Predictive Analytics and Decision Support for Heart Failure patients

Thesis (Master's)--University of Washington, 2016-08

Liquid Business Process Model Collections

Many organizations realize that increasing amounts of data (“Big Data”) need to be dealt with intelligently in order to compete with other organizations in terms of efficiency, speed and services. The goal is not to collect as much data as possible, but to turn event data into valuable insights that can be used to improve business processes. However, data-oriented analysis approaches fail to relate event data to process models. At the same time, large organizations are generating piles of process models that are disconnected from the real processes and information systems. In this chapter we propose to manage large collections of process models and event data in an integrated manner. Observed and modeled behavior need to be continuously compared and aligned. This results in a “liquid” business process model collection, i.e. a collection of process models that is in sync with the actual organizational behavior. The collection should self-adapt to evolving organizational behavior and incorporate relevant execution data (e.g. process performance and resource utilization) extracted from the logs, thereby allowing insightful reports to be produced from factual organizational data.

The case for “n«all”: Why the Big Data revolution will probably happen differently in the mining sector

Big Data and predictive analytics have received significant attention from the media and academic literature throughout the past few years, and it is likely that these emerging technologies will materially impact the mining sector. This short communication argues, however, that these technological forces will probably unfold differently in the mining industry than they have in many other sectors because of significant differences in the marginal cost of data capture and storage. To this end, we offer a brief overview of what Big Data and predictive analytics are, and explain how they are bringing about changes in a broad range of sectors. We discuss the “N=all” approach to data collection being promoted by many consultants and technology vendors in the marketplace but, by considering the economic and technical realities of data acquisition and storage, we then explain why a “n « all” data collection strategy probably makes more sense for the mining sector. Finally, towards shaping the industry’s policies with regards to technology-related investments in this area, we conclude by putting forward a conceptual model for leveraging Big Data tools and analytical techniques that is a more appropriate fit for the mining sector.

Progettazione e implementazione di un’applicazione per il monitoraggio e la manutenzione predittiva di sistemi

Le macchine impiegate nei processi di produzione industriale sono soggette a usura e destinate a esibire malfunzionamenti qualora non venga attuata un'attenta opera di manutenzione preventiva. In questa tesi è proposta una proof of concept relativa alla manutenzione predittiva la quale, analizzando i segnali trasmessi dai sensori installati sulla macchina, mira a segnalare in tempo utile i guasti futuri, onde consentire l'attività manutentiva prima che si verifichi il guasto.

Frequencies and risk factors for bisphosphonate-related osteonecrosis of the jaw in cancer patients: A matched case-control study

Bisphosphonates represent a unique class of drugs that effectively treat and prevent a variety of bone-related disorders including metastatic bone disease and osteoporosis. High tolerance and high efficacy rates quickly ranked bisphosphonates as the standard of care for bone-related diseases. However, in the early 2000s, case reports began to surface that linked bisphosphonates with osteonecrosis of the jaw (ONJ). Since that time, studies conducted have corroborated the linkage. However, as with most disease states, many factors can contribute to the onset of disease. The aim of this study was to determine which comorbid factors presented an increased risk for developing ONJ in cancer patients.^ Using a case-control study design, investigators used a combination of ICD-9 codes and chart review to identify confirmed cases of ONJ at The University of Texas M. D. Anderson Cancer Center (MDACC). Each case was then matched to five controls based on age, gender, race/ethnicity, and primary cancer diagnosis. Data querying and chart review provided information on variables of interest. These variables included bisphosphonate exposure, glucocorticoids exposure, smoking history, obesity, and diabetes. Statistical analysis was conducted using PASW (Predictive Analytics Software) Statistics, Version 18 (SPSS Inc., Chicago, Illinois).^ One hundred twelve (112) cases were identified as confirmed cases of ONJ. Variables were run using univariate logistic regression to determine significance (p < .05); significant variables were included in the final conditional logistic regression model. Concurrent use of bisphosphonates and glucocorticoids (OR, 18.60; CI, 8.85 to 39.12; p < .001), current smokers (OR, 2.52; CI, 1.21 to 5.25; p = .014), and presence of diabetes (OR, 1.84; CI, 1.06 to 3.20; p = .030) were found to increase the risk for developing ONJ. Obesity was not associated significantly with ONJ development.^ In this study, cancer patients that received bisphosphonates as part of their therapeutic regimen were found to have an 18-fold increase in their risk of developing ONJ. Other factors included smoking and diabetes. More studies examining the concurrent use of glucocorticoids and bisphosphonates may be able to strengthen any correlations.^

Dynamic Programming Approaches for Estimating and Applying Large-scale Discrete Choice Models

People go through their life making all kinds of decisions, and some of these decisions affect their demand for transportation, for example, their choices of where to live and where to work, how and when to travel and which route to take. Transport related choices are typically time dependent and characterized by large number of alternatives that can be spatially correlated. This thesis deals with models that can be used to analyze and predict discrete choices in large-scale networks. The proposed models and methods are highly relevant for, but not limited to, transport applications. We model decisions as sequences of choices within the dynamic discrete choice framework, also known as parametric Markov decision processes. Such models are known to be difficult to estimate and to apply to make predictions because dynamic programming problems need to be solved in order to compute choice probabilities. In this thesis we show that it is possible to explore the network structure and the flexibility of dynamic programming so that the dynamic discrete choice modeling approach is not only useful to model time dependent choices, but also makes it easier to model large-scale static choices. The thesis consists of seven articles containing a number of models and methods for estimating, applying and testing large-scale discrete choice models. In the following we group the contributions under three themes: route choice modeling, large-scale multivariate extreme value (MEV) model estimation and nonlinear optimization algorithms. Five articles are related to route choice modeling. We propose different dynamic discrete choice models that allow paths to be correlated based on the MEV and mixed logit models. The resulting route choice models become expensive to estimate and we deal with this challenge by proposing innovative methods that allow to reduce the estimation cost. For example, we propose a decomposition method that not only opens up for possibility of mixing, but also speeds up the estimation for simple logit models, which has implications also for traffic simulation. Moreover, we compare the utility maximization and regret minimization decision rules, and we propose a misspecification test for logit-based route choice models. The second theme is related to the estimation of static discrete choice models with large choice sets. We establish that a class of MEV models can be reformulated as dynamic discrete choice models on the networks of correlation structures. These dynamic models can then be estimated quickly using dynamic programming techniques and an efficient nonlinear optimization algorithm. Finally, the third theme focuses on structured quasi-Newton techniques for estimating discrete choice models by maximum likelihood. We examine and adapt switching methods that can be easily integrated into usual optimization algorithms (line search and trust region) to accelerate the estimation process. The proposed dynamic discrete choice models and estimation methods can be used in various discrete choice applications. In the area of big data analytics, models that can deal with large choice sets and sequential choices are important. Our research can therefore be of interest in various demand analysis applications (predictive analytics) or can be integrated with optimization models (prescriptive analytics). Furthermore, our studies indicate the potential of dynamic programming techniques in this context, even for static models, which opens up a variety of future research directions.

Open Space – Estratégia e Concretização: o caso EDP Porto

Este estudo centra-se numa investigação sobre o conceito de trabalho em open space na nova sede no Porto da empresa Energias de Portugal - SA, tendo em conta a estratégia implementada e os resultados conseguidos. Para isso, dissecámos as premissas apresentadas aos trabalhadores na cerimónia de inauguração do novo espaço - “O Open Space opera como plataforma de comunicação e de partilha de informação” e “O Open Space responde às necessidades dos trabalhadores, criando ambientes de trabalho modernos e funcionais”. A fim de avaliarmos o campo empírico, construímos e enviámos em formato eletrónico para o e-mail de todos os trabalhadores da amostra um instrumento de medida que denominámos de open space (OS). As ilações retiradas estão baseadas nos resultados analisados e discutidos após processamento em SPSS - predictive analytics software and solutions e em reports gráficos. O open space da EDP Porto é um local moderno e funcional, privilegiado em relação à fluidez e partilha de informação, capaz de manifestar estratégias de negócio e de salientar aspetos da marca e da cultura da Empresa. A formação/informação sobre comportamentos e regras básicas a seguir na partilha de um mesmo espaço, as razões de negócio que levam a organização a mudar o espaço de trabalho, a par das vantagens que ambas as partes podem tirar do novo conceito, influencia positivamente ou negativamente a perceção da mudança e o estado emocional dos trabalhadores. O ruído, a temperatura ambiente, a concentração ou a privacidade, são alguns dos fatores que poderão variar com o layout e funcionam como condicionantes de uma maior ou menor satisfação ambiental. No entanto, existem sempre questões que permanecem pendentes e foi nesse contexto que deixámos algumas propostas para novas investigações num trabalho científico que nunca se esgota. / This study focuses on researching the concept of working in an open space in the new Oporto’s headquarters of the company Energias de Portugal - SA, given the strategy implemented and the results achieved. For this, we dissected the assumptions presented to workers at the inauguration ceremony of the new space - "The Open Space operates as a platform for communication and information sharing" and "The Open Space responds to the needs of workers, creating modern and functional workplaces". In order to evaluate the empirical side, we built and sent, in electronic format, an e-mail to all the workers of the sample with a measurement tool that we called the open space (OS). The conclusions are based on the results analyzed and discussed after being processed in SPSS - predictive analytics software and solutions and graphs in reports. The open space of the EDP Oporto is a modern and functional place, privileged in relation to fluidity and information sharing, capable of manifesting business strategies and highlight aspects of the brand and culture of the Company. The training/information on behaviors and basic rules to follow when sharing the same space, the business reasons that lead the organization to change the workspace, along with the advantages that both parties can benefit from the new concept, influence positively or negatively the perception of change and the emotional state of workers. Noise, temperature, concentration or privacy, are some of the factors that may vary with the layout and function as constraints in a greater or lesser environmental satisfaction. However, there are always issues that remain outstanding and it was in this context that we made some proposals for further research in a scientific paper that never runs out.

Dynamic Programming Approaches for Estimating and Applying Large-scale Discrete Choice Models

People go through their life making all kinds of decisions, and some of these decisions affect their demand for transportation, for example, their choices of where to live and where to work, how and when to travel and which route to take. Transport related choices are typically time dependent and characterized by large number of alternatives that can be spatially correlated. This thesis deals with models that can be used to analyze and predict discrete choices in large-scale networks. The proposed models and methods are highly relevant for, but not limited to, transport applications. We model decisions as sequences of choices within the dynamic discrete choice framework, also known as parametric Markov decision processes. Such models are known to be difficult to estimate and to apply to make predictions because dynamic programming problems need to be solved in order to compute choice probabilities. In this thesis we show that it is possible to explore the network structure and the flexibility of dynamic programming so that the dynamic discrete choice modeling approach is not only useful to model time dependent choices, but also makes it easier to model large-scale static choices. The thesis consists of seven articles containing a number of models and methods for estimating, applying and testing large-scale discrete choice models. In the following we group the contributions under three themes: route choice modeling, large-scale multivariate extreme value (MEV) model estimation and nonlinear optimization algorithms. Five articles are related to route choice modeling. We propose different dynamic discrete choice models that allow paths to be correlated based on the MEV and mixed logit models. The resulting route choice models become expensive to estimate and we deal with this challenge by proposing innovative methods that allow to reduce the estimation cost. For example, we propose a decomposition method that not only opens up for possibility of mixing, but also speeds up the estimation for simple logit models, which has implications also for traffic simulation. Moreover, we compare the utility maximization and regret minimization decision rules, and we propose a misspecification test for logit-based route choice models. The second theme is related to the estimation of static discrete choice models with large choice sets. We establish that a class of MEV models can be reformulated as dynamic discrete choice models on the networks of correlation structures. These dynamic models can then be estimated quickly using dynamic programming techniques and an efficient nonlinear optimization algorithm. Finally, the third theme focuses on structured quasi-Newton techniques for estimating discrete choice models by maximum likelihood. We examine and adapt switching methods that can be easily integrated into usual optimization algorithms (line search and trust region) to accelerate the estimation process. The proposed dynamic discrete choice models and estimation methods can be used in various discrete choice applications. In the area of big data analytics, models that can deal with large choice sets and sequential choices are important. Our research can therefore be of interest in various demand analysis applications (predictive analytics) or can be integrated with optimization models (prescriptive analytics). Furthermore, our studies indicate the potential of dynamic programming techniques in this context, even for static models, which opens up a variety of future research directions.

The application of learning analytics to improve learning: Questions from the academy

Since 2007, close collaboration between the Learning and Teaching Unit’s Academic Quality and Standards team and the Department of Reporting and Analysis’ Business Objects team resulted in a generational approach to reporting where QUT established a place of trust. This place of trust is where data owners are confident in date storage, data integrity, reported and shared. While the role of the Department of Reporting and Analysis focused on the data warehouse, data security and publication of reports, the Academic Quality and Standards team focused on the application of learning analytics to solve academic research questions and improve student learning. Addressing questions such as: • Are all students who leave course ABC academically challenged? • Do the students who leave course XYZ stay within the faculty, university or leave? • When students withdraw from a unit do they stay enrolled on full or part load or leave? • If students enter through a particular pathway, what is their experience in comparison to other pathways? • With five years historic reporting, can a two-year predictive forecast provide any insight? In answering these questions, the Academic Quality and Standards team then developed prototype data visualisation through curriculum conversations with academic staff. Where these enquiries were applicable more broadly this information would be brought into the standardised reporting for the benefit of the whole institution. At QUT an annual report to the executive committees allows all stakeholders to record the performance and outcomes of all courses in a snapshot in time or use this live report at any point during the year. This approach to learning analytics was awarded the Awarded 2014 ATEM/Campus Review Best Practice Awards in Tertiary Education Management for The Unipromo Award for Excellence in Information Technology Management.

Prediction and Privacy in Healthcare Analytics

Thesis (Master's)--University of Washington, 2016-03

Hierarchical Prediction Machines and Big Data Analytics

An emerging consensus in cognitive science views the biological brain as a hierarchically-organized predictive processing system. This is a system in which higher-order regions are continuously attempting to predict the activity of lower-order regions at a variety of (increasingly abstract) spatial and temporal scales. The brain is thus revealed as a hierarchical prediction machine that is constantly engaged in the effort to predict the flow of information originating from the sensory surfaces. Such a view seems to afford a great deal of explanatory leverage when it comes to a broad swathe of seemingly disparate psychological phenomena (e.g., learning, memory, perception, action, emotion, planning, reason, imagination, and conscious experience). In the most positive case, the predictive processing story seems to provide our first glimpse at what a unified (computationally-tractable and neurobiological plausible) account of human psychology might look like. This obviously marks out one reason why such models should be the focus of current empirical and theoretical attention. Another reason, however, is rooted in the potential of such models to advance the current state-of-the-art in machine intelligence and machine learning. Interestingly, the vision of the brain as a hierarchical prediction machine is one that establishes contact with work that goes under the heading of 'deep learning'. Deep learning systems thus often attempt to make use of predictive processing schemes and (increasingly abstract) generative models as a means of supporting the analysis of large data sets. But are such computational systems sufficient (by themselves) to provide a route to general human-level analytic capabilities? I will argue that they are not and that closer attention to a broader range of forces and factors (many of which are not confined to the neural realm) may be required to understand what it is that gives human cognition its distinctive (and largely unique) flavour. The vision that emerges is one of 'homomimetic deep learning systems', systems that situate a hierarchically-organized predictive processing core within a larger nexus of developmental, behavioural, symbolic, technological and social influences. Relative to that vision, I suggest that we should see the Web as a form of 'cognitive ecology', one that is as much involved with the transformation of machine intelligence as it is with the progressive reshaping of our own cognitive capabilities.

Optimized Water Demand Management Through Intelligent Sensing And Analytics: The WISDOM Approach

New business and technology platforms are required to sustainably manage urban water resources [1,2]. However, any proposed solutions must be cognisant of security, privacy and other factors that may inhibit adoption and hence impact. The FP7 WISDOM project (funded by the European Commission - GA 619795) aims to achieve a step change in water and energy savings via the integration of innovative Information and Communication Technologies (ICT) frameworks to optimize water distribution networks and to enable change in consumer behavior through innovative demand management and adaptive pricing schemes [1,2,3]. The WISDOM concept centres on the integration of water distribution, sensor monitoring and communication systems coupled with semantic modelling (using ontologies, potentially connected to BIM, to serve as intelligent linkages throughout the entire framework) and control capabilities to provide for near real-time management of urban water resources. Fundamental to this framework are the needs and operational requirements of users and stakeholders at domestic, corporate and city levels and this requires the interoperability of a number of demand and operational models, fed with data from diverse sources such as sensor networks and crowsourced information. This has implications regarding the provenance and trustworthiness of such data and how it can be used in not only the understanding of system and user behaviours, but more importantly in the real-time control of such systems. Adaptive and intelligent analytics will be used to produce decision support systems that will drive the ability to increase the variability of both supply and consumption [3]. This in turn paves the way for adaptive pricing incentives and a greater understanding of the water-energy nexus. This integration is complex and uncertain yet being typical of a cyber-physical system, and its relevance transcends the water resource management domain. The WISDOM framework will be modeled and simulated with initial testing at an experimental facility in France (AQUASIM – a full-scale test-bed facility to study sustainable water management), then deployed and evaluated in in two pilots in Cardiff (UK) and La Spezia (Italy). These demonstrators will evaluate the integrated concept providing insight for wider adoption.