Engineering Commons^™

Physics-Informed Deep Learning With Kalman Filter Mixture For Traffic State Prediction, Niharika Deshpande, Hyoshin (John) Park

Engineering Management & Systems Engineering Faculty Publications

Accurate traffic forecasting is crucial for understanding and managing congestion for efficient transportation planning. However, conventional approaches often neglect epistemic uncertainty, which arises from incomplete knowledge across different spatiotemporal scales. This study addresses this challenge by introducing a novel methodology to establish dynamic spatiotemporal correlations that captures the unobserved heterogeneity in travel time through distinct peaks in probability density functions, guided by physics-based principles. We propose an innovative approach to modifying both prediction and correction steps of the Kalman Filter (KF) algorithm by leveraging established spatiotemporal correlations. Central to our approach is the development of a novel deep learning model …

Learning Deep Time-Index Models For Time Series Forecasting, Jiale Gerald Woo, Chenghao Liu, Doyen Sahoo, Akshat Kumar, Steven Hoi

Research Collection School Of Computing and Information Systems

Deep learning has been actively applied to time series forecasting, leading to a deluge of new methods, belonging to the class of historicalvalue models. Yet, despite the attractive properties of time-index models, such as being able to model the continuous nature of underlying time series dynamics, little attention has been given to them. Indeed, while naive deep timeindex models are far more expressive than the manually predefined function representations of classical time-index models, they are inadequate for forecasting, being unable to generalize to unseen time steps due to the lack of inductive bias. In this paper, we propose DeepTime, a …

Hyper-Local Weather Predictions With The Enhanced General Urban Area Microclimate Predictions Tool, Kevin A. Adkins, William Becker, Sricharan Ayyalasomayajula, Steven Lavenstein, Kleoniki Vlachou, David Miller, Marc Compere, Avinash Muthu Krishnan, Nickolas Macchiarella

Publications

This paper presents enhancements to, and the demonstration of, the General Urban area Microclimate Predictions tool (GUMP), which is designed to provide hyper-local weather predictions by combining machine-learning (ML) models and computational fluid dynamic (CFD) simulations. For the further development and demonstration of GUMP, the Embry–Riddle Aeronautical University (ERAU) campus was used as a test environment. Local weather sensors provided data to train ML models, and CFD models of urban- and suburban-like areas of ERAU’s campus were created and iterated through with a wide assortment of inlet wind speed and direction combinations. ML weather sensor predictions were combined with best-fit …

Machine-Learning-Based Model For Hurricane Storm Surge Forecasting In The Lower Laguna Madre, Cesar E. Davila Hernandez, Jungseok Ho, Dong-Chul Kim, Abdoul Oubeidillah

Civil Engineering Faculty Publications and Presentations

During every Atlantic hurricane season, storms represent a constant risk to Texan coastal communities and other communities along the Atlantic coast of the United States. A storm surge refers to the abnormal rise of sea water level due to hurricanes and storms; traditionally, hurricane storm surge predictions are generated using complex numerical models that require high amounts of computing power to be run, which grow proportionally with the extent of the area covered by the model. In this work, a machine-learning-based storm surge forecasting model for the Lower Laguna Madre is implemented. The model considers gridded forecasted weather data on …

Improving Data-Driven Infrastructure Degradation Forecast Skill With Stepwise Asset Condition Prediction Models, Kurt R. Lamm, Justin D. Delorit, Michael N. Grussing, Steven J. Schuldt

Faculty Publications

Organizations with large facility and infrastructure portfolios have used asset management databases for over ten years to collect and standardize asset condition data. Decision makers use these data to predict asset degradation and expected service life, enabling prioritized maintenance, repair, and renovation actions that reduce asset life-cycle costs and achieve organizational objectives. However, these asset condition forecasts are calculated using standardized, self-correcting distribution models that rely on poorly-fit, continuous functions. This research presents four stepwise asset condition forecast models that utilize historical asset inspection data to improve prediction accuracy: (1) Slope, (2) Weighted Slope, (3) Condition-Intelligent Weighted Slope, and (4) …

Predicting Pair Success In A Pair Programming Eye Tracking Experiment Using Cross-Recurrence Quantification Analysis, Maureen M. Villamor, Maria Mercedes T. Rodrigo

Department of Information Systems & Computer Science Faculty Publications

Pair programming is a model of collaborative learning. It has become a well-known pedagogical practice in teaching introductory programming courses because of its potential benefits to students. This study aims to investigate pair patterns in the context of pair program tracing and debugging to determine what characterizes collaboration and how these patterns relate to success, where success is measured in terms of performance task scores. This research used eye-tracking methodologies and techniques such as cross-recurrence quantification analysis. The potential indicators for pair success were used to create a model for predicting pair success. Findings suggest that it is possible to …

Forecasting Nodal Price Difference Between Day-Ahead And Real-Time Electricity Markets Using Long-Short Term Memory And Sequence-To-Sequence Networks, Ronit Das, Rui Bo, Haotian Chen, Waqas Ur Rehman, Donald C. Wunsch

Electrical and Computer Engineering Faculty Research & Creative Works

Price forecasting is at the center of decision making in electricity markets. Much research has been done in forecasting energy prices for a single market while little research has been reported on forecasting price difference between markets, which presents higher volatility and yet plays a critical role in applications such as virtual trading. To this end, this paper takes the first attempt at it and employs novel deep learning architecture with Bidirectional Long-Short Term Memory (LSTM) units and Sequence-to-Sequence (Seq2Seq) architecture to forecast nodal price difference between day-ahead and real-time markets. In addition to value prediction, these deep learning architectures …

Sortie-Based Aircraft Component Demand Rate To Predict Requirements, Thomas R. O'Neal, John M. Dickens, Lance Champaign, Aaron V. Glassburner, Jason R. Anderson, Timothy W. Breitbach

Faculty Publications

Purpose — Forecasting techniques improve supply chain resilience by ensuring that the correct parts are available when required. In addition, accurate forecasts conserve precious resources and money by avoiding new start contracts to produce unforeseen part requests, reducing labor intensive cannibalization actions and ensuring consistent transportation modality streams where changes incur cost. This study explores the effectiveness of the United States Air Force’s current flying hour-based demand forecast by comparing it with a sortie-based demand forecast to predict future spare part needs. Design/methodology/approach — This study employs a correlation analysis to show that demand for reparable parts on certain aircraft …

Artificial Intelligence Method For The Forecast And Separation Of Total And Hvac Loads With Application To Energy Management Of Smart And Nze Homes, Rosemary E. Alden, Huangjie Gong, Evan S. Jones, Cristinel Ababei, Dan M. Ionel

Electrical and Computer Engineering Faculty Publications

Separating the HVAC energy use from the total residential load can be used to improve energy usage monitoring and to enhance the house energy management systems (HEMS) for existing houses that do not have dedicated HVAC circuits. In this paper, a novel method is proposed to separate the HVAC dominant load component from the house load. The proposed method utilizes deep learning techniques and the physical relationship between HVAC energy use and weather. It employs novel long short-term memory (LSTM) encoder-decoder machine learning (ML) models, which are developed based on future weather data input in place of weather forecasts. In …

Quo Vadis Lakes Azuei And Enriquillo: A Future Outlook For Two Of The Caribbean Basin's Largest Lakes, Mahrokh Moknatian, Michael Piasecki

Publications and Research

Lakes Azuei (LA) and Enriquillo (LE) on Hispaniola Island started expanding in 2005 and continued to do so until 2016. After inundating large swaths of arable land, submerging a small community, and threatening to swallow a significant trade route between the Dominican Republic and Haiti; worries persisted at how far this seemingly unstoppable expansion would go. The paper outlines the approach to a look forward to answer this question vis-à-vis climate change scenarios developed by the Intergovernmental Panel on Climate Change (IPCC). It uses numerical representations of the two lakes, and it examines how the lakes might evolve, deploying three …

Home Energy Management System For Coordinated Pv And Hvac Controls Based On Ai Forecasting, Huangjie Gong, Rosemary E. Alden, Dan M. Ionel

Power and Energy Institute of Kentucky Presentations

Introduction

• This HEMS serves to transform HVAC system demand into a schedulable load bank or “dispatchable load” through controls based on day ahead forecasts
• Within this poster, a complete structure from data acquisition to day-ahead load scheduling is proposed
• For the purpose of study, measured data is used in place of forecasts to showcase best case results.

A Bibliometric Survey On The Use Of Long Short-Term Memory Networks For Multivariate Time Series Forecasting, Vidur Sood Mr., Manobhav Mehta Mr., Vedansh Mishra Mr., Akash Upadhyay Mr., Shilpa Hudnurkar, Shilpa Gite Dr., Neela Rayavarapu Dr.

Library Philosophy and Practice (e-journal)

In this paper, we aim to review and analyze the publications related to the utilization of Long Short-Term Memory (LSTM) networks for multivariate time series forecasting. The purpose of this bibliometric survey was to study how technology in the field of LSTM has evolved over the years. There were 242 research papers published, by over 50 researchers, over 6 years, on the topic of “Multivariate time series forecasting using LSTM”. The majority of these papers were published between the years 2018 and 2020. The Scopus database was utilized for analyzing recent trends in this area and to determine the …

Vpeak: Exploiting Volunteer Energy Resources For Flexible Peak Shaving, Phuthipong Bovornkeeratiroj, John Wamburu, David Irwin, Prashant Shenoy

Publications

Traditionally, utility companies have employed demand response for large loads or deployed centralized energy storage to alleviate the effects of peak demand on the grid. The advent of Internet of Things (IoT) and the proliferation of networked energy devices have opened up new opportunities for coordinated control of smaller residential loads at large scales to achieve similar benefits. In this paper, we present VPeak, an approach that uses residential loads volunteered by their owners for coordinated control by a utility for grid optimizations. Since the use of volunteer resources comes with hard limits on how frequently they can be used …

Cost Estimating Using A New Learning Curve Theory For Non-Constant Production Rates, Dakotah Hogan, John J. Elshaw, Clay M. Koschnick, Jonathan D. Ritschel, Adedeji B. Badiru, Shawn M. Valentine

Faculty Publications

Traditional learning curve theory assumes a constant learning rate regardless of the number of units produced. However, a collection of theoretical and empirical evidence indicates that learning rates decrease as more units are produced in some cases. These diminishing learning rates cause traditional learning curves to underestimate required resources, potentially resulting in cost overruns. A diminishing learning rate model, namely Boone’s learning curve, was recently developed to model this phenomenon. This research confirms that Boone’s learning curve systematically reduced error in modeling observed learning curves using production data from 169 Department of Defense end-items. However, high amounts of variability in …

Dim: Adaptively Combining User Interests Mined At Different Stages Based On Deformable Interest Model, Xiaoru Wang, Yueli Li, Zhihong Yu, Fu Li, Heng Zhang, Yali Cai, Lixian Li

Electrical and Computer Engineering Faculty Publications and Presentations

User interest mining is widely used in the fields of personalized search and personalized recommendation. Traditional methods ignore the formation of user interest which is a process that evolves over time. This leads to the inability to accurately describe the distribution of user interest. In this paper, we propose the interest tracking model (ITM). To add the timing, ITM uses Dirichlet distribution and multinomial distribution to describe the evolutional process of interest topics and frequent patterns, which well adapts to the evolution of user interest hidden in short texts between different time slices. In addition, it is well known that …

A Novel Monte Carlo-Based Neural Network Model For Electricity Load Forecasting, Binbin Yong, Zijian Xu, Jun Shen, Huaming Chen, Jianqing Wu, Fucun Li, Qingguo Zhou

Faculty of Engineering and Information Sciences - Papers: Part B

The ongoing rapid growth of electricity over the past few decades greatly promotes the necessity of accurate electricity load forecasting. However, despite a great number of studies, electricity load forecasting is still an enormous challenge for its complexity. Recently, the developments of machine learning technologies in different research areas have demonstrated its great advantages. General Vector Machine (GVM) is a new machine learning model, which has been proven very effective in time series prediction. In this article, we firstly review the basic concepts and implementation of GVM. Then we apply it in electricity load forecasting, which is based on the …

Artificial Neural Network Model For Bridge Deterioration And Assessment, G. Ali, A. Elsayegh, R. Assaad, Islam H. El-Adaway, I. S. Abotaleb

Civil, Architectural and Environmental Engineering Faculty Research & Creative Works

Missouri has the seventh largest number of bridges nationwide, yet must maintain its inventory with funding from just the fourth lowest gasoline tax in the country. Estimation and prediction of the condition of bridges is necessary to create and optimize future maintenance, repair, and rehabilitation plans as well as to assign the necessary associated budgets. Previous studies have used statistical analysis, fuzzy logic, and Markovian models to develop algorithms for predicting future bridge conditions. Due to the non-linear nature of the relationship between the characteristics of bridges and their deterioration behavior, Artificial Neural Networks (ANN) have shown to be more …

Forecasting Anomalous Events And Performance Correlation Analysis In Event Data, Sonya Leech [Thesis]

Dissertations

Classical and Deep Learning methods are quite common approaches for anomaly detection. Extensive research has been conducted on single point anomalies. Collective anomalies that occur over a set of two or more durations are less likely to happen by chance than that of a single point anomaly. Being able to observe and predict these anomalous events may reduce the risk of a server’s performance. This paper presents a comparative analysis into time-series forecasting of collective anomalous events using two procedures. One is a classical SARIMA model and the other is a deep learning Long-Short Term Memory (LSTM) model. It then …

Ensemble Neural Network Method For Wind Speed Forecasting, Binbin Yong, Fei Qiao, Chen Wang, Jun Shen, Yongqiang Wei, Qingguo Zhou

Faculty of Engineering and Information Sciences - Papers: Part B

Wind power generation has gradually developed into an important approach of energy supply. Meanwhile, due to the difficulty of electricity storage, wind power is greatly affected by the real-time wind speed in wind fields. Generally, wind speed has the characteristics of nonlinear, irregular, and non-stationary, which make accurate wind speed forecasting a difficult problem. Recent studies have shown that ensemble forecasting approaches combining different sub-models is an efficient way to solve the problem. Therefore, in this article, two single models are ensembled for wind speed forecasting. Meanwhile, four data pre-processing hybrid models are combined with the reliability weights. The proposed …

From Business Understanding To Deployment: An Application Of Machine Learning Algorithms To Forecast Customer Visits Per Hour To A Fast-Casual Restaurant In Dublin, Odunayo David Adedeji

Dissertations

This research project identifies the significant factors that affects the number of customer visits to a fast-casual restaurant every hour and proceeds to develop several machine learning models to forecast customer visits. The core value proposition of fast-casual restaurants is quality food delivered at speed which means they have to prepare meals in advance of customers visit but the problem with this approach is in forecasting future demand, under estimating demand could lead to inadequate meal preparation which would leave customers unsatisfied while over estimation of demand could lead to wastage especially with restaurants having to comply with food safety …

Solar Irradiance Forecasting Using Deep Neural Networks, Ahmad Alzahrani, Pourya Shamsi, Cihan H. Dagli, Mehdi Ferdowsi

Electrical and Computer Engineering Faculty Research & Creative Works

Predicting solar irradiance has been an important topic in renewable energy generation. Prediction improves the planning and operation of photovoltaic systems and yields many economic advantages for electric utilities. The irradiance can be predicted using statistical methods such as artificial neural networks (ANN), support vector machines (SVM), or autoregressive moving average (ARMA). However, they either lack accuracy because they cannot capture long-term dependency or cannot be used with big data because of the scalability. This paper presents a method to predict the solar irradiance using deep neural networks. Deep recurrent neural networks (DRNNs) add complexity to the model without specifying …

Predicting General Aviation Pilots’ Weather-Related Performance Through A Scenario-Based Assessment, Jessica Cruit, Christina Frederick, Beth Blickensderfer, Joseph Keebler, Thomas Guinn

Publications

Weather-related accidents continue to challenge the general aviation (GA) community and with the development of advanced weather technology, GA pilots need additional education and training on how to effectively use these weather products to ensure flight safety. Currently, the literature on aviation weather suggests that there is a gap in both training and assessment strategy for GA pilots. Furthermore, several studies advocate assessing GA pilots at a deeper level of learning by including weather-based, scenario/application questions on the Federal Aviation Administration’s (FAA) written exam for private pilots. After first developing a scenario-based, aviation weather assessment, we used a multiple regression …

Ballistic Limit Equations For Non-Aluminum Projectiles Impacting Dual-Wall Spacecraft Systems, William P. Schonberg, J. Martin Ratliff

Civil, Architectural and Environmental Engineering Faculty Research & Creative Works

One of the primary design considerations of earth-orbiting spacecraft is the mitigation of the damage that might occur from an on-orbit MMOD impact. Traditional damage-resistant design consists of a 'bumper' that is placed a small distance away from a spacecraft component or from the wall of the element in which it is housed. The performance of such a multi-wall structural element is typically characterized by its ballistic limit equation (BLE), which defines the threshold particle size that results in a failure of the spacecraft element. BLEs are also key components of any micro-meteoroid/orbital debris (MMOD) risk assessment calculations. However, these …

Application Of An Artificial Neural Network To Predict Graduation Success At The United States Military Academy, Gene Lesinski, Steven Corns, Cihan H. Dagli

Engineering Management and Systems Engineering Faculty Research & Creative Works

This paper presents a neural network approach to classify student graduation status based upon selected academic, demographic, and other indicators. A multi-layer feedforward network with backpropagation learning is used as the model framework. The model is trained, tested, and validated using 5100 student samples with data compiled from admissions records and institutional research databases. Nine input variables consist of categorical and numeric data elements including: high school rank, high school quality, standardized test scores, high school faculty assessments, extra-curricular activity score, parent's education status, and time since high school graduation. These inputs and the multi-layer neural network model are used …

Evaluating Forecasting Methods By Considering Different Accuracy Measures, Nijat Mehdiyev, David Lee Enke, Peter Fettke, Peter Loos

Engineering Management and Systems Engineering Faculty Research & Creative Works

Choosing the appropriate forecasting technique to employ is a challenging issue and requires a comprehensive analysis of empirical results. Recent research findings reveal that the performance evaluation of forecasting models depends on the accuracy measures adopted. Some methods indicate superior performance when error based metrics are used, while others perform better when precision values are adopted as accuracy measures. As scholars tend to use a smaller subset of accuracy metrics to assess the performance of forecasting models, there is a need for a concept of multiple accuracy dimensions to assure the robustness of evaluation. Therefore, the main purpose of this …

Using Neural Networks To Forecast Volatility For An Asset Allocation Strategy Based On The Target Volatility, Youngmin Kim, David Lee Enke

Engineering Management and Systems Engineering Faculty Research & Creative Works

The objective of this study is to use artificial neural networks for volatility forecasting to enhance the ability of an asset allocation strategy based on the target volatility. The target volatility level is achieved by dynamically allocating between a risky asset and a risk-free cash position. However, a challenge to data-driven approaches is the limited availability of data since periods of high volatility, such as during financial crises, are relatively rare. To resolve this issue, we apply a stability-oriented approach to compare data for the current period to a past set of data for a period of low volatility, providing …

Advances In Repurposing And Recycling Of Post-Vehicle-Application Lithium-Ion Batteries, Charles R. Standridge, Lindsay Corneal, Nicholas Baine

Mineta Transportation Institute

Increased electrification of vehicles has increased the use of lithium-ion batteries for energy storage, and raised the issue of what to do with post-vehicle-application batteries. Three possibilities have been identified: 1) remanufacturing for intended reuse in vehicles; 2) repurposing for non-vehicle, stationary storage applications; and 3) recycling, extracting the precious metals, chemicals and other byproducts. Advances in repurposing and recycling are presented, along with a mathematical model that forecasts the manufacturing capacity needed for remanufacturing, repurposing, and recycling. Results obtained by simulating the model show that up to a 25% reduction in the need for new batteries can be achieved …

Noise Canceling In Volatility Forecasting Using An Adaptive Neural Network Filter, Soheil Almasi Monfared, David Lee Enke

Engineering Management and Systems Engineering Faculty Research & Creative Works

Volatility forecasting models are becoming more accurate, but noise looks to be an inseparable part of these forecasts. Nonetheless, using adaptive filters to cancel the noise should help improve the performance of the forecasting models. Adaptive filters have the advantage of changing based on the environment. This feature is vital when they are used along with a model for volatility forecasting and error cancellation in the financial markets. Nonlinear Autoregressive (NAR) neural networks have simple structures, but they are efficient tools in error cancelation systems when working with non-stationary and random walk noise processes. For this research, an adaptive threshold …

Wind Energy And Ireland: Could Forecasting Errors Lead To A Flawed Market?, Michael Mcdonald, Thomas Woolmington, Keith Sunderland

Conference papers

This paper explores wind energy forecasting consistency by considering the error benchmarks associated with the generation output of a small wind farm in comparison to the national forecasting as provided by Eirgrid, the Irish TSO. This percentage error analysis will contrast the predicted (Eirgrid) capacity and actual wind energy output observations (Wind farm) and postulations that consider alternative prediction metrics are discussed. The findings suggest that in monthly like for like comparisons over a twelve month period, total MWh percentage errors of -0.36% and 5.7% are observed respectively for the actual generation and the forecasted …

Ad-Hoc Automated Teller Machine Failure Forecast And Field Service Optimization, Michelle L. F. Cheong, Ping Shung Koo, B. Chandra Babu

Research Collection School Of Computing and Information Systems

As part of its overall effort to maintain good customer service while managing operational efficiency and reducing cost, a bank in Singapore has embarked on using data and decision analytics methodologies to perform better ad-hoc ATM failure forecasting and plan the field service engineers to repair the machines. We propose using a combined Data and Decision Analytics Framework which helps the analyst to first understand the business problem by collecting, preparing and exploring data to gain business insights, before proposing what objectives and solutions can and should be done to solve the problem. This paper reports the work in analyzing …