Digital Commons Network^™

Automated Methods For Estimating Blood Alcohol Concentration Level From Facial Cues, Ensiyeh Keshtkaran

Theses: Doctorates and Masters

This thesis investigates different approaches for detecting alcohol intoxication in drivers by analysing facial video data. Tackling this issue necessitates the creation of a novel dataset to overcome the limitations of existing datasets. The dataset constructed in this study is the first to include RGB video recordings of individual faces at varying levels of alcohol intoxication during simulated driving, featuring 60 participants with BAC levels ranging from 0 to 0.165 g/100ml. The constructed dataset not only supports this thesis, but also offers the broader scientific community a valuable resource for further study and development.

Building on this, this thesis presents …

A Comprehensive Usability And Economic Analysis Of Heat-Related Wearable Technologies: Applications To Occupational Health, Ryan T. Cannady

Theses & Dissertations

The purpose of this research was to analyze the usability and economic considerations of real-time wearable technologies that are implemented in occupational settings to assess risk of heat stress and heat strain. The study population included current agriculture workers and Department of Energy (DOE), Environmental Management (EM) contractors. We employed a mixed-methods approach to comprehensively analyze the usability and economic considerations of heat-related technologies. Specifically, our approach assessed three distinct aspects the applications of these technologies in occupational settings to comprehensively address our research objective: (1) worker perceptions of heat-related wearable technologies, (2) field-based assessment of these heat-related wearable technologies, …

(R2111) Effect Of Stenotic-Aneurysmal Arterial Regime On Unsteady Magnetohydrodynamic Non-Newtonian Blood Flow With Heat Radiation, Babatunde A. Joseph, Dada M. Sunday, Bello A.J. Funsho, Akeem B. Disu, Alamu-Awoniran F., Danas James Y.

Applications and Applied Mathematics: An International Journal (AAM)

The study aims to investigate the effect of magneto-hydrodynamic on a non-Newtonian unsteady blood flow with internal heat energy in the presence of blood ironic properties characterized by stenosis. The formulated mathematical equations resulted in differential forms and were solved analytically by Differential Transform Method. The obtained solutions were displayed by graphs showing different flow physiognomies like blood velocity, temperature profile, Nusselt number, wall shear stress and stream function.

The results indicated that velocity profile increases as magnetic field, Darcy number and aneurysmal artery rise, while it decreases as heat radiation, Reynold number, and Casson parameter speedup. The temperature profile …

Advancing Emotional Health Assessments: A Hybrid Deep Learning Approach Using Physiological Signals For Robust Emotion Recognition, Amna Waheed Awan, Imran Taj, Shehzad Khalid, Syed Muhammad Usman, Ali Shariq Imran, Muhammad Usman Akram

All Works

Emotional health significantly impacts physical and psychological well-being, with emotional imbalances and cognitive disorders leading to various health issues. Timely diagnosis of mental illnesses is crucial for preventing severe disorders and enhancing medical care quality. Physiological signals, such as Electrocardiograms (ECG) and Electroencephalograms (EEG), which reflect cardiac and neuronal activities, are reliable for emotion recognition as they are less susceptible to manipulation than physical signals. Galvanic Skin Response (GSR) is also closely linked to emotional states. Researchers have developed various methods for classifying signals to detect emotions. However, these signals are susceptible to noise and are inherently non-stationary, meaning they …

Optimization Of Mass Spectrometry-Based Methods For Low-Input And Spatial Proteomics, Andikan Jones Nwosu

Theses and Dissertations

Eukaryotic cells are highly heterogeneous. These cells are arranged into different compartments, carrying out separate functions and facilitating biological processes. Proteins are the effector biomolecules targeted to subcellular locations that help fulfill specific tasks in living organisms. Spatial proteomics can help unravel molecularly how protein abundance and localization are altered in cells, which is not feasible in traditional bulk-scale proteomics. To achieve this, our lab has developed a miniaturized sample processing platform called nanoPOTS, reduced separation columns' inner diameter to increase ionization efficiency and concentrate analytes for mass spectrometers and optimized data acquisition modes for increasing proteome coverage in spatial …

T. Boudieri Extract Potentiates The Effects Of Capecitabine Treatment In Human Colon Cancer Cells, Katia Sawaya, Mahmoud Khalil, Ghada Khawaja

BAU Journal - Science and Technology

Resistance to chemotherapy remains a major challenge for colorectal cancer patients worldwide, hence the persistent need to uncover alternative treatments as well as new adjunct therapies in the fight against cancer. Natural extracts constitute an excellent source of bioactive substances that have a promising potential in that regard, with minimal negative side effects. We have previously demonstrated that both the ethanolic as well as the water extracts of Terfezia boudieri, a black desert truffle abundant in and part of the cuisine of the Mediterranean region, have significant antiproliferative effects against colon cancer cells. Our aim in this study was …

Advancing Sentiment Analysis Through Emotionally-Agnostic Text Mining In Large Language Models (Llms), Jay Ratican, James Hutson

Faculty Scholarship

The conventional methodology for sentiment analysis within large language models (LLMs) has predominantly drawn upon human emotional frameworks, incorporating physiological cues that are inherently absent in text-only communication. This research proposes a paradigm shift towards an emotionallyagnostic approach to sentiment analysis in LLMs, which concentrates on purely textual expressions of sentiment, circumventing the confounding effects of human physiological responses. The aim is to refine sentiment analysis algorithms to discern and generate emotionally congruent responses strictly from text-based cues. This study presents a comprehensive framework for an emotionally-agnostic sentiment analysis model that systematically excludes physiological indicators whilst maintaining the analytical depth …

Development Of An Enhanced Sampling Workflow To Accelerate Molecular Docking With Sparse Biophysical Information, Zachary Stichter

Masters Theses & Specialist Projects

Rapid docking of flexible biological macromolecules remains a significant open challenge in protein structure determination. While rigid docking is relatively simple with toolkits such as TagDock, a key obstacle to rapid flexible docking is the complexity and roughness of the free energy surface associated with protein conformational motion (often termed the many-minima problem), meaning conventional molecular dynamics methods do not effectively sample protein conformations near the interaction complex in accessible timescales. Methods such as metadynamics and replica exchange molecular dynamics exist to ameliorate this obstacle, yet these methods use nonphysical biases or random swaps to enhance sampling. In contrast, high …

Igwas: Image-Based Genome-Wide Association Of Self-Supervised Deep Phenotyping Of Retina Fundus Images, Ziqian Xie, Tao Zhang, Sangbae Kim, Jiaxiong Lu, Wanheng Zhang, Cheng-Hui Lin, Man-Ru Wu, Alexander Davis, Roomasa Channa, Luca Giancardo, Han Chen, Sui Wang, Rui Chen, Degui Zhi

Faculty, Staff and Student Publications

Existing imaging genetics studies have been mostly limited in scope by using imaging-derived phenotypes defined by human experts. Here, leveraging new breakthroughs in self-supervised deep representation learning, we propose a new approach, image-based genome-wide association study (iGWAS), for identifying genetic factors associated with phenotypes discovered from medical images using contrastive learning. Using retinal fundus photos, our model extracts a 128-dimensional vector representing features of the retina as phenotypes. After training the model on 40,000 images from the EyePACS dataset, we generated phenotypes from 130,329 images of 65,629 British White participants in the UK Biobank. We conducted GWAS on these phenotypes …

Virtual Reality As An Adjunct To Behavior Therapy: A Systematic Literature Review, Alya Alharrasi

Honors Theses

The World Health Organization (WHO) projects that by 2030, mental disorders will become the primary source of global disease burden [1]. Anxiety-related disorders, including specific phobias, post-traumatic stress disorder (PTSD), and various forms of general or specific anxiety, are the most rapidly growing mental health disorders worldwide [2]. In the United States (US), over 1 in 10 American youths are experiencing depression, resulting in a severe impact on their personal, academic, or professional encounters and social engagements [3]. Similarly, anxiety disorders affect up to one-third of the US population during their lifetime [4].

Due to the growth of mental health …

Interrelationships Among Local Values Of Wet Bulb Globe Temperature, Heat Index, And Adjusted Temperature, Andrea Giraldo

USF Tampa Graduate Theses and Dissertations

Occupational heat stress significantly affects outdoor workers who face challenges due to increased heat exposure. Because of the prevalence of heat illness, it is important to measure heat stress for outdoor workers. Monitoring occupational heat stress most often relies on the Wet Bulb Globe Temperature (WBGT) measure. Heat Index (HI) is a widely used measure to account for air temperature and humidity. Adjusted Temperature (Tadj) considers air temperature, humidity and estimates radiant heat. There is interest in predicting WBGT from HI and HI from WBGT. This study builds on previous USF research by Bernard and Iheanacho and Irvin to evaluate …

Ur2m: Uncertainty And Resource-Aware Event Detection On Microcontrollers, Hong Jia, Young D. Kwon, Dong Ma, Nhat Pham, Lorena Qendro, Tam Vu, Cecilia Mascolo

Research Collection School Of Computing and Information Systems

Traditional machine learning techniques are prone to generating inaccurate predictions when confronted with shifts in the distribution of data between the training and testing phases. This vulnerability can lead to severe consequences, especially in applications such as mobile healthcare. Uncertainty estimation has the potential to mitigate this issue by assessing the reliability of a model's output. However, existing uncertainty estimation techniques often require substantial computational resources and memory, making them impractical for implementation on microcontrollers (MCUs). This limitation hinders the feasibility of many important on-device wearable event detection (WED) applications, such as heart attack detection. In this paper, we present …

Reinforcement Learning For Team Based Air Combat Maneuvering Decisions With Directed Energy Weaponry, Joshua D. Combs

Theses and Dissertations

Leveraging the Advanced Framework for Simulation, Integration, and Modeling (AFSIM) we investigate the use of reinforcement learning (RL) techniques for imbuing AUCAV agents with high-quality behaviors for the within-visual-range air combat maneuvering problem (ACMP). We formulate the 2v2 WVR ACMP as a Markov decision process wherein friendly AUCAVs are equipped with DEW capabilities and operate with 6 degrees of freedom. We utilize the Double Deep Q-Network RL algorithm, which centrally trains two friendly AUCAVs and employ a phased learning approach, initially exposing the AUCAVs to a dense reward environment for early training, followed by a sparse reward environment to encourage …

Platform-Independent Estimation Of Human Physiological Time From Single Blood Samples, Yitong Huang, Rosemary Braun

Mathematics Sciences: Faculty Publications

Abundant epidemiological evidence links circadian rhythms to human health, from heart disease to neurodegeneration. Accurate determination of an individual's circadian phase is critical for precision diagnostics and personalized timing of therapeutic interventions. To date, however, we still lack an assay for physiological time that is accurate, minimally burdensome to the patient, and readily generalizable to new data. Here, we present TimeMachine, an algorithm to predict the human circadian phase using gene expression in peripheral blood mononuclear cells from a single blood draw. Once trained on data from a single study, we validated the trained predictor against four independent datasets with …

Advanced Optical Biosensing Using Ratiometric Fluorescent Polymer Dots And Nanozyme, Shuyi He

Dissertations and Theses

Biosensors have been deeply valued and widely used in fermentation technology, environmental monitoring, food engineering, clinical medicine, and the military. However, current biosensors still face many technical challenges, such as miniaturization, convenience, high precision, and low power consumption which restrict the popularization and development of biosensors. Meeting these challenges require the development of advanced materials and technologies. Optical biosensors offer distinct advantages such as high sensitivity, rapid response time, and the potential for miniaturization, making them ideal for overcoming the existing limitations. My research in this dissertation explores the development and application of advanced functional nanomaterials in optical biosensing, focusing …

Cyclistai: A Smartphone Solution For Cyclist Stress Assessment Using Deep Learning, Aairish Singh

Computer Science and Engineering Theses - Archive

Cycling presents a compelling solution for promoting personal health and environmental well-being, particularly for short-distance travel. Despite its numerous advantages, cycling uptake in the United States remains disproportionately low, primarily due to safety concerns. Traditional frameworks for assessing cyclist stress are hindered by their impracticality and inability to provide real-time evaluations. Self-report surveys and physiological measurements offer alternative approaches but suffer from limitations such as retrospective reporting biases and accessibility challenges, respectively. This thesis introduces CyclistAI, a novel smartphone-based cyclist stress assessment model that leverages context sensing. By combining Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) techniques, CyclistAI …

Adaptable And Trustworthy Machine Learning For Human Activity Recognition From Bioelectric Signals, Morgan S. Stuart

Theses and Dissertations

Enabling machines to learn measures of human activity from bioelectric signals has many applications in human-machine interaction and healthcare. However, labeled activity recognition datasets are costly to collect and highly varied, which challenges machine learning techniques that rely on large datasets. Furthermore, activity recognition in practice needs to account for user trust - models are motivated to enable interpretability, usability, and information privacy. The objective of this dissertation is to improve adaptability and trustworthiness of machine learning models for human activity recognition from bioelectric signals. We improve adaptability by developing pretraining techniques that initialize models for later specialization to unseen …

Determinants Of Physicochemical Composition Of Palm Oil Mill Effluent - Implications On Environment And Bio-Digester Treatment Design, E.B. Tambe, A.U. Okonkwo, I.E. Mbuka-Nwosu, C.O. Cookey, E. Agbe, S.C. Onwusa, I.N. Ekpe, U.F. Evuen, J. Okpoghono

Applied Environmental Research

Growing need for renewable energy and addressing challenges associated with indiscriminate wastes disposal has necessitated harnessing wastes to wealth. The study investigated parameters determining the physicochemical composition of palm oil mill effluent (POME) generated at Agricultural Development Authority Palm (ADAPALM) and palm oil mills in its catchment communities, located at Ohaji/ Egbema Local Government Area of Imo State, Nigeria and their implications on environmental health and treatment approaches required. Survey research design was used. From a randomly sampled small-scaled mill in each community, and for the lone medium and large-scaled mills, four homogenous samples of POME were collected from sampled …

In Vivo Measurement Of Nadh Fluorescence Lifetime In Skeletal Muscle Via Fiber-Coupled Time-Correlated Single Photon Counting, Kathryn M. Priest, Jacob V. Schluns, Nathania Nischal, Colton L. Gattis, Jeffery C. Wolchok, Timothy J. Muldoon

Biomedical Engineering Faculty Publications and Presentations

Nicotinamide adenine dinucleotide (NADH) is a cofactor that serves to shuttle electrons during metabolic processes such as glycolysis, the tricarboxylic acid cycle, and oxidative phosphorylation (OXPHOS). NADH is autofluorescent, and its fluorescence lifetime can be used to infer metabolic dynamics in living cells. Fiber-coupled time-correlated single photon counting (TCSPC) equipped with an implantable needle probe can be used to measure NADH lifetime in vivo, enabling investigation of changing metabolic demand during muscle contraction or tissue regeneration. This study illustrates a proof of concept for point-based, minimally-invasive NADH fluorescence lifetime measurement in vivo. Volumetric muscle loss (VML) injuries were …

(R2055) Magnetic Effects On Unsteady Non-Newtonian Blood Flow Through A Tapered And Overlapping Stenotic Artery, Abiodun J. Babatunde, Moses S. Dada

Applications and Applied Mathematics: An International Journal (AAM)

This study aims to investigating the effect of magnetic field and porosity on non-Newtonian flow of blood through a tapered, and overlapping stenosed artery. The Casson fluid model represents the rheological character of blood. A tapered and overlapping stenosed artery influences the hemodynamic behavior of the blood flow. The problem is solved by using analytical techniques with the help of boundary conditions, and results are displayed graphically for different flow characteristics like pressure drop, shear stress, velocity profile and stream function. It is realized that rises in Darcy number and Womersley number accelerates the velocity profile and reduces the radial …

A Novel Computing Scheme Based On Pattern Matching For Identification Of Nephron Loss And Chronic Kidney Disease Stage, Rehan Ahmad, Basant Mohanty

Turkish Journal of Electrical Engineering and Computer Sciences

Nephrons are the basic filtering units of the kidneys. Progression of chronic kidney disease (CKD) destroys nephrons permanently. Although there are many computing schemes suggested in recent years to identify CKD stages, no computing method has been suggested for identifying the nephron loss within kidney regions during CKD progression. In this paper, a novel pattern matching-based computation scheme is proposed to detect nephron loss in the kidney regions during CKD progression. We consider image registration (IR) with different transforms and a structural similarity index algorithm (SSIM) to match patterns of ultrasound images of kidney regions to identify the nephron loss. …

Electrospun Ethyl Cellulose Nanofibers With Phase Change Materials: Designing Temperature-Responsive Drug Delivery Systems, Michael Wildy

Theses and Dissertations

In this study, ethyl cellulose (EC) nanofibers loaded with either Rhodamine B (RhB) or Doxorubicin HCl (DOX) and phase change materials (PCM) were fabricated by blend electrospinning. EC is a cellulose derivative widely used as an excipient in the pharmaceutical industry and an ideal polymer for controlled drug release. Lauric acid (LA) and stearic acid (SA) were used as a material with a melting point close to physiological body temperature. Good drug-polymer compatibility and an amorphous distribution of drugs were shown by Fourier transform infrared spectroscopy, differential scanning calorimetry, and X-ray diffraction. The release rate of RhB was shown to …

Electrospun Nanofibers: Shaping The Future Of Controlled And Responsive Drug Delivery., Michael Joshua Wildy, Ping Lu

College of Science & Mathematics Departmental Research

Electrospun nanofibers for drug delivery systems (DDS) introduce a revolutionary means of administering pharmaceuticals, holding promise for both improved drug efficacy and reduced side effects. These biopolymer nanofiber membranes, distinguished by their high surface area-to-volume ratio, biocompatibility, and biodegradability, are ideally suited for pharmaceutical and biomedical applications. One of their standout attributes is the capability to offer the controlled release of the active pharmaceutical ingredient (API), allowing custom-tailored release profiles to address specific diseases and administration routes. Moreover, stimuli-responsive electrospun DDS can adapt to conditions at the drug target, enhancing the precision and selectivity of drug delivery. Such localized API …

Soft Microreactors For The Deposition Of Microstructures And The Related Surface Chemistries Of Polymeric Materials, Jessica Wagner

Dissertations and Doctoral Documents, University of Nebraska-Lincoln, 2023–

The precise control over small volumes of liquids is of great interest to various fields such as biotechnology, drug development, and diagnostics. Working at small scales reduces cost, time, and waste, which is why microfluidic lab-on-chip technologies have become popular in a wide range of industries and applications. Additionally, there are differences in properties such as mass transport and heat dissipation at the micron scale compared to in bulk. Microfluidic devices contain several interfaces to consider when preparing to fabricate devices. The substrate/device, substrate/solution, and solution/device interfaces are all of importance and must carefully be tuned depending on the desired …

International Conference On Mechatronic, University For Business And Technology - Ubt

UBT International Conference

UBT Annual International Conference is the 12th international interdisciplinary peer reviewed conference which publishes works of the scientists as well as practitioners in the area where UBT is active in Education, Research and Development. The UBT aims to implement an integrated strategy to establish itself as an internationally competitive, research-intensive university, committed to the transfer of knowledge and the provision of a world-class education to the most talented students from all background. The main perspective of the conference is to connect the scientists and practitioners from different disciplines in the same place and make them be aware of the recent …

Wearable Sensor-Based Walkability Assessment At Ferry Terminal Using Machine Learning: A Case Study Of Mokpo, Korea, Jungyeon Choi, Hwayoung Kim

Journal of Marine Science and Technology–Taiwan

Walkability assessments are becoming more popular, as walking offers numerous health, environmental, and economic benefits to communities. However, previous studies on ferry terminal walkability assessment have been inadequate. This study aimed to develop a wearable sensor system to automatically assess walkability at ferry terminals without conducting surveys. We applied seven machine learning (ML) classifiers to detect different walking environments, including flat ground (FG), downhill slope (DS), uphill slope (US), and uneven surface (UE). The ML models were evaluated across different combinations of classes: 2-class (FG vs. UE), 3-class (U) (FG vs. US vs. UE), 3-class (D) (FG vs. DS vs. …

Biopsychosocial Resilience Through A Complex Adaptive Systems Lens: A Narrative Review Of Nonlinear Modeling Approaches, Adam W. Kiefer, David Pincus

Psychology Faculty Articles and Research

Human resilience is often considered as static traits using a reductionist approach. More recent work has demonstrated it to be a dynamic and emergent property of complex systems. This narrative review explores human resilience through a self-organizing framework with a specific emphasis on the application of nonlinear modeling approaches. Four classes of approaches are examined: univariate dynamics, bivariate coupling, topological modeling, and network modeling. Univariate dynamics capture the temporal structure and flexibility within a single time series, while bivariate coupling approaches quantify the interaction dynamics and coordination between two time series. Topological modeling identifies bifurcations and attractor dynamics as signals …

Optimization Of Electrode Configurations For Calibration-Free, Remote Sensing Of Heavy Metals In Water Using Double-Potenital Step Anodic Coulometry, Jessica Bone

Online Theses and Dissertations

Many areas around the world are known and predicted to suffer from arsenic-contaminated drinking water resulting in elevated medical issues. Current arsenic detection techniques require that a sample be taken at the site, carried to the lab, and then tested by a skilled technician, which is not practical for remote, hard to reach places. In collaboration with researchers at the University of Louisville and the University of Kentucky, we are designing an electrochemical cell for a calibration-free detection technique that can be performed remotely, eliminating the need for on-site technicians, and helping to prevent chronic arsenic poisoning. A validated and …

Identifying Factors Contributing To Under-Five Mortality In Nigeria, Olateju Alao Bamigbala, Ayodeji Oluwatobi * Ojetunde

Tanzania Journal of Science

The under-5 mortality rate (U5MR) is the probability that a child born in a specified year will die before turning 5 years of age. U5MR is still high in Nigeria. Therefore, this study aimed to identify factors contributing to under-5 mortality in Nigeria. The data used in this study were from the 2018 NDHS, encompassing 2013–2018. The methods of analysis used for this study were frequency, percentage, and Zero Inflated Negative Binomial (ZINB) regression. Data were analyzed using R programming v.4.1.2 and p < 0.05 was considered to be statistically significant. The result showed 35.4% under-5 mortality out of the 33,924 infant mortality sample data that were collected. The findings revealed maternal age, regions (North East and North West), maternal education (no education), wealth index (poorest households), and size of child at birth (very small birth size) as significant factors associated with under-5 mortality in Nigeria. The results also showed that the odds of under-5 mortality increase as the age of the mother increases. Therefore, the Nigerian government should understand that poverty is not just an economic problem but also a significant factor in health; as a result, the battle against poverty needs to receive the necessary attention.  Keywords:    Under-5 mortality; World Health Organization; Zero inflated distribution; Risk factors; Nigeria.

Utilizing New Technologies To Measure Therapy Effectiveness For Mental And Physical Health, Jonathan Ossie

Dissertations

Mental health is quickly becoming a major policy concern, with recent data reporting increasing and disproportionately worse mental health outcomes, including anxiety, depression, increased substance abuse, and elevated suicidal ideation. One specific population that is especially high risk for these issues is the military community because military conflict, deployment stressors, and combat exposure contribute to the risk of mental health problems.

Although several pharmacological approaches have been employed to combat this epidemic, their efficacy is mixed at best, which has led to novel nonpharmacological approaches. One such approach is Operation Surf, a nonprofit that provides nature-based programs advocating the restorative …