Digital Commons Network^™

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 …

Implementation Of Machine Learning Using Deep Neural Networks To Estimate The Failure Risk Caused By Leakage In Pressure Relief Devices, Adi Yudho Wijayanto, Yossi Andreano, M. Ali Yafi Rizky, Dedi Priadi

Journal of Materials Exploration and Findings

The primary objective of deploying Pressure Relief Device (PRD) equipment is to ensure the safety of pressure vessels within a pressurized system. Over time, PRD equipment may degrade and fail to perform its intended function, which must be identified as a failure mode. To mitigate potential risks associated with this, it is recommended that an approach such as risk-based inspection (RBI) be implemented. Despite the widespread adoption of RBI, the method relies on qualitative techniques, leading to significant variations in equipment risk assessments. This study proposes a novel risk analysis method that uses deep learning-based machine learning to develop a …

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.

Unveiling Key Features: A Comparative Study Of Machine Learning Models For Alzheimer's Detection, Cailean Bushnell

All Graduate Reports and Creative Projects, Fall 2023 to Present

This thesis rigorously evaluates the application of an array of natural language processing (NLP) techniques and machine learning models to identify linguistic signatures indicative of dementia, as sourced from the DementiaBank Pitt corpus. Utilizing a binary classification paradigm, this study meticulously integrates sophisticated embedding methods—including Doc2Vec, Word2Vec, GloVe, and BERT—with traditional machine learning algorithms such as Random Forest, Multinomial Naïve Bayes, ADA boost, KNN classifier, and Logistic Regression, alongside deep learning architectures like LSTM, Bi-LSTM, and CNN-LSTM. The efficacy of these methodologies is evaluated based on their capacity to differentiate between transcribed speech impacted by dementia and that from control …

Assessing The Efficacy: Statistical Models Vs. Machine Learning (Ml) Approaches For Prediction Modeling In The Construction Industry, Stuti Garg

All Theses

The construction industry has witnessed a significant surge in the daily volume of objective data (i.e., precise data sources representing actual project progress) accumulated across a project's lifecycle. This abundance of data presents an opportunity to extract valuable organizational insights and potential remedies for project management issues. The construction technology landscape is gradually evolving towards integrated software platforms to meet customer needs more effectively. However, the construction sector lacks comprehensive predictive analytics solutions for projects or industry-wide applications - a significant portion of descriptive analytics tools rely on trade association surveys or dashboards constructed from collected company data, suffering from …

Storm Surge Modeling In The Ai Era: Using Lstm-Based Machine Learning For Enhancing Forecasting Accuracy, Stefanos Giaremis, Noujoud Nader, Clint Dawson, Carola Kaiser, Efstratios Nikidis, Hartmut Kaiser

Faculty Publications

Physics simulation results of natural processes usually do not fully capture the real world. This is caused for instance by limits in what physical processes are simulated and to what accuracy. In this work we propose and analyze the use of an LSTM-based deep learning network machine learning (ML) architecture for capturing and predicting the behavior of the systemic error for storm tide forecast models with respect to real-world water elevation observations from gauge stations during hurricane events. The overall goal of this work is to predict the systemic error of the physics model and use it to improve the …

Ensemble Machine Learning At The Edge Using The Codec Classifier Structure And Weak Learners Guided By Mutual Information, Aj Beckwith

All Graduate Theses and Dissertations, Fall 2023 to Present

The Codec Classifier is a low-computation, low-memory tree ensemble method that dramatically improves feasibility of image classification on resource-constrained edge devices. It achieves advantages over other tree ensemble methods due the separation of encoder and decoder tasks in the classifier. The encoder partitions feature space, and the decoder labels the regions in the partition. This functional separation of tasks enables the encoder design (partitioning) to be guided by maximizing the mutual information (MI) between class labels and the features (i.e. the encoded representation of the data) without regard to the error performance of the classifier. Experiments show maximizing MI leads …

A Multimodal Foundation Agent For Financial Trading : Tool-Augmented, Diversified, And Generalist, Wentao Zhang, Lingxuan Zhao, Haochong Xia, Shuo Sun, Jiaze Sun, Molei Qin, Xinyi Li, Yuqing Zhao, Yilei Zhao, Xinyu Cai, Longtao Zheng, Xinrun Wang, Bo An

Research Collection School Of Computing and Information Systems

Financial trading is a crucial component of the markets, informed by a multimodal information landscape encompassing news, prices, and Kline charts, and encompasses diverse tasks such as quantitative trading and high-frequency trading with various assets. While advanced AI techniques like deep learning and reinforcement learning are extensively utilized in finance, their application in financial trading tasks often faces challenges due to inadequate handling of multimodal data and limited generalizability across various tasks. To address these challenges, we present FinAgent, a multimodal foundational agent with tool augmentation for financial trading. FinAgent's market intelligence module processes a diverse range of data-numerical, textual, …

Kilonova Modeling And Parameter Inference, Marko Ristic

Theses

This dissertation details the generation of a kilonova simulation training library and the training of subsequent machine learning emulators used for multidimensional interpolation. We begin with a Gaussian process interpolation methodology and apply that emulator for Bayesian inference with the AT 2017gfo light-curve dataset. We then expand on our emulator interpolation methodology, replacing the scalar Gaussian process emulator with a vector neural network emulator for light-curve generation. Our neural network emulator results are localized to a much more narrow region of the parameter space, prompting a detailed supportive investigation of the systematic uncertainty associated with our inference approach. We then …

Influential Factors And Predicting Dose Delivery Accuracy For Imaging And Radiation Oncology Core’S Phantom Program Using Machine Learning, Hunter Mehrens

Dissertations and Theses (Open Access)

IROC’s mission is to help ensure consistent and comparable, high-quality radiotherapy across clinics that participate in national clinical trials. To obtain this mission, IROC’s phantom program provides a third-party end-to-end check of the clinical workflow of a patient receiving radiotherapy. The goal of the phantom audit is to compare the dose delivered to the dose planned by the treatment system ensuring dose delivery accuracy. While IROC’s phantoms are better equipped to catch dose delivery errors compared to a clinic’s QA process, the end-to-end process and reporting of results is time-consuming creating a bottleneck for clinical trial participation. Furthermore, IROC’s passing …

Exploratory Analysis In Rio Grande Valley Real Estate Development, Mathew C. Sosa

Theses and Dissertations

The aim of this thesis is to apply exploratory data analysis and machine learning (ML) to answer critical questions in real estate development within the Rio Grande Valley (RGV). The real estate development sector is highly dynamic and relies on multiple integrated systems and planning to bring new homes to the market. Customer Relationship Management (CRM) software and real estate listing services, such as Redfin, are utilized to manage the customer lifecycle and analyze the local market, respectively. Two of the most crucial aspects of the customer lifecycle are the first home tour and deal closing. This paper explores the …

A Comparative Study Of The Performance Of Machine Learning Methods And Deep Neural Networks In Intrusion Detection, Milan Artis

Masters Theses and Doctoral Dissertations

Intrusion detection systems (IDS) can be improved by using machine learning to teach the IDS what traffic is normal and therefore should be allowed into a network, or what traffic is abnormal and should be denied access to a network. The performance of intrusion detection systems can be improved through the use of machine learning methods that can accurately identify and classify normal attack versus attack traffic. There are numerous machine learning methods that can be employed for the purpose of improving intrusion detection. We use the NSL-KDD dataset to evaluate various machine learning models in order to determine the …

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 …

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 …

Aligned With The Blueprint For An Ai Bill Of Rights? An Ai Transparency Evaluation Of Company Privacy Notices And Explanations, Jonathan A. Obar, Giuseppina D'Agostino, Motunrayo Akinyemi

Conference Papers

In its Blueprint for an AI Bill of Rights, the White House lists “notice and explanation” as one of five principles fundamental to protecting the American public as artificial intelligence (AI) is deployed. The Blueprint states “[y]ou should know that an automated system is being used and understand how and why it contributes to outcomes that impact you.” In its description of the notice/explanation principle, The White House emphasizes the importance of plain language explanations about AI use. Furthermore, a company should describe how it plans to use AI systems, how the systems work, and explain any risks to consumers. …

Predicting Hand Grasping Orientation For Prosthetic Hand Control Using Multimodal Sensor Data (Eeg, Emg, And Imu) With Machine Learning Approach, Nafiseh Ghaffar Nia

Masters Theses and Doctoral Dissertations

Enhancing the control of prosthetic hands is a crucial challenge that directly impacts the daily functionality of individuals with limb loss. Our research delves into advanced machine learning (ML) methodologies to accurately predict hand-grasping orientations, thereby improving the precision of prosthetic control. We present a comprehensive framework that amalgamates inputs from multiple sensors. This includes electroencephalography (EEG) to discern user intentions, electromyography (EMG) to evaluate muscle activity, and inertial measurement units (IMU) to track features of hand movement. By harmoniously integrating these varied data streams, our ML model strives to provide predictions of hand orientation that are more accurate and …

Increasing The Robustness Of Machine Learning By Adversarial Attacks, Gourab Mukhopadhyay

Theses and Dissertations

By perturbation or physical attacks any machine can be fooled into predicting something else other than the intended output. There are training data based on which the model is trained to predict unknown things. The objective was to create noises and shades of different levels on the images and do experiments for measuring accuracy and making the model classify the traffic signs. When it comes to adding shades to the pictures, pixels were modified for three different layers of the pictures. The experiment also shows that with the shadows getting deeper, the accuracies drop significantly. Here, some changes in pixels …

An Enhanced Deep Autoencoder For Flight Delay Prediction, Desmond B. Bisandu, Dan Andrei Soviani-Sitoiu, Irene Moulitsas

Journal of Aviation/Aerospace Education & Research

Accurate and timely flight delay prediction cannot be overemphasized because of the ever-increasing demand for air travel and its importance in deploying intelligent transportation systems. Nonetheless, there has not been a universal solution to the problem, as more intelligent flight decision systems are required for the aviation industry's future growth. Existing flight delay classification and prediction approaches are mainly shallow traffic models and do not satisfy many applications in the real world. Our motivation to rethink the deep architecture model for predicting flight delays emanates from the problem. In this research, we proposed a technique that modified stacked autoencoder architecture …

Mixed Potential Sensor For Natural Gas Leak Detection Design, Manufacturing, And Simulation, Sleight Halley

Chemical and Biological Engineering ETDs

There is a need for a low-cost robust sensor accurately detecting leaks from oil and gas infrastructure. This work presents the development of an electrochemical sensor based on an yttria stabilized zirconia (YSZ) electrolyte with La_0.87Sr_0.13CrO₃, Indium Tin Oxide (In₂O₃ 90 wt%, SnO₂ 10 wt%), Au, Pt electrodes. Selectivity to target gasses of the three sensing electrodes in conjunction with machine learning allows for the accurate discrimination between possible methane sources as well as the quantification of methane concentration. Sensor sensitivity is improved through a low-ionic conductivity substrate of magnesia …

A New Approach: Ordinal Predictive Maintenance With Ensemble Binary Decomposition (Opmeb), Ozlem Ece Yurek, Derya Birant

Turkish Journal of Electrical Engineering and Computer Sciences

Predictive maintenance (PdM), a fundamental element of modern industrial systems, employs machine learning to monitor equipment conditions, estimate failure probabilities, and optimize maintenance schedules. Its core objective is to enhance equipment reliability, extend lifespan, and minimize costs through data-driven insights by enabling efficient maintenance scheduling, reducing downtime, and optimizing resource allocation. In this paper, we propose a novel ordinal predictive maintenance with ensemble binary decomposition (OPMEB) method for the PdM domain, considering the hierarchical nature of class labels reflecting the machine's health status, including categories like healthy, low risk, moderate risk, and high risk. The proposed OPMEB method was validated …

Predicting Choroidal Nevus Transformation To Melanoma Using Machine Learning, Prashant D. Tailor, Piotr K. Kopinski, Haley S. D'Souza, David A. Leske, Timothy W. Olsen, Carol L. Shields, Jerry A. Shields, Lauren A. Dalvin

Wills Eye Hospital Papers

PURPOSE: To develop and validate machine learning (ML) models to predict choroidal nevus transformation to melanoma based on multimodal imaging at initial presentation.

DESIGN: Retrospective multicenter study.

PARTICIPANTS: Patients diagnosed with choroidal nevus on the Ocular Oncology Service at Wills Eye Hospital (2007-2017) or Mayo Clinic Rochester (2015-2023).

METHODS: Multimodal imaging was obtained, including fundus photography, fundus autofluorescence, spectral domain OCT, and B-scan ultrasonography. Machine learning models were created (XGBoost, LGBM, Random Forest, Extra Tree) and optimized for area under receiver operating characteristic curve (AUROC). The Wills Eye Hospital cohort was used for training and testing (80% training-20% testing) with …

Machine Learning Boiling Prediction: From Autonomous Vision Of Flow Visualization Data To Performance Parameter Theoretical Modeling, Cho Ning Huang, Issam Mudawar, Chirag R. Kharangate

Faculty Scholarship

Flow boiling is a highly efficient configuration for meeting the high heat dissipation demands of thermal management systems. However, the complex physics of two-phase flow has hindered its broader application, especially in terms of quantifying visual information. Recent advancements in machine learning vision tools have revolutionized the analysis of phase change phenomena by enabling the digitalization of physically meaningful features such as void fraction, vapor-liquid interfacial behaviors, and liquid-solid wall wetting front areas en masse. In this study, we systematically investigate two-phase models that compute void fractions, heat transfer coefficients, and critical heat flux using live bubble data streams under …

Cost-Effective System For Rural Roadway Traffic, Surface Conditions And Weather Conditions Monitoring, Yinhai Wang, Wei Sun, Sam Ricord, Cesar Maia De Souza, Yifan Ling, Yan Shi, Bingzhang Wang, Mehrdad Nasri

CSET Project Reports

This report presents the Mobile Unit for Sensing Traffic (MUST) project, which addresses the critical need for comprehensive traffic data in tribal and rural areas that often suffer from disproportionately high rates of traffic incidents due to limited infrastructure and resources. By implementing a low-cost, user-friendly data collection system, the MUST project aimed to provide real-time traffic information to significantly enhance traffic safety. The pilot installation in Yakama Nation, Washington, at a high-traffic intersection known for frequent accidents, marks a crucial step in this initiative. Collaboration with the Yakama Nation's Tribal Traffic Safety Coordinator and Yakama Power ensured the successful …

Assessing Pedestrian Safety On Roads Through Machine Learning Approaches For State Highways In Washington State, Yinhai Wang, Wei Sun, Sam Ricord, Cesar Maia De Souza

CSET Project Reports

The report presents a unique contrast for several Machine Learning approaches aiming at understanding pedestrian fatal collisions. Four classification techniques are applied to assess how roadway features mainly correlate to pedestrian fatal crashes: Logistic Regression, Nearest Neighbor Classification, Decision Tree, and Random Forest Classifier. The data used in this project was collected from the Highway Safety Information System (HSIS) database, which provides both collision data for the entire state of Washington and roadway characteristics for all state highways. Each of the four modeling approaches was implemented using K-fold cross-validation, a process that allows choosing the best parameters for the model. …

Toward Concurrent Identification Of Human Activities With A Single Unifying Neural Network Classification: First Step, Andrew Smith, Musa Azeem, Chrisogonas O. Odhiambo, Pamela J. Wright Phd, Ms, Med, Rn, Cen, Hanim E. Diktas, Spencer Upton, Corby K. Martin, Brett Froeliger, Cynthia F. Corbett, Homayoun Valafar

Publications

The characterization of human behavior in real-world contexts is critical for developing a comprehensive model of human health. Recent technological advancements have enabled wearables and sensors to passively and unobtrusively record and presumably quantify human behavior. Better understanding human activities in unobtrusive and passive ways is an indispensable tool in understanding the relationship between behavioral determinants of health and diseases. Adult individuals (N = 60) emulated the behaviors of smoking, exercising, eating, and medication (pill) taking in a laboratory setting while equipped with smartwatches that captured accelerometer data. The collected data underwent expert annotation and was used to train a …

Effects Of Running Shoe Stack Height On Movement Variability - A Shared Biomechanical And Motor Control Perspective, Bernd J. Stetter, Cagla Fadillioglu, Stefan Sell, Thorsten Stein

ISBS Proceedings Archive

Understanding how shoe features affect motor control processes is crucial for designing targeted running shoes. The purpose of this study was to investigate adaptations of coupled movement components, i.e. kinematic synergies (kSYNs), when running with different shoe stack heights (19 mm, 35 mm, and 50 mm). The applied analysis combined a principal component analysis, support vector machine classifiers, and stride-to-stride variability (SSV) calculations. The results showed classification rates ranging from 82.9% to 94.4% across different stack heights. Notably, only the 50 mm stack height demonstrated increased SSV for the kSYNs that highly contribute to separating the two stack heights when …

Standing Long Jump Power Estimation From Smartphone Imus, Beatrice De Lazzari, Giuseppe Vannozzi, Valentina Camomilla

ISBS Proceedings Archive

The purpose of this study was to provide athletes/coaches with an easy-to-implement estimate of the power of standing long jump (SLJ), recognized as an indicator of the ability of lower limbs of exert power. To this aim, inertial sensors embedded in smartphones were used. A sample group of 150 trained young participants was recruited and asked to perform the SLJ task while holding the smartphone. A set of features was identified, based on biomechanical knowledge and literature, and then selected through Lasso regression to be feed as input of three different optimized machine learning architectures to estimate the SLJ power. …

Determination Of Gait Events From 2d Video Using Long Short-Term Memory Neural Networks, Marion Mundt, Steffi Colyer, Jacqueline Alderson

ISBS Proceedings Archive

The purpose of this study was to automatically identify the key gait events, foot-strike and foot-off, from 2D video data. Markerless motion capture and pose estimation have become accepted tools in many biomechanics applications to automatically analyse 2D videos of human movement. However, the accurate detection of gait events from various camera views is still a challenge. We trained a long short-term memory neural network to identify foot-strike and foot-off events in walking and running trials captured from nine different camera views based on 2D pose estimation keypoint labels. We achieved a detection accuracy of 86.3-96.1% (F1 score 76.2-92.5%). These …