Data Science Commons^™

Emulate Randomized Clinical Trials Using Heterogeneous Treatment Effect Estimation For Personalized Treatments: Methodology Review And Benchmark, Yaobin Ling, Pulakesh Upadhyaya, Luyao Chen, Xiaoqian Jiang, Yejin Kim

Faculty, Staff and Student Publications

Big data and (deep) machine learning have been ambitious tools in digital medicine, but these tools focus mainly on association. Intervention in medicine is about the causal effects. The average treatment effect has long been studied as a measure of causal effect, assuming that all populations have the same effect size. However, no "one-size-fits-all" treatment seems to work in some complex diseases. Treatment effects may vary by patient. Estimating heterogeneous treatment effects (HTE) may have a high impact on developing personalized treatment. Lots of advanced machine learning models for estimating HTE have emerged in recent years, but there has been …

Survey Of West Nile And Banzi Viruses In Mosquitoes, South Africa, 2011-2018, Caitlin Macintyre, Milehna Mara Guarido, Megan Amy Riddin, Todd Johnson, Leo Braack, Maarten Schrama, Erin Gorsich, Antonio Paulo Gouveia Almeida, Marietjie Venter

Faculty, Staff and Student Publications

We collected >40,000 mosquitoes from 5 provinces in South Africa during 2011-2018 and screened for zoonotic flaviviruses. We detected West Nile virus in mosquitoes from conservation and periurban sites and potential new mosquito vectors; Banzi virus was rare. Our results suggest flavivirus transmission risks are increasing in South Africa.

Predicting Housing Prices Using Ai, Eric Sconyers

Williams Honors College, Honors Research Projects

I have created an AI model that can predict housing prices with 70 percent accuracy in Ames Iowa. I was able to use data from a website called Kaggle.com which is a website that provides datasets to the public so they can create AI models with the data. I found the dataset pertaining to housing prices in Ames Iowa. With this data, I was able to create an AI model that can predict the housing price of these homes. The technology I used in this project was Python as the programming language, and I used the scikit-learn library which has …

Modeling The Bidirectional Relationship Between Shared-Patient Physician Networks And Patient Longitudinal Treatment Patterns: Application To Physician Risky-Prescribing, Xin Ran

Dartmouth College Ph.D Dissertations

Risky-prescribing is a pressing public health concern in the United States. Opioids, benzodiazepines, and non-benzodiazepine sedative-hypnotics (sedative-hypnotics) are three commonly-prescribed but potentially risky drug groups, prescribed alone or in combination. Physician shared-patient networks provide a unique perspective in studying physician network characteristics and structures, as well as their association with the delivery of health care. Understanding how physician shared-patient networks are related to their prescribing may inform network-based interventions targeting risky-prescribing, which is yet to be fully studied.

We investigated patient receipt of risky prescriptions and physician risky-prescribing intensity through the scope of shared-patient networks. We used retrospective Medicare insurance …

Machine Learning Approach To Predict Tdcs-Induced Electric Current In The Human Brain, Chikako Olsen

Dissertations and Theses

Background: Transcranial direct current stimulation (tDCS) is a promising non-invasive method for treating neurological and psychiatric disorders and enhancing cognitive function. However, the underlying mechanisms of tDCS are not fully understood, and there is no ground truth for determining, non-invasively, where in the brain tDCS electrical currents flow. At the same time, effective neuronal engagement from tDCS requires accurate localization of the induced currents to specific brain target regions. Machine Learning (ML) has the potential to significantly improve the accuracy and precision of tDCS current prediction. This study aims to develop a novel approach using ML to predict the location …

Analysis Of Chemical Elements In Basalts Using Mislabeled Data, A Machine Learning Approach, Jenifer Vivar

Dissertations and Theses

Scientists use basalt chemistry to discriminate among different tectonic settings. There are well-known chemical elements used to classify tectonic settings. An exploration of new features is done using Logistic Regression and Random Forest to discover any new elements of interest. The models were used with other tools, such as recursive feature elimination and permutations, to increase reliability. Among the scarcely explored chemical elements are Terbium (Tb), Holmium (Ho), Samarium (Sm), and Erbium (Er). The data used for the exploration contained many outliers. Therefore, an ensemble model was created to explore the location and composition of such outliers. The ensemble was …

Exploring Information Leakage In Historical Stock Market Data, Edison Hua

Dissertations and Theses

Information leakage is a major concern for traders who want to execute large orders without affecting the market price. In this paper, we explore the sources and effects of information leakage in historical stock market data using various methods and metrics. We first define information leakage as a pattern caused by a trader that would otherwise not occur without the trader’s activity. Using historical data, the direct impact of a potential large trade cannot be measured, but we consider a minimal impact large trade to be one that minimizes changes to the established trading data. We then analyze how information …

Shallow Water Coral Distribution And Its Response To Climate Change, Amaury De Jesus

Dissertations and Theses

Shallow water corals are one of the main reef-building organisms that secrete carbonates as their skeletons, and therefore, are one of the major sinks of CO2 in the ocean. These reef builders are also very crucial to marine environments and human society. As the global energy demand continues rising, fossil fuel burning increases at a faster pace despite the increase in energy supply using clean and renewable energy. The increase of CO2 in the atmosphere has been shown to exacerbate global warming and may cause ocean acidification, threatening the habitat of shallow-water corals. Many recent observations show alarming signs of …

A Study On Global Reef Deterioration: Exploring Coral Bleaching, Emily Fernandez

CMC Senior Theses

This thesis is a study on coral bleaching and coral mortality, studying the relationship between variables such as depth, exposure, distance to shore, and temperature for percent bleaching. All of the analyses were made using two different data sets, that contain information about bleaching events in specific regions, and dates, and provide information factors such as depth, temperature, and exposure. Models were created for different relationships of variables for eco-regions, recent data, and countries. I attempted to find relationships between variables such as depth, temperature, exposure, and distance to shore, and how they affect coral bleaching. Unfortunately, I did not …

Defining The "Quadruple-A" Player: What Makes A Baseball Player Succeed In The Minor Leagues And Fail In The Major Leagues?, Sam Bogen

CMC Senior Theses

The "Quadruple-A" player is defined as one who is too good to play in Triple-A (the league one step down from Major League Baseball) but not good enough to play consistently in Major League Baseball. This thesis paper attempts to explain the phenomenon of the "Quadruple-A" player. Using Triple-A data from 2013-2022 and Major League data from the "Statcast Era" (2015-2022), I build logistic and linear regression models to predict Major League success based on Triple-A performance data as well as Major League Statcast data, discovering that statistics related to how a player hits the ball such as the speed …

Application Of Sentiment Analysis And Machine Learning Techniques To Predict Daily Cryptocurrency Price Returns, Edward Wu

CMC Senior Theses

This paper examines the effects of social media sentiment relating to Bitcoin on the daily price returns of Bitcoin and other popular cryptocurrencies by utilizing sentiment analysis and machine learning techniques to predict daily price returns. Many investors think that social media sentiment affects cryptocurrency prices. However, the results of this paper find that social media sentiment relating to Bitcoin does not add significant predictive value to forecasting daily price returns for each of the six cryptocurrencies used for analysis and that machine learning models that do not assume linearity between the current day price return and previous daily price …

Comparative Analysis Of Fullstack Development Technologies: Frontend, Backend And Database, Qozeem Odeniran

College of Graduate Studies: Theses & Dissertations

Accessing websites with various devices has brought changes in the field of application development. The choice of cross-platform, reusable frameworks is very crucial in this era. This thesis embarks in the evaluation of front-end, back-end, and database technologies to address the status quo. Study-a explores front-end development, focusing on angular.js and react.js. Using these frameworks, comparative web applications were created and evaluated locally. Important insights were obtained through benchmark tests, lighthouse metrics, and architectural evaluations. React.js proves to be a performance leader in spite of the possible influence of a virtual machine, opening the door for additional research. Study b …

Generalized Sparse Bayesian Learning And Application To Image Reconstruction, Jan Glaubitz, Anne Gelb, Guohui Song

Mathematics & Statistics Faculty Publications

Image reconstruction based on indirect, noisy, or incomplete data remains an important yet challenging task. While methods such as compressive sensing have demonstrated high-resolution image recovery in various settings, there remain issues of robustness due to parameter tuning. Moreover, since the recovery is limited to a point estimate, it is impossible to quantify the uncertainty, which is often desirable. Due to these inherent limitations, a sparse Bayesian learning approach is sometimes adopted to recover a posterior distribution of the unknown. Sparse Bayesian learning assumes that some linear transformation of the unknown is sparse. However, most of the methods developed are …

Using Long Short-Term Memory (Lstm) Networks With The Toy Model Concept For Compressible Pulsatile Flow Metering, Indranil Brahma

Faculty Journal Articles

The metering of periodically oscillating pulsating flow has traditionally relied on eliminating pulsations, which is not possible for many systems such as internal combustion engines. Recent advances in the Deep Learning Suite of tools allow the extraction of useful information from complex signals acquired by inexpensive sensors. In this work, Long Short-Term Memory (LSTM) networks have been proposed to meter highly compressible pulsatile flow by learning the relationship between the average flow rate and the temporal patterns of standard orifice measurements. The model was built and evaluated with separate training and testing datasets that had different pulsation frequencies and waveforms. …

An Explainable Deep Learning Prediction Model For Severity Of Alzheimer's Disease From Brain Images, Godwin O. Ekuma

Graduate Theses/Dissertations

Deep Convolutional Neural Networks (CNNs) have become the go-to method for medical imaging classification on various imaging modalities for binary and multiclass problems. Deep CNNs extract spatial features from image data hierarchically, with deeper layers learning more relevant features for the classification application. The effectiveness of deep learning models are hampered by limited data sets, skewed class distributions, and the undesirable "black box" of neural networks, which decreases their understandability and usability in precision medicine applications. This thesis addresses the challenge of building an explainable deep learning model for a clinical application: predicting the severity of Alzheimer's disease (AD). AD …

Feature Extraction Of Footwear Impression Images For Quality Assessment, Alexandra Hill

Graduate Theses, Dissertations, and Problem Reports (ETD)

Forensic footwear impression analysis is a valuable tool in criminal investigations. Extracting useful features from images of footwear impressions is a critical step in this process. However, the quality of these images can vary widely, making feature extraction challenging. In order to give a quality assessment rating to a footwear impression image, the image should first be analyzed to extract features from the impression. In this paper, we present a method to extract features from a 2D grayscale footwear impression image. A Hierarchical Grid Model implementation has been adapted from use on a 3D dataset to assist in finding features, …

An Investigation Of Methods For Improving Spatial Invariance Of Convolutional Neural Networks For Image Classification, David Noel

CCAC Theses and Dissertations

Convolutional Neural Networks (CNNs) have achieved impressive results on complex visual tasks such as image recognition. They are commonly assumed to be spatially invariant to small transformations of their input images. Spatial invariance is a fundamental property that characterizes how a model reacts to input transformations, i.e., its generalizability - and deep networks that can robustly classify objects placed in different orientations or lighting conditions have the property of invariance. However, several authors have recently shown that this is not the case, and that slight rotations, translations, or rescaling of their input images significantly reduce the network’s predictive accuracy. Furthermore, …

Face Anti-Spoofing And Deep Learning Based Unsupervised Image Recognition Systems, Enoch Solomon

Theses and Dissertations

One of the main problems of a supervised deep learning approach is that it requires large amounts of labeled training data, which are not always easily available. This PhD dissertation addresses the above-mentioned problem by using a novel unsupervised deep learning face verification system called UFace, that does not require labeled training data as it automatically, in an unsupervised way, generates training data from even a relatively small size of data. The method starts by selecting, in unsupervised way, k-most similar and k-most dissimilar images for a given face image. Moreover, this PhD dissertation proposes a new loss function to …

Dental Claires: Contrastive Language Image Retrieval Search For Dental Research, Tanjida Kabir, Luyao Chen, Muhammad F Walji, Luca Giancardo, Xiaoqian Jiang, Shayan Shams

Faculty, Staff and Student Publications

Learning about diagnostic features and related clinical information from dental radiographs is important for dental research. However, the lack of expert-annotated data and convenient search tools poses challenges. Our primary objective is to design a search tool that uses a user's query for oral-related research. The proposed framework,

Network Intrusion Detection Using Deep Reinforcement Learning, Hamed T. Sanusi

College of Graduate Studies: Theses & Dissertations

This thesis delves into cybersecurity by applying Deep Reinforcement(DRL) Learning in network intrusion detection. One advantage of DRL is the ability to adapt to changing network conditions and evolving attack methods, making it a promising solution for addressing the challenges involved in intrusion detection. The thesis will also discuss the obstacles and benefits of using Classification methods for network intrusion detection and the need for high-quality training data. To train and test our proposed method, the NSL-KDD dataset was used and then adjusted by converting it from a multi-classification to a binary classification, achieved by joining all attacks into one. …