PhD, University of Cincinnati, 2024, Engineering and Applied Science: Civil Engineering

This research aims at optimizing the winter pavement management practices by (1) developing an efficient yet simple pothole surveillance system utilizing state-of-the-art connected and autonomous vehicle (CAV) sensors, including LiDAR and camera and (2) developing prediction models with machine learning algorithms and applying survival analysis to estimate the service life of commonly used pothole patching methods/materials combinations and ultimately calculating the life cycle cost associated with it. For pothole detection, automobile industry-grade mechanical LiDAR and a camera were used. Two pothole detection approaches were proposed. In the first approach, data collected from the camera and LiDAR were fused and consequently applied deep learning-based object detection algorithm to locate potholes and extract point cloud data corresponding to the potholes using the coordinates of the detected bounding box. The second approach detected potholes directly from the cross-sectional LiDAR point cloud data using a deep learning-based object detection technique followed by utilizing the point clouds' spatial information to estimate the potholes' dimensions. In both approaches, the timestamps of the GPS and LiDAR were synchronized to locate the pothole coordinate. While the first approach showed great promise in estimating the pothole dimensions with unprecedented accuracy, the validation of the second approach demonstrated that the approach can be reliably employed to locate potholes and estimate the dimensions at different highway speeds. Two life cycle cost-based approaches were proposed to optimize pothole patching practice with various combinations of patching materials and methods considering different factors such as traffic volume, size of the potholes, and climatic conditions. The first approach included a non-parametric survival approach to identify the factors affecting the survival life of the pothole patches, consequently using this information to es (open full item for complete abstract)

Committee: Munir Nazzal Ph.D. (Committee Chair); Matthew Steiner Ph.D. (Committee Member); Lei Wang Ph.D. (Committee Member); Nabil Nassif (Committee Member) Subjects: Civil Engineering

Doctor of Philosophy, The Ohio State University, 2021, Computer Science and Engineering

Life sciences literature is replete with detailed and not-so-detailed instructions for wet-lab processes, called protocols, that communicate biological experiments to the scientific community. Nevertheless, due to the manual execution of these protocols, over 70% of researchers have failed to reproduce another scientist's experiments, with more than 50% unable to reproduce their research. An estimated $28B/year is spent on research that is not reproducible, with about 11% attributed to execution errors. Hence, there is a significant reproducibility and scalability crisis in scientific research. A researcher can spend weeks or even months setting up, optimizing, and validating new experimental techniques. And thus, he/she can at best realize the experiments in minimal ways (small sample sizes, etc.). With an ever-increasing need for reproducibility and error-free replication of experimental procedures, laboratory automation is becoming increasingly crucial in many sectors of life science research. However, compared with manufacturing and service industries, the life science research industry is lagging in utilizing large-scale industrial automation for productivity, capacity, and quality improvements. Technological advancements (e.g., AI, modern software architectures and best practices, and sensing) can spur the development of intelligent automation systems for experimental procedures at higher precision and throughput that can also provide a significant reduction in human error. However, currently offered solutions have not seen widespread adoption. One of the barriers in the intelligent automation of wet lab protocols is that the vast majority of them are written in natural language that effectively disseminates practical procedures within the research community but is difficult for automation systems to interpret. Through years of experience, life science researchers can naturally interpret wet lab instructions by understanding sentence structure, grounding (open full item for complete abstract)

Committee: Raghu Machiraju PhD (Advisor); Huan Sun PhD (Committee Member); Rachel Kopec PhD (Committee Member); Eric Fosler-Lussier PhD (Advisor) Subjects: Artificial Intelligence; Computer Engineering; Computer Science; Experiments; Microbiology; Molecular Biology; Molecular Chemistry; Robotics; Robots

MS, University of Cincinnati, 2020, Engineering and Applied Science: Electrical Engineering

Recent evidence suggests that sonar provides bats only with limited information about the environment. Nevertheless, they can fly swiftly through dense environments while avoiding obstacles. Previously, we proposed a model of sonar-based obstacle avoidance that only relied on the interaural level difference of the onset of the echoes. In this paper, we extend this previous model. In particular, we present a model that (1) is equipped with a short term memory of recent echo trains, and (2) uses the full echo train. Because handcrafting a controller to use more sonar data is challenging, we resort to machine learning to train a robotic model. We find that both extensions increase performance and conclude that these could be used to enhance our models of bat sonar behavior. We discuss the implications or our method and findings for both biology and bio-inspired engineering.

Committee: Dieter Vanderelst Ph.D. (Committee Chair); Zachariah Fuchs Ph.D. (Committee Member); Ali Minai Ph.D. (Committee Member) Subjects: Artificial Intelligence

Master of Science, The Ohio State University, 2016, Earth Sciences

While life is known to exist in the subsurface environment, specific limitations to microbial populations inhabiting deep subsurface habitats are assumed and include organic substrate and terminal electron acceptor availability, temperature and space to live. Microbial populations have been found in environments where they are least expected, notably 3 km deep in granite as well as in the boreholes and near-borehole environment of oil and gas wells where they often cause problems for oil and gas operators. While an anthropogenic source is assumed for microbes in and near the borehole of oil and gas wells in the Utica-Point Pleasant system due to the high temperatures the rock has undergone, the question remains whether microbial populations could have survived in less mature rock to the West of contemporary oil and gas operations. As a component of an NSF funded study “Microbial Biodiversity and Functionality of Deep Shale and it's Interfaces” this research attempts to answer whether microbes could have survived to the present day in pores as well as questions relating to biological limitations and whether these are present in the Utica-Point Pleasant. Looking at sulfur, organic carbon and potential micro-lithologies within the Utica-Point Pleasant organic-rich mudstone may yield a better understanding of how the diagenesis of a marine mud affects anaerobic microbial populations established in these muds. Utilizing a variety of petrophysical, geochemical and high resolution imaging techniques this research has identified micro-lithologies within the Utica-Point Pleasant system that likely provided safe harbor for anaerobic microbes until the habitat was either sterilized due to temperature or in-filled with minerals, sealing off these habitats. Further, these micro-lithologies may respond to hydraulic fracturing chemicals and processes and become inhabitable for anthropogenically introduced microbial populations.

Committee: David Cole PhD (Advisor); Matthew Saltzman PhD (Committee Member); Michael Wilkins PhD (Committee Member) Subjects: Chemistry; Earth; Geology; Microbiology

PhD, University of Cincinnati, 2016, Engineering and Applied Science: Mechanical Engineering

Machine health monitoring has advanced significantly for improving machine uptime and efficiency by providing proper fault detection and remaining useful life (RUL) prediction information to machine users. Despite these advancements, conventional condition monitoring (CM) techniques face several challenges in machine prognostics, including the ineffective RUL prediction modeling for machine under dynamic working regimes, and the lack of complete lifecycle data for modeling and validation, among others. To address these issues, this research introduces Accelerated Degradation Tests (ADT) with a deep learning technique, which is a novel method to improve machine life prediction accuracy under different working regimes for Prognostics and Health Management applications. This dissertation work highlights the mathematical framework of deep learning based machine life modeling under an ADT environment, including Constant Stress Accelerated Degradation Testing (CSADT) and Step-Stress ADT (SSADT) conditions. Since most CM features show no trend or indication of failure until a machine is approaching the end of its life, current RUL prediction techniques are not applicable in that they are only effective when incipient degradation is detected. This dissertation work applies feature enhancement to condition-based features using the enhanced Restricted Boltzmann Machine (RBM) method with a prognosability regularization term; afterwards, a similarity-based method is applied to predict machine life with the enhanced RBM features. In addition, this research has added varying stress conditions during experiments to replicate dynamic operation regimes. The stress variable, a type of regime variables, is input into Mixed-Variate RBM (MV-RBM) model. Therefore, a Regime Matrix based RBM (RM-RBM) is proposed to improve the feature prognosability and reduce the impact that the working stresses have on the features. Then the RBM features can be fused into a single health value which ref (open full item for complete abstract)

Committee: Jay Lee Ph.D. (Committee Chair); Linxia Liao Ph.D. (Committee Member); Teik Lim Ph.D. (Committee Member); David Thompson Ph.D. (Committee Member) Subjects: Mechanical Engineering; Mechanics