Document understanding using data mining and machine learning techniques

With the explosive growth of the volume and complexity of document data (e.g., news, blogs, web pages), it has become a necessity to semantically understand documents and deliver meaningful information to users. Areas dealing with these problems are crossing data mining, information retrieval, and machine learning. For example, document clustering and summarization are two fundamental techniques for understanding document data and have attracted much attention in recent years. Given a collection of documents, document clustering aims to partition them into different groups to provide efficient document browsing and navigation mechanisms. One unrevealed area in document clustering is that how to generate meaningful interpretation for the each document cluster resulted from the clustering process. Document summarization is another effective technique for document understanding, which generates a summary by selecting sentences that deliver the major or topic-relevant information in the original documents. How to improve the automatic summarization performance and apply it to newly emerging problems are two valuable research directions. To assist people to capture the semantics of documents effectively and efficiently, the dissertation focuses on developing effective data mining and machine learning algorithms and systems for (1) integrating document clustering and summarization to obtain meaningful document clusters with summarized interpretation, (2) improving document summarization performance and building document understanding systems to solve real-world applications, and (3) summarizing the differences and evolution of multiple document sources.

Integration of Satellite and Financial Data to Model Future Economic Impact of Citrus Crops (Final Project Report)

This study analyzed the health and overall landcover of citrus crops in Florida. The analysis was completed using Landsat satellite imagery available free of charge from the University of Maryland Global Landcover Change Facility. The project hypothesized that combining citrus production (economic) data with citrus area per county derived from spectral signatures would yield correlations between observable spectral reflectance throughout the year, and the fiscal impact of citrus on local economies. A positive correlation between these two data types would allow us to predict the economic impact of citrus using spectral data analysis to determine final crop harvests.

Learning Data-Driven Models of Non-Verbal Behaviors for Building Rapport Using an Intelligent Virtual Agent

There is a growing societal need to address the increasing prevalence of behavioral health issues, such as obesity, alcohol or drug use, and general lack of treatment adherence for a variety of health problems. The statistics, worldwide and in the USA, are daunting. Excessive alcohol use is the third leading preventable cause of death in the United States (with 79,000 deaths annually), and is responsible for a wide range of health and social problems. On the positive side though, these behavioral health issues (and associated possible diseases) can often be prevented with relatively simple lifestyle changes, such as losing weight with a diet and/or physical exercise, or learning how to reduce alcohol consumption. Medicine has therefore started to move toward finding ways of preventively promoting wellness, rather than solely treating already established illness. Evidence-based patient-centered Brief Motivational Interviewing (BMI) interven- tions have been found particularly effective in helping people find intrinsic motivation to change problem behaviors after short counseling sessions, and to maintain healthy lifestyles over the long-term. Lack of locally available personnel well-trained in BMI, however, often limits access to successful interventions for people in need. To fill this accessibility gap, Computer-Based Interventions (CBIs) have started to emerge. Success of the CBIs, however, critically relies on insuring engagement and retention of CBI users so that they remain motivated to use these systems and come back to use them over the long term as necessary. Because of their text-only interfaces, current CBIs can therefore only express limited empathy and rapport, which are the most important factors of health interventions. Fortunately, in the last decade, computer science research has progressed in the design of simulated human characters with anthropomorphic communicative abilities. Virtual characters interact using humans’ innate communication modalities, such as facial expressions, body language, speech, and natural language understanding. By advancing research in Artificial Intelligence (AI), we can improve the ability of artificial agents to help us solve CBI problems. To facilitate successful communication and social interaction between artificial agents and human partners, it is essential that aspects of human social behavior, especially empathy and rapport, be considered when designing human-computer interfaces. Hence, the goal of the present dissertation is to provide a computational model of rapport to enhance an artificial agent’s social behavior, and to provide an experimental tool for the psychological theories shaping the model. Parts of this thesis were already published in [LYL+12, AYL12, AL13, ALYR13, LAYR13, YALR13, ALY14].

Ensemble Stream Model for Data-Cleaning in Sensor Networks

Ensemble Stream Modeling and Data-cleaning are sensor information processing systems have different training and testing methods by which their goals are cross-validated. This research examines a mechanism, which seeks to extract novel patterns by generating ensembles from data. The main goal of label-less stream processing is to process the sensed events to eliminate the noises that are uncorrelated, and choose the most likely model without over fitting thus obtaining higher model confidence. Higher quality streams can be realized by combining many short streams into an ensemble which has the desired quality. The framework for the investigation is an existing data mining tool. First, to accommodate feature extraction such as a bush or natural forest-fire event we make an assumption of the burnt area (BA*), sensed ground truth as our target variable obtained from logs. Even though this is an obvious model choice the results are disappointing. The reasons for this are two: One, the histogram of fire activity is highly skewed. Two, the measured sensor parameters are highly correlated. Since using non descriptive features does not yield good results, we resort to temporal features. By doing so we carefully eliminate the averaging effects; the resulting histogram is more satisfactory and conceptual knowledge is learned from sensor streams. Second is the process of feature induction by cross-validating attributes with single or multi-target variables to minimize training error. We use F-measure score, which combines precision and accuracy to determine the false alarm rate of fire events. The multi-target data-cleaning trees use information purity of the target leaf-nodes to learn higher order features. A sensitive variance measure such as f-test is performed during each node’s split to select the best attribute. Ensemble stream model approach proved to improve when using complicated features with a simpler tree classifier. The ensemble framework for data-cleaning and the enhancements to quantify quality of fitness (30% spatial, 10% temporal, and 90% mobility reduction) of sensor led to the formation of streams for sensor-enabled applications. Which further motivates the novelty of stream quality labeling and its importance in solving vast amounts of real-time mobile streams generated today.

Improving resource management in virtualized data centers using application performance models

The rapid growth of virtualized data centers and cloud hosting services is making the management of physical resources such as CPU, memory, and I/O bandwidth in data center servers increasingly important. Server management now involves dealing with multiple dissimilar applications with varying Service-Level-Agreements (SLAs) and multiple resource dimensions. The multiplicity and diversity of resources and applications are rendering administrative tasks more complex and challenging. This thesis aimed to develop a framework and techniques that would help substantially reduce data center management complexity.^ We specifically addressed two crucial data center operations. First, we precisely estimated capacity requirements of client virtual machines (VMs) while renting server space in cloud environment. Second, we proposed a systematic process to efficiently allocate physical resources to hosted VMs in a data center. To realize these dual objectives, accurately capturing the effects of resource allocations on application performance is vital. The benefits of accurate application performance modeling are multifold. Cloud users can size their VMs appropriately and pay only for the resources that they need; service providers can also offer a new charging model based on the VMs performance instead of their configured sizes. As a result, clients will pay exactly for the performance they are actually experiencing; on the other hand, administrators will be able to maximize their total revenue by utilizing application performance models and SLAs. ^ This thesis made the following contributions. First, we identified resource control parameters crucial for distributing physical resources and characterizing contention for virtualized applications in a shared hosting environment. Second, we explored several modeling techniques and confirmed the suitability of two machine learning tools, Artificial Neural Network and Support Vector Machine, to accurately model the performance of virtualized applications. Moreover, we suggested and evaluated modeling optimizations necessary to improve prediction accuracy when using these modeling tools. Third, we presented an approach to optimal VM sizing by employing the performance models we created. Finally, we proposed a revenue-driven resource allocation algorithm which maximizes the SLA-generated revenue for a data center.^

Improving Resource Management in Virtualized Data Centers using Application Performance Models

The rapid growth of virtualized data centers and cloud hosting services is making the management of physical resources such as CPU, memory, and I/O bandwidth in data center servers increasingly important. Server management now involves dealing with multiple dissimilar applications with varying Service-Level-Agreements (SLAs) and multiple resource dimensions. The multiplicity and diversity of resources and applications are rendering administrative tasks more complex and challenging. This thesis aimed to develop a framework and techniques that would help substantially reduce data center management complexity. We specifically addressed two crucial data center operations. First, we precisely estimated capacity requirements of client virtual machines (VMs) while renting server space in cloud environment. Second, we proposed a systematic process to efficiently allocate physical resources to hosted VMs in a data center. To realize these dual objectives, accurately capturing the effects of resource allocations on application performance is vital. The benefits of accurate application performance modeling are multifold. Cloud users can size their VMs appropriately and pay only for the resources that they need; service providers can also offer a new charging model based on the VMs performance instead of their configured sizes. As a result, clients will pay exactly for the performance they are actually experiencing; on the other hand, administrators will be able to maximize their total revenue by utilizing application performance models and SLAs. This thesis made the following contributions. First, we identified resource control parameters crucial for distributing physical resources and characterizing contention for virtualized applications in a shared hosting environment. Second, we explored several modeling techniques and confirmed the suitability of two machine learning tools, Artificial Neural Network and Support Vector Machine, to accurately model the performance of virtualized applications. Moreover, we suggested and evaluated modeling optimizations necessary to improve prediction accuracy when using these modeling tools. Third, we presented an approach to optimal VM sizing by employing the performance models we created. Finally, we proposed a revenue-driven resource allocation algorithm which maximizes the SLA-generated revenue for a data center.

The development, application, and implications of a strategy for reflective learning from experience

The problem on which this study focused was individuals' reduced capacity to respond to change and to engage in innovative learning when their reflective learning skills are limited. In this study, the preceding problem was addressed by two primary questions: To what degree can mastery of a strategy for reflective learning be facilitated as a part of an academic curriculum for professional practitioners? What impact will mastery of this strategy have on the learning style and adaptive flexibility of adult learners? The focus of the study was a direct application of human resource development technology in the professional preparation of teachers. The background of the problem in light of changing global paradigms and educational action orientations was outlined and a review of the literature was provided. Roots of thought for two key concepts (i.e., learning to learn from experience and meaningful reflection in learning) were traced. Reflective perspectives from the work of eight researchers were compared. A meta-model of learning from experience drawn from the literature served as a conceptual framework for the study. A strategy for reflective learning developed from this meta-model was taught to 109 teachers-in-training at Florida International University in Miami, Florida. Kolb's Adaptive Style Inventory and Learning Style Inventory were administered to the treatment group and to two control groups taught by the same professor. Three research questions and fourteen hypotheses guided data analysis. Qualitative review of 1565 personal documents generated by the treatment group indicated that 77 students demonstrated "double-loop" learning, going beyond previously established limits to perception, understanding, or action. The mean score for depth of reflection indicated "single-loop" learning with "reflection-in-action" present. The change in the mean score for depth of reflection from the beginning to end of the study was statistically significant (p $<$.05). On quantitative measures of adaptive flexibility and learning style, with two exceptions, there were no significant differences noted between treatment and control groups on pre-test to post-test differences and on post-test mean scores adjusted for pre-test responses and demographic variables. Conclusions were drawn regarding treatment, instrumentation, and application of the strategy and the meta-model. Implications of the strategy and the meta-model for research, for education, for human resource development, for professional practice, and for personal growth were suggested. Qualitative training materials and Kolb's instruments were provided in the appendices.

Knowledge discovery using multiple sources of biological data

The primary aim of this dissertation is to develop data mining tools for knowledge discovery in biomedical data when multiple (homogeneous or heterogeneous) sources of data are available. The central hypothesis is that, when information from multiple sources of data are used appropriately and effectively, knowledge discovery can be better achieved than what is possible from only a single source. ^ Recent advances in high-throughput technology have enabled biomedical researchers to generate large volumes of diverse types of data on a genome-wide scale. These data include DNA sequences, gene expression measurements, and much more; they provide the motivation for building analysis tools to elucidate the modular organization of the cell. The challenges include efficiently and accurately extracting information from the multiple data sources; representing the information effectively, developing analytical tools, and interpreting the results in the context of the domain. ^ The first part considers the application of feature-level integration to design classifiers that discriminate between soil types. The machine learning tools, SVM and KNN, were used to successfully distinguish between several soil samples. ^ The second part considers clustering using multiple heterogeneous data sources. The resulting Multi-Source Clustering (MSC) algorithm was shown to have a better performance than clustering methods that use only a single data source or a simple feature-level integration of heterogeneous data sources. ^ The third part proposes a new approach to effectively incorporate incomplete data into clustering analysis. Adapted from K-means algorithm, the Generalized Constrained Clustering (GCC) algorithm makes use of incomplete data in the form of constraints to perform exploratory analysis. Novel approaches for extracting constraints were proposed. For sufficiently large constraint sets, the GCC algorithm outperformed the MSC algorithm. ^ The last part considers the problem of providing a theme-specific environment for mining multi-source biomedical data. The database called PlasmoTFBM, focusing on gene regulation of Plasmodium falciparum, contains diverse information and has a simple interface to allow biologists to explore the data. It provided a framework for comparing different analytical tools for predicting regulatory elements and for designing useful data mining tools. ^ The conclusion is that the experiments reported in this dissertation strongly support the central hypothesis.^

Learning Behind Bars: Exploring Prison Educators’ Facilitation of Inmates’ Self-directed Learning through Garrison’s Model

Formal education programs in prisons have had success in reducing recidivism, but the introduction of informal learning can have additional benefits and longer lasting effects. This paper addresses recidivism and its effects on inmates and society at large and how prison educators can facilitate self-directed learning in prisons through Garrison’s model.

A planning model for needs analysis for subacute care

The purpose of this study is to produce a model to be used by state regulating agencies to assess demand for subacute care. In accomplishing this goal, the study refines the definition of subacute care, demonstrates a method for bed need assessment, and measures the effectiveness of this new level of care. This was the largest study of subacute care to date. Research focused on 19 subacute units in 16 states, each of which provides high-intensity rehabilitative and/or restorative care carried out in a high-tech unit. Each of the facilities was based in a nursing home, but utilized separate staff, equipment, and services. Because these facilities are under local control, it was possible to study regional differences in subacute care demand.^ Using this data, a model for predicting demand for subacute care services was created, building on earlier models submitted by John Whitman for the American Hospital Association and Robin E. MacStravic. The Broderick model uses the "bootstrapping" method and takes advantage of high technology: computers and software, databases in business and government, publicly available databases from providers or commercial vendors, professional organizations, and other information sources. Using newly available sources of information, this new model addresses the problems and needs of health care planners as they approach the challenges of the 21st century. ^

Best practices in exemplary service delivery: A multiple case study of service quality

The purpose of this study was to explain how exemplary service providers in luxury hotels provide consistently excellent service. Using a case study framework, the study investigated the service provider's strategies and concepts of service delivery, the importance and implementation of organizational and individual controls, and the role of training and learning. The study identified barriers to service provision and characteristics of the exemplary individuals that affect their ability to deliver luxury service. This study sought to better understand how exemplary service providers learn, think about, and do their work. The sample population of three Five-Diamond-Award winning resorts was selected for their potential for learning about the phenomenon of interest. The results demonstrate that exemplary service providers possess individual characteristics that are enhanced by the organizations for which they work. Exemplary service providers are often exemplary communicators who are emotionally generous and genuinely enjoy helping and serving others. Exemplary service organizations treat their employees as they treat their customers, as suggested by the Service-Profit Chain (Heskett, Sasser & Schlesinger, 1997). Further, they have systems and standards to guarantee satisfactory service experiences for every guest. They also encourage their service providers to personalize their service delivery and to seek opportunities to delight their guests, using a combination of controls, traditions and cultural values. Several customer service theories are discussed in relationship to whether they were or were not supported by the data. The study concluded that the delivery of exemplary service is a complex phenomenon that requires successful interactions between guests, service providers and the organization. A Model of Exemplary Service Delivery is presented and discussed that demonstrates the components of service quality as shown in the data. The model can be used by practitioners seeking to create, enhance, or evaluate their service quality, and by researchers seeking insights into the complex concepts in service quality research. Implications for future research are discussed.

User-centric music information retrieval

The rapid growth of the Internet and the advancements of the Web technologies have made it possible for users to have access to large amounts of on-line music data, including music acoustic signals, lyrics, style/mood labels, and user-assigned tags. The progress has made music listening more fun, but has raised an issue of how to organize this data, and more generally, how computer programs can assist users in their music experience. An important subject in computer-aided music listening is music retrieval, i.e., the issue of efficiently helping users in locating the music they are looking for. Traditionally, songs were organized in a hierarchical structure such as genre->artist->album->track, to facilitate the users’ navigation. However, the intentions of the users are often hard to be captured in such a simply organized structure. The users may want to listen to music of a particular mood, style or topic; and/or any songs similar to some given music samples. This motivated us to work on user-centric music retrieval system to improve users’ satisfaction with the system. The traditional music information retrieval research was mainly concerned with classification, clustering, identification, and similarity search of acoustic data of music by way of feature extraction algorithms and machine learning techniques. More recently the music information retrieval research has focused on utilizing other types of data, such as lyrics, user-access patterns, and user-defined tags, and on targeting non-genre categories for classification, such as mood labels and styles. This dissertation focused on investigating and developing effective data mining techniques for (1) organizing and annotating music data with styles, moods and user-assigned tags; (2) performing effective analysis of music data with features from diverse information sources; and (3) recommending music songs to the users utilizing both content features and user access patterns.

A generic model of execution for synthesizing domain-specific models

Software engineering researchers are challenged to provide increasingly more powerful levels of abstractions to address the rising complexity inherent in software solutions. One new development paradigm that places models as abstraction at the forefront of the development process is Model-Driven Software Development (MDSD). MDSD considers models as first class artifacts, extending the capability for engineers to use concepts from the problem domain of discourse to specify apropos solutions. A key component in MDSD is domain-specific modeling languages (DSMLs) which are languages with focused expressiveness, targeting a specific taxonomy of problems. The de facto approach used is to first transform DSML models to an intermediate artifact in a HLL e.g., Java or C++, then execute that resulting code.^ Our research group has developed a class of DSMLs, referred to as interpreted DSMLs (i-DSMLs), where models are directly interpreted by a specialized execution engine with semantics based on model changes at runtime. This execution engine uses a layered architecture and is referred to as a domain-specific virtual machine (DSVM). As the domain-specific model being executed descends the layers of the DSVM the semantic gap between the user-defined model and the services being provided by the underlying infrastructure is closed. The focus of this research is the synthesis engine, the layer in the DSVM which transforms i-DSML models into executable scripts for the next lower layer to process.^ The appeal of an i-DSML is constrained as it possesses unique semantics contained within the DSVM. Existing DSVMs for i-DSMLs exhibit tight coupling between the implicit model of execution and the semantics of the domain, making it difficult to develop DSVMs for new i-DSMLs without a significant investment in resources.^ At the onset of this research only one i-DSML had been created for the user- centric communication domain using the aforementioned approach. This i-DSML is the Communication Modeling Language (CML) and its DSVM is the Communication Virtual machine (CVM). A major problem with the CVM's synthesis engine is that the domain-specific knowledge (DSK) and the model of execution (MoE) are tightly interwoven consequently subsequent DSVMs would need to be developed from inception with no reuse of expertise.^ This dissertation investigates how to decouple the DSK from the MoE and subsequently producing a generic model of execution (GMoE) from the remaining application logic. This GMoE can be reused to instantiate synthesis engines for DSVMs in other domains. The generalized approach to developing the model synthesis component of i-DSML interpreters utilizes a reusable framework loosely coupled to DSK as swappable framework extensions.^ This approach involves first creating an i-DSML and its DSVM for a second do- main, demand-side smartgrid, or microgrid energy management, and designing the synthesis engine so that the DSK and MoE are easily decoupled. To validate the utility of the approach, the SEs are instantiated using the GMoE and DSKs of the two aforementioned domains and an empirical study to support our claim of reduced developmental effort is performed.^

Statistical dialog management for health interventions

Research endeavors on spoken dialogue systems in the 1990s and 2000s have led to the deployment of commercial spoken dialogue systems (SDS) in microdomains such as customer service automation, reservation/booking and question answering systems. Recent research in SDS has been focused on the development of applications in different domains (e.g. virtual counseling, personal coaches, social companions) which requires more sophistication than the previous generation of commercial SDS. The focus of this research project is the delivery of behavior change interventions based on the brief intervention counseling style via spoken dialogue systems. ^ Brief interventions (BI) are evidence-based, short, well structured, one-on-one counseling sessions. Many challenges are involved in delivering BIs to people in need, such as finding the time to administer them in busy doctors' offices, obtaining the extra training that helps staff become comfortable providing these interventions, and managing the cost of delivering the interventions. Fortunately, recent developments in spoken dialogue systems make the development of systems that can deliver brief interventions possible. ^ The overall objective of this research is to develop a data-driven, adaptable dialogue system for brief interventions for problematic drinking behavior, based on reinforcement learning methods. The implications of this research project includes, but are not limited to, assessing the feasibility of delivering structured brief health interventions with a data-driven spoken dialogue system. Furthermore, while the experimental system focuses on harmful alcohol drinking as a target behavior in this project, the produced knowledge and experience may also lead to implementation of similarly structured health interventions and assessments other than the alcohol domain (e.g. obesity, drug use, lack of exercise), using statistical machine learning approaches. ^ In addition to designing a dialog system, the semantic and emotional meanings of user utterances have high impact on interaction. To perform domain specific reasoning and recognize concepts in user utterances, a named-entity recognizer and an ontology are designed and evaluated. To understand affective information conveyed through text, lexicons and sentiment analysis module are developed and tested.^

A planning model for needs analysis for subacute care

The purpose of this study is to produce a model to be used by state regulating agencies to assess demand for subacute care. In accomplishing this goal, the study refines the definition of subacute care, demonstrates a method for bed need assessment, and measures the effectiveness of this new level of care. This was the largest study of subacute care to date. Research focused on 19 subacute units in 16 states, each of which provides high-intensity rehabilitative and/or restorative care carried out in a high-tech unit. Each of the facilities was based in a nursing home, but utilized separate staff, equipment, and services. Because these facilities are under local control, it was possible to study regional differences in subacute care demand. Using this data, a model for predicting demand for subacute care services was created, building on earlier models submitted by John Whitman for the American Hospital Association and Robin E. MacStravic. The Broderick model uses the "bootstrapping" method and takes advantage of high technology: computers and software, databases in business and government, publicly available databases from providers or commercial vendors, professional organizations, and other information sources. Using newly available sources of information, this new model addresses the problems and needs of health care planners as they approach the challenges of the 21st century.