While it is evident that network services continue to play an ever-increasing role in our daily lives, it is less evident that our information infrastructure requires a concerted, well-conceived, and fastidiously executed strategy to remain viable. Government agencies, Non-Governmental Organizations (\NGOs"), and private organizations are all targets for malicious online activity. Security has deservedly become a serious focus for organizations that seek to assume a more proactive posture; in order to deal with the many facets of securing their infrastructure. At the same time, the discipline of data science has rapidly grown into a prominent role, as once purely theoretical machine learning algorithms have become practical for implementation. This is especially noteworthy, as principles that now fall neatly into the field of data science has been contemplated for quite some time, and as much as over two hundred years ago. Visionaries like Thomas Bayes [18], Andrey Andreyevich Markov [65], Frank Rosenblatt [88], and so many others made incredible contributions to the field long before the impact of Moore's law [92] would make such theoretical work commonplace for practical use; giving rise to what has come to be known as "Data Science". / Includes bibliography. / Dissertation (Ph.D.)--Florida Atlantic University, 2020. / FAU Electronic Theses and Dissertations Collection

In recent years, increasing availability of data and advances in predictive analytics present new opportunities and challenges to healthcare management. Predictive models are developed to evaluate various aspects of healthcare systems, such as patient demand, patient pathways, and patient outcomes. While these predictions potentially provide valuable information to improve healthcare delivery, there are still many open questions considering how to integrate these forecasts into operational decisions. In this context, this dissertation develops methodologies to combine predictive analytics with the design of healthcare delivery systems. The first part of dissertation considers how to schedule proactive care in the presence of patient deterioration. Healthcare systems are typically limited resource environments where scarce capacity is reserved for the most urgent patients. However, there has been a growing interest in the use of proactive care when a less urgent patient is predicted to become urgent while waiting. On one hand, providing care for patients when they are less critical could mean that fewer resources are needed to fulfill their treatment requirement. On the other hand, due to prediction errors, the moderate patients who are predicted to deteriorate in the future may self cure on their own and never need the treatment. Hence, allocating limited resource for these patients takes the capacity away from other more urgent ones who need it now. To understand this tension, we propose a multi-server queueing model with two patient classes: moderate and urgent. We allow patients to transition classes while waiting. In this setting, we characterize how moderate and urgent patients should be prioritized for treatment when proactive care for moderate patients is an option. The second part of the dissertation focuses on the nurse staffing decisions in the emergency departments (ED). Optimizing ED nurse staffing decisions to balance the quality of service and staffing cost can be extremely challenging, especially when there is a high level of uncertainty in patient demand. Increasing data availability and continuing advancements in predictive analytics provide an opportunity to mitigate demand uncertainty by utilizing demand forecasts. In the second part of the dissertation, we study a two-stage prediction-driven staffing framework where the prediction models are integrated with the base (made weeks in advance) and surge (made nearly real-time) staffing decisions in the ED. We quantify the benefit of having the ability to use the more expensive surge staffing. We also propose a near-optimal two-stage staffing policy that is straightforward to interpret and implement. Lastly, we develop a unified framework that combines parameter estimation, real-time demand forecasts, and capacity sizing in the ED. High-fidelity simulation experiments for the ED demonstrate that the proposed framework can reduce annual staffing costs by 11%-16% ($2 M-$3 M) while guaranteeing timely access to care.

Some local health organizations in Ontario (e.g., Local Health Integration Network or LHINs) have put forward a strategic objective to identify patients with preventable high cost healthcare service usage (e.g., hospitalizations, emergency department [ED] visits). To attain this goal, primary care service providers, who are considered the entry point to the health system, need tools to help diagnose, treat and refer those patients identified as being potential high users of the health care system. The goal of this study was to develop a management and referral tool to identify, manage and refer patients living with multiple comorbidities to specialized care teams such as Health Links. Data used in this analysis were obtained from the Canadian Primary Care Sentinel Surveillance Network (CPCSSN) primary care data holdings. The dataset created for this study contained 14,004 patient records. Data analysis techniques included use of both statistical and predictive analytic tools. The base models included four data mining classification algorithms: Decision Tree, Naïve Bayes, Neural Network and Clustering. The predictive modeling approach was complemented by an association analysis. The one-way ANOVA analysis indicated that age and health status (number of conditions, and individual medical conditions) identified statistically significant differences in patient utilization of health services. Results from the predictive analytics showed that patient age and patient medical conditions, as well as number of medical conditions for each patient (5 or more) could be used as criteria to develop tools (e.g. searches, reminders). Specifically, Parkinson disease, dementia and epilepsy were found to be important predictors (i.e. most frequently associated with) the top 4 most prevalent conditions (hypertension, osteoarthritis, depression and diabetes) within the population of the study. The association analysis also revealed that chronic obstructive pulmonary disease (COPD) was closely associated with the top 4 most prevalent conditions. Based on the findings of this study, Parkinson Disease, dementia, epilepsy and COPD can be used to identify patients with complex medical needs who are likely to be high users of the healthcare system and to be considered for early, personalized intervention. / Thesis / Master of Health Sciences (MSc)

Recent advancements in sensing technologies offer new opportunities for quality improvement and assurance in manufacturing and service systems. The sensor advances provide a vast amount of data, accommodating quality improvement decisions such as fault diagnosis (root cause analysis), and real-time process monitoring. These quality improvement decisions are typically made based on the predictive analysis of the sensor data, so called sensor-based predictive analytics. Sensor-based predictive analytics encompasses a variety of statistical, machine learning, and data mining techniques to identify patterns between the sensor data and historical facts. Given these patterns, predictions are made about the quality state of the process, and corrective actions are taken accordingly. Although the recent advances in sensing technologies have facilitated the quality improvement decisions, they typically result in high dimensional sensor data, making the use of sensor-based predictive analytics challenging due to their inherently intensive computation. This research begins in Chapter 1 by raising an interesting question, whether all these sensor data are required for making effective quality improvement decisions, and if not, is there any way to systematically reduce the number of sensors without affecting the performance of the predictive analytics? Chapter 2 attempts to address this question by reviewing the related research in the area of signal processing, namely, compressive sensing (CS), which is a novel sampling paradigm as opposed to the traditional sampling strategy following the Shannon Nyquist rate. By CS theory, a signal can be reconstructed from a reduced number of samples, hence, this motivates developing CS based approaches to facilitate predictive analytics using a reduced number of sensors. The proposed research methodology in this dissertation encompasses CS approaches developed to deliver the following two major contributions, (1) CS sensing to reduce the number of sensors while capturing the most relevant information, and (2) CS predictive analytics to conduct predictive analysis on the reduced number of sensor data. The proposed methodology has a generic framework which can be utilized for numerous real-world applications. However, for the sake of brevity, the validity of the proposed methodology has been verified with real sensor data associated with multi-station assembly processes (Chapters 3 and 4), additive manufacturing (Chapter 5), and wearable sensing systems (Chapter 6). Chapter 7 summarizes the contribution of the research and expresses the potential future research directions with applications to big data analytics. / Ph. D.

The depleting fossil fuel and environmental concerns have created a revolutionary movement towards the installation and utilization of Renewable Energy Sources (RES) such as wind and solar energy. The RES entails challenges, both in regards to the physical integration into a grid system and regarding management of the expected demand. The flexibility in energy demand can facilitate the alignment of the supply and demand to achieve a dynamic Demand Response (DR). The flexibility is often not explicitly available or provided by a user and has to be analyzed and extracted automatically from historical consumption data. The predictive analytics of consumption data can reveal interesting patterns and periodicities that facilitate the effective extraction and representation of flexibility. The device-level analysis captures the atomic flexibilities in energy demand and provides the largest possible solution space to generate demand/supply schedules. The presence of stochasticity and noise in the device-level consumption data and the unavailability of contextual information makes the analytics task challenging. Hence, it is essential to design predictive analytical techniques that work at an atomic data granularity and perform various analyses on the effectiveness of the proposed techniques. The Ph.D. study is sponsored by the TotalFlex Project (http://www.totalflex.dk/) and is part of the IT4BI-DC program with Aalborg University and TU Dresden as Home and Host University, respectively. The main objective of the TotalFlex project is to develop a cost-effective, market-based system that utilizes total flexibility in energy demand, and provide financial and environmental benefits to all involved parties. The flexibilities from various devices are modeled using a unified format called a flex-offer, which facilitates, e.g., aggregation and trading in the energy market. In this regards, this Ph.D. study focuses on the predictive analytics of the historical device operation behavior of consumers for an efficient and effective extraction of flexibilities in their energy demands. First, the thesis performs a comprehensive survey of state-of-the-art work in the literature. It presents a critical review and analysis of various previously proposed approaches, algorithms, and methods in the field of user behavior analysis, forecasting, and flexibility analysis. Then, the thesis details the flexibility and flex-offer concepts and formally discusses the terminologies used throughout the thesis. Second, the thesis contributes to a comprehensive analysis of energy consumption behavior at the device-level. The key motive of the analysis is to extract device operation patterns of users, the correlation between devices operations, and influence of external factors in device-level demands. A novel cost/benefit trade-off analysis of device flexibility is performed to categorize devices into various segments according to their flexibility potential. Moreover, device-specific data preprocessing steps are proposed to clean device-level raw data into a format suitable for flexibility analysis. Third, the thesis presents various prediction models that are specifically tuned for device-level energy demand prediction. Further, it contributes to the feature engineering aspect of generating additional features from a demand consumption timeseries that effectively capture device operation preferences and patterns. The demand predictions utilize the carefully crafted features and other contextual information to improve the performance of the prediction models. Further, various demand prediction models are evaluated to determine the model, forecast horizon, and data granularity best suited for the device-level flexibility analysis. Furthermore, the effect of the forecast accuracy on flexibility-based DR is evaluated to identify an error level a market can absorb maintaining profitability. Fourth, the thesis proposes a generalized process for automated generation and evaluation of flex-offers from the three types of household devices, namely Wet-devices, Electric Vehicles (EV), and Heat Pumps. The proposed process automatically predicts and estimates times and values of device-specific events representing flexibility in its operations. The predicted events are combined to generate flex-offers for the device future operations. Moreover, the actual flexibility potential of household devices is quantified for various contextual conditions and degree days. Fifth, the thesis presents user-comfort oriented prescriptive techniques to prescribe flex-offers schedules. The proposed scheduler considers the trade-off between both social and financial aspects during scheduling of flex-offers, i.e., maximizing the financial benefits in a market and at the same time minimizing the loss of user comfort. Moreover, it also provides a distance-aware error measure that quantifies the actual performance of forecast models designed for flex-offers generation and scheduling. Sixth, the thesis contributes to the comprehensive analysis of the financial viability of device-level flexibility for dynamic balancing of demand and supply. The thesis quantifies the financial benefits of flexibility and investigates the device type specific market that maximizes the potential of flexibility, both regarding DR and financial incentives. Henceforth, a financial analysis of each proposed technique, namely forecast model, flex-offer generation model, and flex-offer scheduling is performed. The key motive is to evaluate the usability of the proposed models in the device-level flexibility based DR scheme and their potential in generating a positive financial incentive to markets and customers. Seven, the thesis presents a benchmark platform for device-level demand prediction. The platform provides the research community with a centralized repository of device-level datasets, forecast models, and functionalities that facilitate comparisons, evaluations, and validation of device-level forecast models. The results of the thesis can contribute to the energy market in materializing the vision of utilizing consumption and production flexibility to obtain dynamic energy balance. The developed demand forecast and flex-offer generation models also contribute to the energy data analytics and data mining fields. The quantification of flexibility further contributes by demonstrating the feasibility and financial benefits of flexibility-based DR. The developed experimental platform provide researchers and practitioners with the resources required for device-level demand analytics and prediction.

The depleting fossil fuel and environmental concerns have created a revolutionary movement towards the installation and utilization of Renewable Energy Sources (RES) such as wind and solar energy. The RES entails challenges, both in regards to the physical integration into a grid system and regarding management of the expected demand. The flexibility in energy demand can facilitate the alignment of the supply and demand to achieve a dynamic Demand Response (DR). The flexibility is often not explicitly available or provided by a user and has to be analyzed and extracted automatically from historical consumption data. The predictive analytics of consumption data can reveal interesting patterns and periodicities that facilitate the effective extraction and representation of flexibility. The device-level analysis captures the atomic flexibilities in energy demand and provides the largest possible solution space to generate demand/supply schedules. The presence of stochasticity and noise in the device-level consumption data and the unavailability of contextual information makes the analytics task challenging. Hence, it is essential to design predictive analytical techniques that work at an atomic data granularity and perform various analyses on the effectiveness of the proposed techniques. The Ph.D. study is sponsored by the TotalFlex Project (http://www.totalflex.dk/) and is part of the IT4BI-DC program with Aalborg University and TU Dresden as Home and Host University, respectively. The main objective of the TotalFlex project is to develop a cost-effective, market-based system that utilizes total flexibility in energy demand, and provide financial and environmental benefits to all involved parties. The flexibilities from various devices are modeled using a unified format called a flex-offer, which facilitates, e.g., aggregation and trading in the energy market. In this regards, this Ph.D. study focuses on the predictive analytics of the historical device operation behavior of consumers for an efficient and effective extraction of flexibilities in their energy demands. First, the thesis performs a comprehensive survey of state-of-the-art work in the literature. It presents a critical review and analysis of various previously proposed approaches, algorithms, and methods in the field of user behavior analysis, forecasting, and flexibility analysis. Then, the thesis details the flexibility and flex-offer concepts and formally discusses the terminologies used throughout the thesis. Second, the thesis contributes to a comprehensive analysis of energy consumption behavior at the device-level. The key motive of the analysis is to extract device operation patterns of users, the correlation between devices operations, and influence of external factors in device-level demands. A novel cost/benefit trade-off analysis of device flexibility is performed to categorize devices into various segments according to their flexibility potential. Moreover, device-specific data preprocessing steps are proposed to clean device-level raw data into a format suitable for flexibility analysis. Third, the thesis presents various prediction models that are specifically tuned for device-level energy demand prediction. Further, it contributes to the feature engineering aspect of generating additional features from a demand consumption timeseries that effectively capture device operation preferences and patterns. The demand predictions utilize the carefully crafted features and other contextual information to improve the performance of the prediction models. Further, various demand prediction models are evaluated to determine the model, forecast horizon, and data granularity best suited for the device-level flexibility analysis. Furthermore, the effect of the forecast accuracy on flexibility-based DR is evaluated to identify an error level a market can absorb maintaining profitability. Fourth, the thesis proposes a generalized process for automated generation and evaluation of flex-offers from the three types of household devices, namely Wet-devices, Electric Vehicles (EV), and Heat Pumps. The proposed process automatically predicts and estimates times and values of device-specific events representing flexibility in its operations. The predicted events are combined to generate flex-offers for the device future operations. Moreover, the actual flexibility potential of household devices is quantified for various contextual conditions and degree days. Fifth, the thesis presents user-comfort oriented prescriptive techniques to prescribe flex-offers schedules. The proposed scheduler considers the trade-off between both social and financial aspects during scheduling of flex-offers, i.e., maximizing the financial benefits in a market and at the same time minimizing the loss of user comfort. Moreover, it also provides a distance-aware error measure that quantifies the actual performance of forecast models designed for flex-offers generation and scheduling. Sixth, the thesis contributes to the comprehensive analysis of the financial viability of device-level flexibility for dynamic balancing of demand and supply. The thesis quantifies the financial benefits of flexibility and investigates the device type specific market that maximizes the potential of flexibility, both regarding DR and financial incentives. Henceforth, a financial analysis of each proposed technique, namely forecast model, flex-offer generation model, and flex-offer scheduling is performed. The key motive is to evaluate the usability of the proposed models in the device-level flexibility based DR scheme and their potential in generating a positive financial incentive to markets and customers. Seven, the thesis presents a benchmark platform for device-level demand prediction. The platform provides the research community with a centralized repository of device-level datasets, forecast models, and functionalities that facilitate comparisons, evaluations, and validation of device-level forecast models. The results of the thesis can contribute to the energy market in materializing the vision of utilizing consumption and production flexibility to obtain dynamic energy balance. The developed demand forecast and flex-offer generation models also contribute to the energy data analytics and data mining fields. The quantification of flexibility further contributes by demonstrating the feasibility and financial benefits of flexibility-based DR. The developed experimental platform provide researchers and practitioners with the resources required for device-level demand analytics and prediction.

abstract: Due to the growing popularity of the Internet and smart mobile devices, massive data has been produced every day, particularly, more and more users’ online behavior and activities have been digitalized. Making a better usage of the massive data and a better understanding of the user behavior become at the very heart of industrial firms as well as the academia. However, due to the large size and unstructured format of user behavioral data, as well as the heterogeneous nature of individuals, it leveled up the difficulty to identify the SPECIFIC behavior that researchers are looking at, HOW to distinguish, and WHAT is resulting from the behavior. The difference in user behavior comes from different causes; in my dissertation, I am studying three circumstances of behavior that potentially bring in turbulent or detrimental effects, from precursory culture to preparatory strategy and delusory fraudulence. Meanwhile, I have access to the versatile toolkit of analysis: econometrics, quasi-experiment, together with machine learning techniques such as text mining, sentiment analysis, and predictive analytics etc. This study creatively leverages the power of the combined methodologies, and apply it beyond individual level data and network data. This dissertation makes a first step to discover user behavior in the newly boosting contexts. My study conceptualize theoretically and test empirically the effect of cultural values on rating and I find that an individualist cultural background are more likely to lead to deviation and more expression in review behaviors. I also find evidence of strategic behavior that users tend to leverage the reporting to increase the likelihood to maximize the benefits. Moreover, it proposes the features that moderate the preparation behavior. Finally, it introduces a unified and scalable framework for delusory behavior detection that meets the current needs to fully utilize multiple data sources. / Dissertation/Thesis / Doctoral Dissertation Business Administration 2019

abstract: Predictive analytics embraces an extensive area of techniques from statistical modeling to machine learning to data mining and is applied in business intelligence, public health, disaster management and response, and many other fields. To date, visualization has been broadly used to support tasks in the predictive analytics pipeline under the underlying assumption that a human-in-the-loop can aid the analysis by integrating domain knowledge that might not be broadly captured by the system. Primary uses of visualization in the predictive analytics pipeline have focused on data cleaning, exploratory analysis, and diagnostics. More recently, numerous visual analytics systems for feature selection, incremental learning, and various prediction tasks have been proposed to support the growing use of complex models, agent-specific optimization, and comprehensive model comparison and result exploration. Such work is being driven by advances in interactive machine learning and the desire of end-users to understand and engage with the modeling process. However, despite the numerous and promising applications of visual analytics to predictive analytics tasks, work to assess the effectiveness of predictive visual analytics is lacking. This thesis studies the current methodologies in predictive visual analytics. It first defines the scope of predictive analytics and presents a predictive visual analytics (PVA) pipeline. Following the proposed pipeline, a predictive visual analytics framework is developed to be used to explore under what circumstances a human-in-the-loop prediction process is most effective. This framework combines sentiment analysis, feature selection mechanisms, similarity comparisons and model cross-validation through a variety of interactive visualizations to support analysts in model building and prediction. To test the proposed framework, an instantiation for movie box-office prediction is developed and evaluated. Results from small-scale user studies are presented and discussed, and a generalized user study is carried out to assess the role of predictive visual analytics under a movie box-office prediction scenario. / Dissertation/Thesis / Doctoral Dissertation Engineering 2017

Clinical intelligence about a patient's risk of future adverse health events can support clinical decision making in personalized and preventive care. Healthcare predictive analytics using electronic health records offers a promising direction to address the challenging tasks of risk profiling. Patients with chronic diseases often face risks of not just one, but an array of adverse health events. However, existing risk models typically focus on one specific event and do not predict multiple outcomes. To attain enhanced risk profiling, we adopt the design science paradigm and propose a principled approach called Bayesian multitask learning (BMTL). Considering the model development for an event as a single task, our BMTL approach is to coordinate a set of baseline models-one for each event-and communicate training information across the models. The BMTL approach allows healthcare providers to achieve multifaceted risk profiling and model an arbitrary number of events simultaneously. Our experimental evaluations demonstrate that the BMTL approach attains an improved predictive performance when compared with the alternatives that model multiple events separately. We also find that, in most cases, the BMTL approach significantly outperforms existing multitask learning techniques. More importantly, our analysis shows that the BMTL approach can create significant potential impacts on clinical practice in reducing the failures and delays in preventive interventions. We discuss several implications of this study for health IT, big data and predictive analytics, and design science research.

<p>Esports have been a growing market segment for recreation and competition. Few works of research examine the decisions that competitors need to make to maximize the probability of winning. Game theory Nash equilibriums are used to evaluate options available for players to select out of game decisions related to side selection, character selection, and stage selection. Backward induction techniques are used to solve these subgame decisions. The introduction of a rating system for players is derived from traditional sport statistics. The primary factor tracked in damage dealt and damage received using the same framework from sabermetrics was used to predict outcomes of baseball games. Conclusions demonstrated tracking damage can be used to predict the outcome of a match. Other techniques such as principal component analysis did not provide adequate data to measure individual metrics for the use of predictive application.</p>