Digital Commons Network^™

Pooling And Winsorizing Machine Learning Forecasts To Predict Stock Returns With High-Dimensional Data, Erik Mekelburg, Jack Strauss

Finance: Faculty Scholarship

We evaluate US market return predictability using a novel data set of several hundred ag- gregated firm-level characteristics. We apply LASSO, Elastic Net, Random Forest, Neural Net, Extreme Gradient Boosting, and Light Gradient Boosting Machine methods and find these models experience large prediction errors that lead to forecast failures. However, winsorizing and pooling machine learning model forecasts provides consistent out-of-sample predictability. To assess robustness, we apply machine learning methods to high-dimensional data for Canada, China, Germany and the UK as well as the Goyal-Welch data. All machine learning models we consider, except for the ensemble pooled methods, fail to significantly …

An Artificial Intelligence Report Card For Judicial Review, Zoe E. Niesel

Michigan Journal of Environmental & Administrative Law

The rapid advancement of technology, including artificial intelligence (AI), is creating new challenges for judicial review under the Administrative Procedure Act (APA). In late 2023, federal administrative agencies publicly disclosed over 700 use cases of AI that employ sophisticated techniques like machine learning and natural language processing. While the APA's flexible judicial review framework certainly allows agencies to utilize new technologies, the APA also requires explainability of agency decisions; thus, agencies must be able to articulate the reasoning and methodology behind AI-enabled decisions for the purpose of judicial review. This Article examines APA judicial review as it applies to agency …

The K-Profile Parameterization Augmented By Deep Neural Networks (Kpp_Dnn) In The General Ocean Turbulence Model (Gotm), Jianguo Yuan, Jun Hong Liang, Eric P. Chassignet, Olmo Zavala-Romero, Xiaoliang Wan, Meghan F. Cronin

Faculty Publications

This study utilizes Deep Neural Networks (DNN) to improve the K-Profile Parameterization (KPP) for the vertical mixing effects in the ocean's surface boundary layer turbulence. The deep neural networks were trained using 11-year turbulence-resolving solutions, obtained by running a large eddy simulation model for Ocean Station Papa, to predict the turbulence velocity scale coefficient and unresolved shear coefficient in the KPP. The DNN-augmented KPP schemes (KPP_DNN) have been implemented in the General Ocean Turbulence Model (GOTM). The KPP_DNN is stable for long-term integration and more efficient than existing variants of KPP schemes with wave effects. Three different KPP_DNN schemes, each …

A Machine Learning Approach To Discovering Physical Models Of Galaxy Formation, Festa Bucinca

Dissertations, Theses, and Capstone Projects

Galaxies are the breathtakingly beautiful starry islands of the Universe. The process of galaxy formation involves the transformation from simple initial conditions in the early Universe to the complex galaxy structures we observe today. Spanning an immense spatial range and tremendous time scales - from the vastness of the Universe to the scale of individual stars - the physics of galaxy formation is both complex and crucial for understanding the Universe we live in. However, despite significant advancements, our theoretical understanding of galaxy formation remains incomplete.

In the era of big data available from hydrodynamical simulations and observations, Machine Learning …

A Staged Approach Using Machine Learning And Uncertainty Quantification To Predict The Risk Of Hip Fracture, Anjum Shaik, Kristoffer A. Larsen, Nancy E. Lane, Chen Zhao, Kuan Jui Su, Joyce H. Keyak, Qing Tian, Qiuying Sha, Hui Shen, Hong Wen Deng, Weihua Zhou

Michigan Tech Publications

Hip fractures present a significant healthcare challenge, especially within aging populations, where they are often caused by falls. These fractures lead to substantial morbidity and mortality, emphasizing the need for timely surgical intervention. Despite advancements in medical care, hip fractures impose a significant burden on individuals and healthcare systems. This paper focuses on the prediction of hip fracture risk in older and middle-aged adults, where falls and compromised bone quality are predominant factors. The study cohort included 547 patients, with 94 experiencing hip fracture. To assess the risk of hip fracture, clinical variables and clinical variables combined with hip DXA …

2024 Summer Proceedings Teuscher Lab, Teuscher Group, Christof Teuscher, Chelsea Ogbede, Lauren Sanday, Sofia Vargas, Artem Arefev

altREU Projects

How will computation evolve in the coming years? What problems can be tackled using artificial intelligence, in a world increasingly driven by data? And how can that data be used to better inform our decisions as a society? In this unique collection of research projects, each chapter represents a distinct work undertaken by a single individual or a group of students as part of the altREU program led by Christof Teuscher. The projects, rooted in applications of artificial intelligence and innovative computation techniques, examine impactful solutions to numerous pressing challenges affecting communities around the world.

Detecting Anomalies In Blockchain Transactions Using Machine Learning Classifiers And Explainability Analysis, Mohammad Hasan, Mohammad Shahriar Rahman, Helge Janicke, Iqbal H. Sarker

Research outputs 2022 to 2026

As the use of blockchain for digital payments continues to rise, it becomes susceptible to various malicious attacks. Successfully detecting anomalies within blockchain transactions is essential for bolstering trust in digital payments. However, the task of anomaly detection in blockchain transaction data is challenging due to the infrequent occurrence of illicit transactions. Although several studies have been conducted in the field, a limitation persists: the lack of explanations for the model's predictions. This study seeks to overcome this limitation by integrating explainable artificial intelligence (XAI) techniques and anomaly rules into tree-based ensemble classifiers for detecting anomalous Bitcoin transactions. The shapley …

Multi-Label Classification Using Conformal Prediction, Chhavi Tyagi

Dissertations

In many machine learning applications, such as image tagging, document classi-fication, and medical diagnosis, a data instance can be associated with multiple classes in parallel so that each instance is associated with multiple response variables simultaneously defining multi-label classification. Standard multi-label classification methods that provide point predictions have been developed. They lack in quantifying the uncertainty of predictions. These methods also lack in accounting for label dependencies and are very computationally expensive. This dissertation develops two methods of multi-label classification using conformal prediction that quantify the uncertainty of predictions. Chapter 1 introduces notations and tools that have been used in …

Federated Learning Systems For Mobile Sensing Data, Xiaopeng Jiang

Dissertations

Federated Learning (FL) has emerged as a new distributed Deep Learning (DL) paradigm that enables privacy-aware training and inference on mobile devices with help from the cloud. This dissertation presents a comprehensive exploration of FL with mobile sensing data, covering systems, applications, and optimizations.

First, a mobile-cloud FL system, FLSys, is designed to balance model performance with resource consumption, tolerate communication failures, and achieve scalability. In FLSys, different DL models with different FL aggregation methods can be trained and accessed concurrently by different apps. In addition, FLSys provides advanced privacy-preserving mechanisms and a common API for third-party app developers to …

Facial Expression Recognition And Classification For Autism Spectrum Disorder Based On Sdft Images Using Deep Learning, Sameer Hameed Abdulshahed, Ahmad Taha Abdulsadda

AUIQ Technical Engineering Science

Autism spectrum disorder (ASD) is a prevalent condition in childhood, affecting around 1 in 44 individuals. Approximately 53% of children with ASD exhibit one or more challenging behaviors (CBs), which include aggression, self-injury, property destruction, elopement, and more. This percentage is significantly higher compared to their typically developing peers or those with other developmental disorders. Cognitive-behavioral therapy (CB) has numerous detrimental effects on the individual, all of which are linked to an unfavorable long-term result. When it comes to caregivers of children with ASD, the presence of Challenging Behaviors (CB) is a more dependable indicator of stress than the intensity …

Supervised Classification Modeling On Louisiana Medicaid Data: A Comparative Study, Yead Rahman

Master's Theses

This thesis systematically optimizes and compares state-of-the-art supervised classification models for Louisiana Medicaid data targeting clinical services, COVID-19 infection, and tobacco use. These target variables are critically important as they represent key health outcomes and behaviors among Medicaid enrollees in Louisiana, a population often characterized by poverty and limited access to education. This study applies advanced machine learning techniques to identify the best model for multinomial and binary classification tasks. These include models such as Logistic Regression, XGBoost, AdaBoost, Random Forest, Decision Tree, Artificial Neural Networks, and Naïve Bayes. Extensive tuning of the hyperparameters and optimization of each classifier were …

Challenges And Practices Of Deep Learning Model Reengineering: A Case Study On Computer Vision, Wenxin Jiang, Vishnu Banna, Naveen Vivek, Abhinav Goel, Nicholas Synovic, George K. Thiruvathukal, James C. Davis

Computer Science: Faculty Publications and Other Works

Many engineering organizations are reimplementing and extending deep neural networks from the research community. We describe this process as deep learning model reengineering. Deep learning model reengineering — reusing, replicating, adapting, and enhancing state-of-the-art deep learning approaches — is challenging for reasons including under-documented reference models, changing requirements, and the cost of implementation and testing.

Approximate Computing And In-Memory Computing: The Best Of The Two Worlds!, Mohammed Essa Fawzy Essa

Theses and Dissertations

Machine learning (ML) has become ubiquitous, integrating into numerous real-life applications. However, meeting the computational demands of ML systems is challenging, as existing computing platforms are constrained by memory bandwidth, and technology scaling no longer yields substantial improvements in system performance. This work introduces novel hardware architectures to accelerate ML workloads, addressing both compute and memory challenges. In the compute domain, we explore various approximate computing techniques to assess their efficacy in accelerating ML computations. Subsequently, we propose the Approximate Tensor Processing Unit (APTPU), a hardware accelerator that utilizes approximate processing elements to replace direct quantization of inputs and weights …

Simultaneous Crack & Wave Propagation And Acoustic Emission Signal Modelling Using Peri-Elastodynamic, Md Mushfiqur Rahman Fahim

Theses and Dissertations

This work presents the use of Peri-Elastodynamic, a guided wave simulation method based on meshfree non-local Peridynamics theory. To model simultaneous crack and wave propagation simulation and its application on Acoustic Emission (AE) signal modelling, a new formulation is presented. The field of nondestructive evaluation (NDE) and structural health monitoring (SHM) is slowly embracing the advancement in Machine Learning (ML) / Artificial Intelligence (AI) for better and cost-effective assessment of structures and damage prediction. AI/ML can revolutionize the NDE/SHM field by automating the data collection and analyzing processes. However, the big challenge is that the model needs a sheer amount …

Feature Engineering For Grain Boundaries And Other Variable-Sized Atom Clusters, C. Braxton Owens

Theses and Dissertations

Obtaining microscopic structure-property relationships for grain boundaries are challenging because of the complex atomic structures that underlie their behavior. This has led to recent efforts to obtain these relationships with machine learning, but representing a grain boundary structure in a manner suitable for machine learning is not a trivial task. There are three key steps common to property prediction in grain boundaries and other variable-sized atom clustered structures. These are: (1) describe the atomic structure as a feature matrix, (2) transform the variable-sized feature matrices of different structures to a fixed length common to all structures, and (3) apply machine …

A Platform For Integrating Internet Of Things, Machine Learning, And Big Data Practicum In Electrical Engineering Curricula, Nandana Jayachandran, Atef Abdrabou, Naod Yamane, Anwer Al-Dulaimi

All Works

The integration of the Internet of Things (IoT), big data, and machine learning (ML) has pioneered a transformation across several fields. Equipping electrical engineering students to remain abreast of the dynamic technological landscape is vital. This underscores the necessity for an educational tool that can be integrated into electrical engineering curricula to offer a practical way of learning the concepts and the integration of IoT, big data, and ML. Thus, this paper offers the IoT-Edu-ML-Stream open-source platform, a graphical user interface (GUI)-based emulation software tool to help electrical engineering students design and emulate IoT-based use cases with big data analytics. …

Groundwater Modeling Of The Ogallala Aquifer: Use Of Machine Learning For Model Parameterization And Sustainability Assessment, Tewodros Aboret Tilahun

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

Addressing groundwater depletion problems in heterogeneous aquifer systems is a challenge. The heterogeneous Ogallala Aquifer, a critical source of groundwater in the central United States, has undergone decades of decline in water levels due to pumping. This project aims to build a robust groundwater model to evaluate optimal scenarios for sustainable use of the groundwater resource within a section of the Ogallala aquifer located in the Middle Republican Natural Resources District (MRNRD). This study follows a comprehensive approach involving parameterization, construction, and optimization. The model is parametrized using hydraulic conductivity and recharge values obtained from a random forest-based machine learning …

Ai-Based Methods For Detecting And Classifying Age-Related Macular Degeneration: A Comprehensive Review, Niveen Nasr El-Den, Mohamed Elsharkawy, Ibrahim Saleh, Mohammed Ghazal, Ashraf Khalil, Mohammad Z. Haq, Ashraf Sewelam, Hani Mahdi, Ayman El-Baz

All Works

This paper explores the advancements and achievements of artificial intelligence (AI) in computer vision (CV), particularly in the context of diagnosing and grading age-related macular degeneration (AMD), one of the most common leading causes of blindness and low vision that impact millions of patients globally. Integrating AI in biomedical engineering and healthcare has significantly enhanced the understanding and development of the CV application to mimic human problem-solving abilities. By leveraging AI-based models, ophthalmologists can improve the accuracy and speed of disease diagnosis, enabling early treatment and mitigating the severity of the conditions. This paper presents a comprehensive analysis of many …

Mapping Urban Tree Canopy Using Publicly Available Satellite Data, Rosemary Mcguinness

Theses and Dissertations

This project addresses the need for accessible, cost-effective tools for quantifying spatial and temporal changes in tree canopy cover in urban areas. Urban tree canopy provides a wide range of ecosystem services, including lowering air temperatures, reducing pollution, and mitigating stormwater runoff. Cities around the world have placed the expansion of their urban forests at the center of their sustainability goals. Consistent and timely data on urban tree canopy is essential for urban greening initiatives to succeed. Existing methods of accessing information about urban tree canopy are highly technical, costly, and labor-intensive, while the freely available source of tree canopy …

Quantinar: A Blockchain Peer-To-Peer Ecosystem For Modern Data Analytics, Raul Bag, Bruno Spilak, Julian Winkel, Wolfgang Karl Hardle

Sim Kee Boon Institute for Financial Economics

The power of data and correct statistical analysis has never been more prevalent. Academics and practitioners require nowadays an accurate application of quantitative methods. Yet many branches are subject to a crisis of integrity, which is shown in an improper use of statistical models, p-hacking, HARKing, or failure to replicate results. We propose the use of a Peer-to-Peer (P2P) ecosystem based on a blockchain network, Quantinar, to support quantitative analytics knowledge paired with code in the form of Quantlets or software snippets. The integration of blockchain technology allows Quantinar to ensure fully transparent and reproducible scientific research.

Real-Time Barge Detection Using Traffic Cameras And Deep Learning On Inland Waterways, Geoffery Eyram Agorku

Graduate Theses and Dissertations

Inland waterways are critical for freight movement, but limited means exist for monitoring their performance and usage by freight-carrying vessels, e.g., barges. While methods to track vessels, e.g., tug and tow boats, are publicly available through Automatic Identification Systems (AIS), ways to track freight tonnages and commodity flows carried on barges along these critical marine highways are non-existent, especially in real-time settings. This paper develops a method to detect barge traffic on inland waterways using existing traffic cameras with opportune viewing angles. Deep learning models, specifically, You Only Look Once (YOLO), Single Shot MultiBox Detector (SSD), and EfficientDet are employed. …

Development Of A Turning Movement Estimator, Somayeh Nazari Enjedani

Boise State University Theses and Dissertations

Turning Movement (TM) counts at intersections are crucial for several reasons. There has been extensive research on this topic throughout the history of traffic research, which reflects its importance in transportation engineering and urban planning. It can be said that one of the most significant applications of TMs is signal timing at intersections. Signal timing design requires data on the turning decisions of vehicles that travel through intersections to allow enough time for each movement at the intersection. Most of organizations around the USA are still applying traditional methods for collecting TM data, such as manual counts. These methods are …

On The Right Track? Energy Use, Carbon Emissions, And Intensities Of World Rail Transportation, 1840–2020, Bernardo Tostes, Sofia T. Henriques, Paul E. Brockway, Matthew Kuperus Heun, Tiago Domingos, Tânia Sousa

University Faculty Publications and Creative Works

The history of rail transport can offer valuable insights for future energy transitions due to its importance in promoting clean mobility. There is a complex interplay between the evolution of the railway network, fuel consumption, efficiency, energy service, and CO2 emissions that requires further exploration. We developed a dataset that covers energy use in all stages of rail transportation, as well as the length of track, energy service, and CO2 emissions at the world scale. To deal with missing data we utilized machine learning techniques for the first time in a historical energy reconstruction study. Our analysis reveals that …

Predicting Personality Or Prejudice? Facial Inference In The Age Of Artificial Intelligence, Shilpa Madan, Gayoung Park

Research Collection Lee Kong Chian School Of Business

Facial inference, a cornerstone of person perception, has traditionally been studied through human judgments about personality traits and abilities based on people's faces. Recent advances in artificial intelligence (AI) have introduced new dimensions to this field, employing machine learning algorithms to reveal people's character, capabilities, and social outcomes based just on their faces. This review examines recent research on human and AI-based facial inference across psychology, business, computer science, legal, and policy studies to highlight the need for scientific consensus on whether or not people's faces can reveal their inner traits, and urges researchers to address the critical concerns …

Leveraging Machine Learning And Stochastic Programming To Address Vaccine Hesitancy In Public Health Resource Allocation, Hieu Trung Bui

Graduate Theses and Dissertations

Infectious disease outbreaks highlight the urgent need for effective strategies to distribute vaccines and allocate critical healthcare resources to contain the disease and reduce its negative impacts on the population. Managing these allocations is a significant challenge, especially in marginalized communities facing uncertainty in healthcare demand and logistical constraints. This dissertation addresses these challenges by investigating factors that influence dynamic changes in vaccine hesitancy (VH) and its implications for disease spread and healthcare resource demand. It develops optimization models for vaccine distribution and resource allocation under uncertainty, validated with data from the COVID-19 pandemic in the U.S. The first study …

Offensive Content Detection In Online Social Platforms, Ebuka Okpala

All Dissertations

Online social platforms enable users to connect with large, diverse audiences and the ability for a message or content to flow from one user to another user, user to followers, followers to user, and followers to followers. Of course, the advantages of this are apparent, and the dangers are also clearly obvious. The user-generated content could be abusive, offensive, or hateful to other users, possibly leading to adverse health effects or offline harm. As more of society's public discourse and interaction move online and these platforms grow and increase their reach, it is inherently important to protect the safety of …

Integration Of Matlab And Machine Learning To Accelerate Evaluation Of Biological Activity In Agricultural Soils And Promote Soil Health Improvement Goals, Andrew Stiven Ortiz Balsero

Department of Agricultural and Biological Systems Engineering: Dissertations, Theses, and Student Research

Traditionally, assessments of soil biological activity have been confined to laboratory settings, creating a disconnect with practical in-field methods. To bridge this gap, cotton fabric degradation has been used to illustrate soil microbial activity under different management practices. While effective, these demonstrations are subjective and labor-intensive.

Researchers have explored using image processing software like ImageJ and Adobe Photoshop to streamline this process. Although these tools accurately quantified fabric degradation under varying soil conditions, the methods remained labor-intensive and complex. Consequently, these methods were still not ideal for on-farm use by agricultural practitioners.

To further address labor and complexity limitations, the …

A Comprehensive Dataset For Arabic Word Sense Disambiguation, Sanaa Kaddoura, Reem Nassar

All Works

This data paper introduces a comprehensive dataset tailored for word sense disambiguation tasks, explicitly focusing on a hundred polysemous words frequently employed in Modern Standard Arabic. The dataset encompasses a diverse set of senses for each word, ranging from 3 to 8, resulting in 367 unique senses. Each word sense is accompanied by contextual sentences comprising ten sentence examples that feature the polysemous word in various contexts. The data collection resulted in a dataset of 3670 samples. Significantly, the dataset is in Arabic, which is known for its rich morphology, complex syntax, and extensive polysemy. The data was meticulously collected …

Benchmarking Machine Learning Algorithms For The Prediction Of Gas Adsorption In Metal-Organic Framework Materials, Juan G. Benitez

Theses and Dissertations

Metal-organic frameworks (MOFs) are nanoporous materials with a structure and chemistry that can be tailored with precision to support a variety of applications, such as gas storage, drug delivery, catalysis, and sensing. Central to the realization of these applications is the need to model adsorption in MOFs. However, if the goal is to screen a large number of the hundreds of thousands of MOFs discovered, conventional high-throughput molecular simulations are prohibitively demanding in terms of computational resources. Therefore, efficient approaches are required to efficiently identify suitable MOFs for specific applications. In our work, machine learning (ML) models to predict adsorption …

Deep Representation Learning For Time Series Forecasting, Gerald Woo

Dissertations and Theses Collection (Open Access)

Time series forecasting has critical applications across business and scien- tific domains, such as demand forecasting, capacity planning and management, and anomaly detection. Being able to predict the future yields immense value, allowing us to make downstream decisions with more confidence. Deep learning for time series forecasting is a burgeoning area of research, moving away from simple linear models found in classical time series analysis literature, towards more expressive, data hungry neural network architectures.

In this thesis, we develop methods leveraging deep representation learning for time series forecasting, from exploring neural network architecture designs which encode inductive biases specific to …