using Euler-Murayama and encoding it as a loss function. The SEINN integrates a regularization parameter to enhance training accuracy. Subsequently, this second method aims to investigate the superiority of stochastic models over deterministic ones. Our findings show that stochastic models outperform their deterministic counterparts based on their error metrics. Finally, we examine the impact of stochasticity and vaccination on nonlinear incidence rates.
The behavior-epidemiology-informed neural network (BEINN) is the third method. It learns an explicit compliance rate that changes over time and identifies the critical epidemiological parameters of a behavioral epidemic model. This third algorithm incorporates behavioral constraints, attention mechanism, and the regularization parameter to improve training precision. This method aims to analyze how social and behavioral factors impact disease dissemination. The computational analysis of BEINN regarding sensitivity, overfitting, and computational time shows the effectiveness and robustness of the third method.
The epidemiological importance of this work includes the following: the outcome of the three methods can help public health officials develop effective vaccination and mitigation strategies by considering randomness in the model and the variability of human behavior in transmitting contagious diseases. We apply these three proposed methods to the spread of COVID-19 in Tennessee. The third methodology is employed to analyze the transmission of COVID-19 in the states of New York and Michigan.Ph.D
SIMULATING SURFACE AND GROUND WATER FLUXES IN COMPLEX KARST SYSTEMS – ANALYSIS OF MIDDLE AND EAST TENNESSEE’S SEQUATCHIE VALLEY USING THE ANNAGNPS WATERSHED POLLUTANT LOADING MODEL
No full textTopographic feature evaluation is a critical component for accurate interpretation and quantification of hydrologic flow in watersheds. In a typical drainage basin, topographic features identify and define surface drainage paths as flow traditionally travels through the most direct pathway. Alternatively, hydrology in karst terrain is often heterogeneous to surface topography and water rapidly redirects underground only to emerge elsewhere as discharge. This study evaluated the predictability of the Annualized Agricultural Non–Point Source (AnnAGNPS) model to simulate runoff over a six–year period (2016 to 2021) in the Sequatchie Valley and adjacent karst valleys located in the Cumberland Plateau of Middle and East Tennessee. After runoff calibration and statistical analysis, it was determined that utilizing the automated/semi–automated processes of AnnAGNPS produced results that indicate the model to be appropriate in simulating surface and surface–ground flow at annual–scales, although future work is recommended to improve monthly–scale results.M.S
EFFECTS OF ANXIETY ON ATTENTION-BASED TASKS IN A COLLEGE POPULATION
No full textWe explored how anxiety may impact performance on two attention-based tasks, the Navon and Stroop tasks. Previous literature has illustrated that trait anxiety may lead to diminishing global processing and, therefore, a local processing bias (Basso et al., 1996). Which may contribute to narrowing the scope of one’s attention, impairing cognitive flexibility (Derryberry & Reed, 1998; Najmi et al., 2012). Additionally, there is conflicting data on how anxiety interacts with performance on the Stroop task (Pacheco-Unguetti et al., 2010; Ursache & Cybele Raver, 2014). We conducted two t-tests analyzing high and low anxiety groups’ performance on the Navon task. We also conducted an ANOVA analyzing three groups’ performance on the Stroop task. We did not find any statistically significant differences in the performance on the Stroop and Navon task between groups of high anxiety and low anxiety.M.A
Confirming Measures of Social Motivation in Background Strains of Mice Using the Weighted Doors Task
No full textThe weighted doors task is a novel measure of social motivation and is used in the current
study to determine the differences in social motivation between C57 and BTBR mice as
well as sex differences. It was found that male mice displayed higher social motivation in
comparison to the female mice and the C57 mice displayed higher social motivation than
the BTBR mice. The social deficits the BTBR mice displayed support their continued use
as an Autism Spectrum Disorder (ASD) mouse model. Additionally, this research
validated the weighted doors task as a robust and reliable measure of social motivation,
allowing future neuroscience research to utilize the weighted doors task as a standardized
measure of social motivation. In this way, conditions such as ASD can be investigated
and better understood for future interventions
Text Summarization and Sentiment Analysis of Drug Reviews: A Transfer Learning Approach
No full textTransfer learning is a machine learning method where a model that has been trained on a specific or general task (source domain) is reused as a starting point for a similar task in a new model (target domain). This is an important concept in the Natural Language Processing field because of its ability to produce remarkable results from small datasets. Text summarization produces a concise and meaningful form of text from a larger one while sentiment analysis distinguishes the polarity present in the text. News and scientific articles have been used in text summarization models over the years, but drug reviews have gotten considerably less attention. This study proposes a text summarization and sentiment analysis method based on the transformer architecture for the 10 most useful reviews for 500 different drugs from a dataset of drugs reviews. We created human summaries for the drug reviews manually and compared the performance of a fine-tuned Text-to-Text Transfer Transformer (T5) model and Pre-training with extracted gap-sentences for abstractive summarization (PEGASUS) models with that of a Long Short-Term Memory (LSTM) model. Additionally, we assessed the impact of various preprocessing steps on the ROUGE scores. We also fine-tuned the Bidirectional Encoder Representation from Transformers (BERT) model for sentiment analysis in comparison to an LSTM model. Our T5-Base model had the best results with average ROUGE1, ROUGE2, and ROUGEL scores of 50.31, 29.14, and 40.06 respectively while the BERT model achieved an accuracy of 84\% for the sentiment analysis task. We evaluated our fine-tuned models on a dataset of BBC news summaries for text summarization and we achieved average ROUGE1, ROUGE2, and ROUGEL scores of 72.20, 63.59, and 57.42 respectively. Our models outperformed two previous works, which had ROUGE1, ROUGE2, and ROUGEL of 47.0, 33.0, 42.0 and 47.30, 26.50 and 36.10 respectively.M.S
Music as Oppression and Resistance: Prisoners of WWII Concentration Camps and Their Daily Encounters with Music
No full textIn this paper, I explore the role played by music in the Holocaust provides an
important understanding of the Holocaust. This research consists of looking into how
music was used as a form of oppression and resistance in concentration camps during
World War II. The detailed accounts of survivors who both experienced music as torture
and used it as resistance are the foundation for this research. Understanding the
connection between human emotions and music is important to be able to further
understand music itself and the history of music within the Holocaust. Prisoners in the
concentration camps took music and used it to validate and give meaning to their
existence against the oppressive forces of the Nazis through original compositions,
performances, and underlying subliminal messages within the musical works. To build
upon the foundation of survivor memoirs, I employ ideas from ethnomusicologists,
archivists in music and Holocaust history, and lyrical analysis of the music
Comparison of Raman and Surface FT-IR to Determine the Orientation of α-Synuclein (61-95) in Monolayer
No full textMembrane proteins poses a lot of challenges for analytical techniques. Thus, it is not a surprise that they are reported to only account for 2.4 % of the solved structures in protein databank, despite being encoded by ~20-30 % of all genes in total genomes. Resolving membrane protein structure is critical because the malfunction of proteins causes many diseases. For instance, the misfolding and subsequent aggregation of alpha-synuclein (α-syn), a protein made up of 140 amino acids, is currently thought to be a main cause of dopaminergic degeneration in Parkinson's disease. An important segmental peptide spanning residues 61-95 also known as the nonamyloid component (NAC) has been detected in the brain of Parkinson disease patients. α-Syn accumulates in the presynaptic terminals where high concentrations of vesicles exist at the amphiphilic interface. However, the reason of the accumulation of α-syn in the presynaptic terminals has been unclear due to the complication of the membrane structure. Fortunately, the amphiphilic membrane structure has been mimicked by the air-water interface as a simple model by a Langmuir monolayer technique. When combined with surface FTIR techniques such as p-polarized multiple-angle incidence resolution spectroscopy (pMAIRS), the conformation and orientation of membrane proteins can be evaluated by deconvoluting the amide I band. In this study, 13C isotope was introduced into α-syn (61-95) at 93G to provide residue-level information. Then, the effect of varying the holding time on the orientation was also investigated. In addition, Raman spectroscopy was also employed in this study and pMAIRS prove to be effective in determining the orientation of α-syn (61-95) even in monolayer.M.S
Rise, Fallen Empire! Exploring the Possibilities of Narrative Storytelling in Video Games
No full textNarrative storytelling has come a long way in video games. What was once a man
dodging barrels to save his lover from a gorilla is now forming relationships with
complex and compelling characters who try to save the world from destruction. In this
creative thesis, I take up the possibilities of narrative storytelling in video games by
creating a game design document and a prototype for a narrative-driven role-playing
game. Building on the video game industry standards for narrative-driven experiences,
the game offers an experience shared by four main protagonists; however, the player
plays in the perspective of one character per playthrough. They make their decisions that
will affect what they can do, how they act, and how their story unfolds
Survey of Classification Systems Used in US Performance Libraries
No full textKnowledge is power, and in order to utilize that knowledge, one has to be able to
find it. The way libraries organize their items so they may be located intuitively is called
classification. This paper aims to research and understand the classification scheme most
used by performance libraries, a specific type of library focusing on music. Performance
libraries are utilized by performing arts organizations to hold materials used to produce
performances. Utilizing original research performed through surveys and interviews, this
paper seeks to identify the most commonly used classification scheme for this type of
library
An Investigation on the Effectiveness of Iconic Gestures as a Vocabulary Teaching Strategy for Novel Concepts in the L2 Classroom
No full textGestures and other bodily movements are frequently used as instructional strategies in second language classrooms. Research has demonstrated that gestures are an effective strategy to improve L2 vocabulary recall. However, previous studies have only used vocabulary items that are known to participants in their native languages. Additionally, previous research has only investigated if gestures improve L2 recall, but whether such recall results in improved passage comprehension has not been studied. In this study, adolescent Spanish-speaking participants learned vocabulary items in English. Half of the words were concepts known to the participants in L1, but the other half were concepts that they had not yet learned in their native language. Half of the participants learned the vocabulary items while making representative gestures, while the other half learned the words by copying them down. After four days of instruction, participants took vocabulary and comprehension assessments over the words they learned. Results suggested that gestures were no more effective for learning L2 vocabulary as conventional second language teaching strategies, and that participants who copied the words learned abstract concepts better than those who made gestures. All participants demonstrated improved comprehension of sentences containing target vocabulary, but there was not a statistically significant difference between conditions. The results of this study suggest that gestures are not a useful strategy for students learning a second language in content-embedded classrooms. Limitations and directions for future research are discussed.Ph.D