Master of Computing and Information Systems, Youngstown State University, 2023, Department of Computer Science and Information Systems

Investors are always looking for ways to make profit in the stock market. Predicting this highly volatile market has been historically challenging. This study explores the use of the social media platform, Twitter, and Machine Learning Algorithm for Time Series Analysis. Our findings suggested that Twitter's data may not be the best for Sentiment Analysis, while other machine learning techniques for Time Series Analysis such as LSTM would be effective. This could potentially help an investor with higher returns.

Committee: John R. Sullins PhD (Advisor); Feng George Yu PhD (Committee Member); Alina Lazar PhD (Committee Member) Subjects: Artificial Intelligence; Computer Science

MS, University of Cincinnati, 2024, Engineering and Applied Science: Mechanical Engineering

This study proposes a novel approach to intracranial pressure (ICP) analysis. ICP is the pressure exerted by fluids and tissue inside of the brain and reveals crucial insights regarding a patient's physiological state after undergoing traumatic brain injury (TBI). ICP waveform morphological analysis can provide clinicians with information regarding a patient's health and facilitate proactive intervention and inhibit the development of secondary pathologies such as cerebral edema (swelling), ischemia (lack of blood to the brain), vascular injuries, neurological dysfunction, and cognitive/behavioral changes. By integrating arterial blood pressure (ABP) and electrocardiogram (ECG) data from patients who have undergone TBI this method aims to enhance the analysis of not just ICP waveform morphology but cross-signal morphological features. The proposed methodology was evaluated on ten patients and their respective ICP, ABP, and ECG data; it involved three key steps: 1) multimodal signal pre-processing alongside manual labeling of ICP waveform morphologies to train a base support vector machine (SVM) morphological classifier. 2) The use of semi-supervised learning leveraging a subject matter expert (SME) to further train the SVM ICP waveform morphological classifier and augment its training data set on all ten patients to assign incoming pre-processed ICP waveforms with a morphology label. A SME used the posterior probability of the SVM machine learning model to aid the algorithm in adapting to new and unseen ICP waveform morphologies that were not present in the initial manually labeled SVM training data set. 3) The utilization of dynamic time warping barycenter averaging (DBA) to produce representative averages (centroids) of ICP waveforms present in the SVM training data set and derivative dynamic time warping (DDTW)-driven subpeak identification to map subpeaks from DBA generated centroid templates with SME assigned ground truth subpeak(s) to incoming SVM clas (open full item for complete abstract)

Committee: Xiaodong Jia Ph.D. (Committee Chair); Brandon Foreman M.D. (Committee Member); Manish Kumar Ph.D. (Committee Member) Subjects: Mechanical Engineering

Doctor of Philosophy, University of Toledo, 2023, Spatially Integrated Social Science

The increase in rate of international migration to the United States since the late 1960s, coupled with a generally high rate among minority populations, altered the racial and ethnic composition of America's urban neighborhoods. The changing demography and increase in shares of minority subpopulations underscore the salience of conducting multigroup studies of residential and socioeconomic segregation beyond the traditional white versus black dichotomy. Segregation based on subgroup characteristics (de facto or de jure) is problematic, particularly for racial minorities and low-income residents who are limited in moving to areas they can afford. These minority neighborhoods are associated with physical and socioeconomic disadvantage due to public and private de-investment. The undercurrents of segregation were explored in the racial tipping point and white flight literature where non-Hispanic white majority residents exit old inner and central city neighborhoods when the share of minority populations increase beyond a critical threshold. Due to strong correlations between race and income, white flight also tends to concentrate poverty in the abandoned neighborhoods. Beyond this relationship between personal choice and segregation however, local and federal public policies have also been historically linked with segregating urban America. Federal highway programs, mortgage loan underwriting processes, suburban housing developments, and restrictive local zoning laws have created race and income-based segregated spaces. Also, reinvestment programs aimed revitalizing physical and socially distressed neighborhoods tend to yield minimal outcomes. This is often due to either limited funding compared to the magnitude of the problem or lack of sustained political commitment, overemphasis on market-based ideas which alienate minorities and low-income residents, and emphasis on new urbanism housing designs associated net losses in the public housing stock. In this dissertatio (open full item for complete abstract)

Committee: Daniel Hammel (Committee Chair); Sujata Shetty (Committee Member); Isabelle Nilsson (Committee Member); Neil Reid (Committee Member); Jami Taylor (Committee Member) Subjects: Geographic Information Science; Geography; Public Policy; Urban Planning

Doctor of Philosophy, University of Akron, 2015, Civil Engineering

The models that are able to appropriately study the temporal and spatial dependence structure of water quality and hydrological time series are the essential tools to evaluate the future state of water availability, pollution loading, and best watershed management options. The mass-balance model is one of the current approaches for modeling water quality. However, it has the following limitations: extensive data for inputs, limited effectiveness for many water quality parameters, and ineffectiveness for long-term forecasts. To address the above limitations, statistical and stochastic models, such as classical ARIMA, ANN, and TFN modeling approaches have also been applied to investigate water quality and hydrological time series. However, they also have the some limitations, i.e., Gaussian process and/or linear dependence. Thereby, this study proposes to investigate the water quality and hydrological time series with the use of the following methodologies: (1) applying the order series transformation method to fulfill the assumptions and to address the limitations of the classic (F)AR(I)MA time series modeling approach; (2) applying the copula theory to investigate the spatial dependence pattern for water quality and hydrological time series at the different locations within the same watershed; (3) investigating the temporal dependence for the observed sequences with the use of copula-based Markov process to address the limitations existed in the classic Markov process. To valid the proposed approaches, three watersheds (i.e., Stillaguamish and Snohomish watersheds in Washington: Forest watershed, Chattahoochee River Watershed in Georgia: Urban Watershed, and Cuyahoga River Watershed in Ohio: watershed with mixed LULC) are selected as case-studies. The findings of this study showed: (1) the order series transformation may successfully transform the heavy-skewed and/or fat-tailed univariate time series to Gaussian process to fulfill the assumptions of (F)AR(I)model (open full item for complete abstract)

Committee: Lan Zhang Dr (Advisor) Subjects: Civil Engineering; Environmental Engineering; Water Resource Management

Master of Sciences, Case Western Reserve University, 2014, Materials Science and Engineering

In pursuit of a higher fidelity understanding of the long-term degradation of long-lived technologies, such as photovoltaic (PV) systems, the framework of Lifetime and Degradation Science (L&DS) goes beyond initial qualification tests and investigates the underpinning mechanisms of degradation. L&DS concerns itself with the complex and multivariate signatures of the degradation process and uncovering the fundamental physical mechanisms contributing to that degradation. In the case of PV modules, this effort requires extensive continuous monitoring of PV modules' power production and climatic conditions. The responses of PV module to the stressors of the real world is cross-correlated to the simulated and accelerated stressors placed on devices in a laboratory setting. A unique, highly instrumented, outdoor test facility for PV materials, components, and systems, the Solar Durability and Lifetime Extension (SDLE) center's SunFarm, was built for the purpose of better understanding the power degradation mechanisms of PV modules and materials. The SDLE SunFarm provides an apparatus for the collection of real-world time series data consisting of output power, weather and insolation metrology. The SunFarm is comprised of 122 individual PV power plants, including 120 module-level plants and 2*8 modules, string-level plants. Output power is monitored through appropriate grid-tied inverters. The metrology package developed at CWRU for the collection of time series data provides a model to be implemented at external sites around the globe. In order to expand the ability of monitoring PV systems' performance under different climatic conditions, a global SunFarm Network was implemented among nine outdoor test facilities around the world in collaboration with academic institutions and industrial partners including commercial power plants. This thesis provides the initial data analytics on the first six months of data from 60 PV modules on the SDLE SunFarm, and (open full item for complete abstract)

Committee: Roger French (Advisor); David Matthiesen (Committee Member); Jennifer Carter (Committee Member); Jiayang Sun (Committee Member); Timothy Peshek (Committee Member); Yifan Xu (Committee Member) Subjects: Energy; Environmental Engineering; Materials Science

Doctor of Philosophy in Urban Studies and Public Affairs, Cleveland State University, 2013, Maxine Goodman Levin College of Urban Affairs

Since the late 1990s, state governments in the U.S. have diversified policy instruments for encouraging the electric power industry to deploy renewable sources for electricity generation. While observing the increasing number of new renewable energy policies at the state level governments, this study raised two research questions: (1) how do state governments intervene in the renewable energy market? and (2) how do various policy approaches taken by state governments affect renewable energy development? To answer for these questions, this study attempts to identify the trends and variations in renewable energy policy designs among states in terms of the combination of aggregate level policy instruments used by state authorities. Additionally, this study aims to examine and compare the effectiveness of policy instruments in the deployment of renewable energy sources for electricity production. This study examined 18 state legislative, renewable energy related regulations, programs, or financial incentives existing between 2001 and 2010 in 48 states. Those 18 individual renewable energy policies were classified into three types of policy instruments: command-and-control, market-based, and information instruments. For the analysis, this study measured the amount and share of the electricity generation from non-hydro renewable sources as renewable energy policy effects. In order to isolate policy effects, this study also considered state specific characteristics such as natural endowment, economic and political environments, and the market conditions of electric power industries in different states. This study employed fixed-effects models to analyze cross-sectional time series data. The results showed that states’ adoption of diverse command-and-control types of policy instruments have significantly influenced the increase of both the amount and share of renewable electricity, while informative policy tools helped increase the share of renewable sources used (open full item for complete abstract)

Committee: William Bowen PhD (Committee Chair); Benjamin Clark PhD (Committee Member); Sung-Han Cho PhD (Committee Member) Subjects: Public Policy

Doctor of Philosophy, The Ohio State University, 2006, Psychology

Dynamic factor analysis (DFA), a combination of factor analysis and time series analysis, involves autocorrelation matrices calculated from multivariate time series. Because the distribution of autocorrelation matrices is intractable, obtaining statistical properties of DFA estimators is difficult. The dissertation proposes using the bootstrap to obtain standard error estimates, confidence intervals, and test statistics for DFA models. The dissertation considers two bootstrap procedures for dependent data, namely the parametric bootstrap and the moving block bootstrap. The parametric bootstrap is like a Monte Carlo study in which the population parameters are the parameter estimates obtained from the original sample. The moving block bootstrap breaks down the original time series to blocks, draws samples with replacement from the blocks, and connects the sampled blocks together to form a bootstrap sample. In addition, the dissertation considers DFA with categorical data, which is common in psychological research. Bootstrap confidence intervals and bootstrap tests require quantiles of the distribution of bootstrap replications. The quantiles are often estimated using empirical cumulative distribution functions. The target distribution method is a semiparametric method for estimating distribution functions. This dissertation also investigates whether the target distribution method can be employed to improve the estimation of the quantiles of bootstrap replications. The bootstrap procedures were illustrated using both simulation studies and two published examples. Results of the simulation studies are (1) Both the parametric bootstrap and the moving block bootstrap provided accurate standard error estimates; (2) Actual coverage probabilities of confidence intervals obtained from the two bootstrap procedures were close to their nominal levels; (3) Actual rejection rates of comparing nested models and of testing individual differences were close to their nominal levels, (open full item for complete abstract)

Committee: Michael Browne (Advisor) Subjects: Psychology, Psychometrics

Master of Science (MS), Ohio University, 2004, Geological Sciences (Arts and Sciences)

Understanding flow-system dynamics of underground coal mine complexes, such as the Corning mine complex that discharges acid mine drainage into Sunday Creek, is essential to designing in-situ remediation. Time series analysis is applied to the study of mine aquifers to characterize the systems between the input function (precipitation) and the output functions (discharge and head). Results are presented as correlograms, coherency diagrams, phase diagrams, and cross correlograms. The analysis of Corning discharge shows that the aquifer has a short response time and has a low storage capacity. A time lag of 3 to 4 days is found between precipitation and mine discharge, which corresponds to pressure pulse propagation and not to the actual advective flow of water. The results also demonstrate the important spatial heterogeneity of the aquifer and indicate that the mine does not behave as a single pool. Assuming porous-medium confined flow, barometric pressure and tidal signals are analyzed to yield mine aquifer properties. The analysis yields estimates of hydraulic conductivity, storage, barometric efficiency, and strain sensitivity. Comparison of the results with the available literature values indicates that the aquifer properties determined in this study have reasonable values. Parameter estimates are used to develop a numerical model of the Corning complex, using MODFLOW. The model simulates observed hydraulic head distributions and mine discharge rates with fair accuracy. The result of the simulations shows that 45% of the inflow to the mine complex derives from the surrounding coal strata, including detached mines. Travel time for water captured at subsidence captures is found to exceed 10 years, because of low gradients. It is finally concluded that a combination of time series analysis, barometric analysis and numerical modeling can provide useful information about the hydrogeology of a mine system prior to a large-scale and expensive in-situ remediation design.

Committee: Mary Stoertz (Advisor) Subjects: Geological Survey

PHD, Kent State University, 2009, College of Business and Entrepreneurship, Ambassador Crawford / Department of Management and Information Systems

This dissertation comprises of a set of three essays on emerging practitioner relevant theories and methods such as Real Options (RO) and Economic Value Added (EVA) for the valuation of investments in technology. The first essay develops an innovative approach for assessing practitioner relevance of academic research that is based on determining Granger causality between academic and practitioner interests in a given topic, as proxied by publication activity on that topic. The academic and practitioner interests are modeled as a two-component vector autoregressive (VAR) process and in addition to gauging Granger causality, which is done on stabilized components of the VAR model, I also utilize cointegration to evaluate the equilibrium relationship between the components of the VAR regardless of their stationarity. This model is tested on the two topics of EVA and RO.The second essay develops an alternative to the Technology Acceptance Model (TAM) called the Methodology Adoption Decision Model (MADM) for the adoption of new methodology by a firm. Analogous to the TAM, the MADM is a parsimonious model which views the theoretical soundness and the practical applicability of a methodology as the key drivers of firm-level adoption of methodology. The theoretical soundness and practical applicability are proxied by the sentiments expressed in the academic and practitioner literatures on the methodology in question. The MADM is used to assess the comparative likelihood of adoption of EVA and RO based on a sentiment extraction experiment for determining the inclinations of the academic and practitioner communities towards EVA and RO. The third essay applies RO to the context of investments by firms in XML-based enterprise integration (EI) technology. An interpretive hermeneutic approach is employed to develop a set of decision-making heuristics for the exercise of real options that optimize the RO value construct of Strategic Net Present Value (SNPV). This decision-making (open full item for complete abstract)

Committee: Marvin Troutt PhD (Committee Chair); Alan Brandyberry PhD (Committee Member); Felix Offodile PhD (Committee Member); John Thornton PhD (Committee Member) Subjects: Finance; Information Systems; Operations Research

Doctor of Philosophy, Case Western Reserve University, 2013, EECS - System and Control Engineering

This thesis investigates the complexity in physiological time series with application to neonatal sleep electroencephalography (EEG) signals. Complexity analysis is applied to two clinical data sets of neonatal sleep Electroencephalography(EEG) time series, to uncover the evolution of signal dynamics and its relationship to neurodevelopment and maturation. A review of the advantages and disadvantages of various complexity measures is provided and it is determined that nonlinear dynamic analysis is complimentary to the traditional linear methods for EEG signal processing. Surrogate data analysis is used to test the nonlinearity structure in the signal. The complexity of the neonatal sleep EEG signals were further quantified by evaluating two complexity measures i.e. Approximate Entropy(ApEn) and Sample Entropy(SaEn). The suitability of ApEn and SaEn for moderate length data and their relative robustness to noise has made them the good candidate for analyzing EEG time series data. Parameter selection is of utmost importance in the computation of complexity measures, and this was addressed in the thesis by improving the process of determining the appropriate time delay. The time delay determination process was applied to both synthetic and real data; and incorporated into the computation of ApEn and SaEn. The two clinical data sets used in this study consist of both preterm and full-term neonates. The two data sets were collected with different cohorts, sampling rate and data collection hardware. The cohorts in one data set are all healthy while cohorts in the other one are either sick and healthy. Though the vast difference between the two data sets, the following conclusions are applicable to both cases: 1) Surrogate data test performed on both data sets shows evidence of non-linear structure;. 2) It further suggests the necessity of using nonunity time delay for the calculation of ApEn and SaEn; 3) ApEn and SaEn were shown to be effective in quantifying the temporal (open full item for complete abstract)

Committee: Kenneth Loparo (Committee Chair); Marc Buchner (Committee Member); Vira Chankong (Committee Member); Mark Scher (Committee Member) Subjects: Electrical Engineering; Engineering; Information Science; Systems Science

Master of Science, The Ohio State University, 1929, Graduate School

Committee: Not Provided (Other) Subjects:

Doctor of Philosophy, The Ohio State University, 2024, Civil Engineering

With the development of remote sensing technology in recent decades, spaceborne sensors with sub-meter and meter spatial resolution (Worldview & PlanetScope) have achieved a considerable image quality to generate 3D geospatial data via a stereo matching pipeline. These achievements have significantly increased the data accessibility in 3D, necessitating adapting these 3D geospatial data to analyze human and natural environments. This dissertation explores several novel approaches based on stereo and multi-view satellite image-derived 3D geospatial data, to deal with remote sensing application issues for built-up area modeling and natural environment monitoring, including building model 3D reconstruction, glacier dynamics tracking, and lake algae monitoring. Specifically, the dissertation introduces four parts of novel approaches that deal with the spatial and temporal challenges with satellite-derived 3D data. The first study advances LoD-2 building modeling from satellite-derived Orthophoto and DSMs with a novel approach employing a model-driven workflow that generates building rectangular 3D geometry models. By integrating deep learning for building detection, advanced polygon extraction, grid-based decomposition, and roof parameter computation, we accurately computed complex building structures in 3D, culminating in the development of SAT2LoD2—a popular open-source tool in satellite-based 3D urban reconstruction. Secondly, we further enhanced our building reconstruction framework for dense urban areas and non-rectangular purposes, we implemented deep learning for unit-level segmentation and introduced a gradient-based circle reconstruction for circular buildings to develop a polygon composition technique for advanced building LoD2 reconstruction. This approach refines building 3D modeling in complex urban structures, particularly for challenging architectural forms. Our third study utilizes high-spatiotemporal resolution PlanetScope satellite imagery for (open full item for complete abstract)

Committee: Rongjun Qin (Advisor); Charles Toth (Committee Member); Alper Yilmaz (Committee Member) Subjects: Civil Engineering; Environmental Science; Geographic Information Science; Geography; Remote Sensing

MA, University of Cincinnati, 2023, Arts and Sciences: Geography

Drug abuse is an important issue in the United States. Marijuana is one of the most commonly used types of drugs, and the long-time use of marijuana can lead to health problems. But as the medical uses of marijuana have been discussed in recent studies, laws and attitudes toward marijuana in the United States have become more permissive. Some studies have explored the impact of the legalization of medical marijuana on people's attitudes toward drugs and drug-related criminal activities, but gaps remain in research, and the relationship between the legalization of medical marijuana and drug activities is still inconclusive. This study aims to analyze changes in the temporal and spatial distribution of drug activity at the micro research unit and test the impact of the legalization of medical marijuana on it. Three main research questions are explored: (1) Is there a change in the amount of drug activity before and after the legalization of medical marijuana? (2) Is there a change in the concentration of drug activity before and after the legalization of medical marijuana? (3) Is the effect of medical marijuana legalization on drug activity statistically significant, with the socio-economic factors and land-use factors controlled? Ohio became the 25th state in the U.S. to legalize medical marijuana on September 8, 2016. Cincinnati, Ohio is the chosen research area and call for service data collected by the emergency telephone service from 2013 to 2018 is used to count drug activities. Results indicate a significant decrease in drug activities since legalization. The number of street segments with drug activities also decreased, suggesting that drug activities became more concentrated. Medical marijuana legalization has likely had a significant effect on drug activity and it is possible that the legalization of medical marijuana has changed people's attitudes towards marijuana-related activities, which in turn affected the likelihood of reporting via 911 calls. The res (open full item for complete abstract)

Committee: Lin Liu Ph.D. (Committee Chair); Changjoo Kim Ph.D. (Committee Member); Jeffrey Brewer Ph.D. (Committee Member) Subjects: Geographic Information Science

Doctor of Philosophy, The Ohio State University, 2023, Environmental Science

Land cover changes refer to any modifications to the physical and biological components of an ecosystem and hence causing changes in its structure and functioning. Such changes encompass a range of magnitudes, from drastic changes such as urbanization and widespread deforestation, to subtle modifications such as forest disturbances, and even subtle shifts in the composition of crops and forest species. Land cover changes influence our climate system via two main pathways: the biogeochemical pathway (i.e., modifications to greenhouse gases), and the biophysical pathway (i.e., changes to land surface biophysics). However, analyzing the impact of land cover changes is challenging in part due to uncertainties of mapping the subtle changes, and also because a direct comparison between resultant biophysical and biogeochemical forcings is debatable as the effect of biophysical forcing is instant while the effect of biogeochemical forcing is long-lasting. The overarching goal of my research is to investigate the climate impact of subtle land cover changes and to build a framework that can compare biophysical impacts with corresponding biogeochemical impacts. To achieve this goal, three objectives are accomplished: (1) develop a multivariate model to better detect subtle land cover changes, (2) investigate the underlying biophysical mechanism regulating the post-change local climate, (3) incorporate the biophysical impact into the well-studied biogeochemical (carbon-centric) analyzing framework. Consistent findings following these objectives demonstrate that (1) the multivariate model we developed, which detects changes both in trends and seasonality, shows improved accuracy in detecting subtle land cover change (e.g., forest disturbance and following recoveries); (2) post-disturbance warming has been observed in all the climate zones except for the alpine tundra. Such warming is dominated by decreased-evapotranspiration-induced warming, even though offset by increased-a (open full item for complete abstract)

Committee: Kaiguang Zhao (Advisor); Yongyang Cai (Committee Member); Yanlan Liu (Committee Member); Gil Bohrer (Committee Member) Subjects: Climate Change; Environmental Economics; Environmental Science; Remote Sensing

Master of Arts in Psychology, Cleveland State University, 2021, College of Sciences and Health Professions

Attention is a complex process which entails selectively focusing on specific parts of one's environment. Previous work has indicated the differing ways in which attention is paid can alter performance on a task, with a more external focus of attention being associated with improved performance on tasks. Research into the time-series structure of movements has indicated a more internal, feedforward process will exhibit a pink-noise structure while a more external feedback process will exhibit a white-noise structure. Analogous results have been seen in the time-series structure of attentional resources. In the current research study, we aimed to examine the fluctuations in the time-series structure to examine attentional fluctuations. Participants were asked to perform a timing task by tapping the SPACE bar in time with the sound of the metronome. The timing task was either a synchronization timing task or a continuation timing task. The interstimulus-interval (ISI) also varied and had a short amount of time between beats at 500ms or had a large amount of time between beats at 2000ms. A two-way repeated-measures ANOVA was used to analyze the data. A statistically significant main effect for task condition was found. We expected to find a significant main effect for ISI as well as the ISI by task interaction, but found these factors were not significant. The continuation timing task exhibited a pink-noise time-series structure in both ISI levels. The synchronization timing task exhibited a whitening of time-series structure in both ISI levels. Our study aids in enhancing our understanding of differing attentional processes as well as timing processes. As well, our study expands our understanding of how attention fluctuates from a moment-to-moment basis.

Committee: Andrew Slifkin (Advisor); Conor McLennan (Committee Member); Eric Allard (Committee Member); Albert Smith (Committee Member) Subjects: Experimental Psychology

Doctor of Philosophy (PhD), Wright State University, 2021, Interdisciplinary Applied Science and Mathematics PhD

This dissertation includes two topics, Bickel-Rosenblatt test based on tilted density estimation for autoregressive models and deep merged survival analysis on cancer study using multiple types of bioinformatic data. In the first topic study, we consider the goodness of fit test the error density of linear and nonlinear autoregressive models using tilted kernel density estimation based on residuals. Bickel-Rosenblatt test statistic is based on the integrated square error of non-parametric error density estimation and a smoothed version of the parametric fit of the density. It is shown that the new type of Bickel-Rosenblatt test statistics behaves asymptotically the same as the one with conventional estimators based on true unobservable errors. We show technique details, simulation studies and real data analysis to present the performance of the new test statistic. The second topic is about deep survival analysis on cancer study. For cancer survival prediction, we propose to use deep merged survival networks with network layers at high levels merged together for better integration of information from multiple heterogeneous data sets to improve prediction accuracy. We conducted simulation studies to compare our proposed method with other methods in the literature under a range of scenarios. We conducted real data analysis based on breast cancer TCGA data to illustrates the advantage of our method over literature methods, and the advantage of using multiple data sets over using only one data set.

Committee: Shuxia Sun Ph.D. (Committee Co-Chair); Zheng Xu Ph.D. (Committee Co-Chair); Weizhen Wang Ph.D. (Committee Member); Yang Liu Ph.D. (Committee Member); Joseph Houpt Ph.D. (Committee Member) Subjects: Statistics

Master of Arts, University of Toledo, 2021, Geography

An Abstract of Comparison of LULC Change of Cities Sharing International Boundaries Using GIS and Remote Sensing (City of Detroit, USA Vs. City of Windsor, Canada) by S M Ahsanullah Submitted to the Graduate Faculty as partial fulfillment of the requirements for the Master of Arts Degree in Geography and Planning The University of Toledo August 2021 Urban land use and land cover (LULC) classification and change analysis has a cumulative effect on understanding the development of human civilization. The study of the world civilizations and development concentrates on explaining the socio-economic hearth of respective eras. Hence a deeper understanding of urban land use will allow us to learn more about how and where neighborhoods have formed. These neighborhoods indicate social clusters of people in a geographic location. Urban areas are established based on locations with resources to support development. Accurate change detection of land use/land cover (LULC) has become a key issue for monitoring local, regional, and global environments and resources. Which provides the foundation for a better understanding of relationships and interactions between humans and natural phenomena in order to improve management and use of resources (Aslami, et al., 2018) (Lu, et al., 2004). Today, 3.9 billion people (54 % of the world's population) reside in urban areas, and this figure is expected to reach 6.3 billion by 2050, with nearly 90 percent of future urban population increases in cities of developing countries (UN, 2015). In this context urban LULC analysis helps to show the spatial expansion of towns and cities. To accommodate growing urban populations effective planning is necessary to guide cities and develop new policies. There is no single reason behind land use change, it is rather an accumulation of a multiple factors working in place. New growth introduces either positive or negative changes, transforms old land use to a new one. Land use ch (open full item for complete abstract)

Committee: Dr. Bhuiyan Alam (Advisor); Dr. Yanqing Xu (Committee Member); Dr. Kevin Czajkowski (Committee Member) Subjects: Geographic Information Science; Geography; Land Use Planning; Remote Sensing

Doctor of Philosophy, University of Akron, 2020, Integrated Bioscience

Monitoring and maintaining freshwater resources are crucial for humans and animals; we simply would not be able to call Earth home without water flowing over its vast surface. Nevertheless, water resources are stressed by human activities all around the world. We pour pollution into rivers, streams, and lakes with both foreseeable and unforeseeable consequences. Monitoring and understanding the effects of these on water resources is an organized complex problem, where the whole is greater than the sum of the parts. Hence, a complete comprehension of various parts is needed in understanding the system. Addressing such a problem can be quite complicated and possibly fruitless. However, simplifying the challenge into small crucial compartments can help. To this end, we developed a monitoring system to predict pH and dissolved oxygen using classical time series and machine learning methods, as well as, developed tools to identify and track sources of pollutions in waterways. Our models showed classical time series analysis can give better estimate for our short-term predictions than more complicated machine learning models (chapter 2 and 3). Our tool showed it is possible to develop open source hardware and software to acquire accurate water monitoring data that can be used by citizen scientists (chapter 4).

Committee: Francisco Moore (Advisor); Hunter King (Advisor); Zhong-Hui Duan (Committee Member); Yingcai Xiao (Committee Member); John Huss (Committee Member); Christopher Miller (Committee Member) Subjects: Computer Science; Ecology

Doctor of Philosophy, Case Western Reserve University, 2020, EECS - System and Control Engineering

Commercial buildings account for around one third of the total electricity consumption in the United States, of which a significant amount is wasted. Heating Ventilation and Cooling (HVAC) systems are one of the largest components of the overall energy consumption in buildings and by improving the operational condition and efficiency of HVAC systems, significant savings can be achieved. Quantification of HVAC performance and characteristics is a critical step in the diagnostics, prognostics, and improvement of savings opportunities. Identifying savings through virtual energy audits using widely available smart-meter time-series data of the total energy consumption is an efficient and robust procedure that can be applied to a large number of buildings' datasets. In this study, we will develop a systematic, automated, and scalable pipeline for quantifying HVAC characteristics from the total energy consumption of smart-meter data to identify savings opportunities in commercial buildings and determine the critical affecting parameters. The automated pipeline layout will not only structure, clean, ingest, and interactively analyze the data, but also utilize the high performance computing cluster (HPC) and a smart job scheduler that we developed in addition to existing resources. Then, two main HVAC savings opportunities of rescheduling and baseload savings through setpoint setback will be quantified and discussed, and the results will be scaled to a statistically significant population of buildings across the US for comparative analysis. We will identify and discuss target buildings with the highest savings opportunities. Then, we will propose a data-driven method for setting back the setpoint of HVAC cooling by 1 degree increments on data and quantify the associated savings followed by a comparative study on the population and variable importance analysis, accordingly. As a result of the automated pipeline, 816 buildings' datasets across the United St (open full item for complete abstract)

Committee: Alexis Abramson (Advisor); Roger French (Advisor); Kenneth Loparo (Committee Chair); Anirban Mondal (Committee Member) Subjects: Comparative; Computer Science; Electrical Engineering; Energy; Engineering

Doctor of Philosophy, The Ohio State University, 2019, Economics

This dissertation consists of six papers. Each of these papers are on a different aspect of statistical analysis of nonlinear time series. In the first paper, we study the behavior of a nonstationary time series which has different behavior for ``high" and ``low" levels. This consists of the introduction of a new nonlinear time series model, a mathematical analysis of the functional limit theorem for this model, a statistical test for behavior similar to this new model, and a proposed technique for robust cointegration in the presence of this new model. The second paper consists of an extension of this idea into volatility modeling. The third paper considers experimental design and sampling of Markov chains. In particular, it focuses on how to feasibly optimally sample a continuous two-state Markov chain. The fourth paper is on integer valued time series. The focus here is on studying the properties of the INGARCH(1,1) model in the nonstationary case. This consists of applying mathematical machinery rarely used in econometrics. Additionally, in this paper extensions towards stationarity tests are considered. The fifth paper studies the dynamic Tobit, a time series model often used when data is censored below. In this paper, weak dependence and mixing properties are shown to hold, which is relevant for studying the statistical properties of estimation for this model. The sixth paper studies the reciprocal of the random walk. This is relevant in time series econometrics as such a process is a possible model for time series with a stochastic diminishing trend.

Committee: Robert de Jong (Advisor); Stephen Cosslett (Committee Member); Jason Blevins (Committee Member); Mehmet Caner (Committee Member) Subjects: Economics