27 research outputs found
Strengthening IT Governance With COBIT 5
No full textThis paper aims to explore the importance of COBIT 5 as a framework, in ensuring the effective “Governance of Enterprise Information Technology (GEIT)”, and to promote the understanding of the five COBIT 5 principles. A comprehensive literature review has also been performed taking into account a total of 56 research papers published in the last decade on COBIT. The data collected from these research papers was analyzed in order to identify various trends- commonalities, differences, themes, and the nature of study. The research papers have been categorized first on basis of their scope and secondly on their nature (empirical, conceptual or descriptive). Towards the end of the paper, we have provided an overview of our findings on the strengths and weaknesses of the research papers studied, and have made suggestions for future research.</jats:p
Uncovering the Research Opportunities in Metaverse Platforms for Teamwork and Collaboration
No full textThe rise of Metaverse platforms is transforming the landscape of the workplace. Workrooms from Meta and AltspaceVR by Microsoft stand out as two leading virtual reality platforms designed to enhance collaboration, meetings, and social interaction within the Metaverse. These platforms are set apart from traditional tools like Zoom and Microsoft Teams by their immersive environments, aiming to redefine remote connectivity. Metaverse platforms could make even mundane tasks less effortless with the novel forms of engrossing telepresence. However, while they offer unparalleled opportunities for engagement and interaction, there\u27s potential for these platforms to introduce new challenges in managing workloads. Yet, the effectiveness of these virtual workplaces as tools for immersive remote collaboration remains under-explored. In this PDS, we are interested in identifying the research opportunities in metaverse platforms for teamwork and collaboration. For example, Is it necessary, or even beneficial, for all teamwork tasks to be performed within a Metaverse context? Whether these metaverse platforms either increase or decrease the difficulties of carrying out everyday teamwork and collaboration tasks
Designing for Self-Management of Multiple Chronic Conditions by the Aging-at-home
No full textMany elderly individuals are aging at home (AAH) as the planet is graying. In the U.S., the number will rise to more than 64 million people by 2040. The AAH are more susceptible to health-related issues due to the normal process of aging coupled with the incidence of multiple chronic conditions (MCC). Self-management of MCC can be cognitively and operationally challenging for the AAH. We are designing digital resources for AAH with MCC following the action design research methodology. In this paper, we describe outcomes from early rounds, including problem formulation with semi-structured interviews of AAH with MCC, exploring theoretical precursors and technology frames, and evaluating design genres to establish a design vision. The outcomes are described as a theory-ingrained, layered digital artifact, MyHealthNotes; along with the results of an initial applicability check and formative usability test. The paper concludes with a discussion of contributions so far and next steps
Fine-grained entity typing system - design and analysis
No full textNamed entity recognition (NER) is a natural language processing (NLP) task that involves identifying mentions (spans of text) denoting entities in a given text document and assigning them a semantic category/type from a given taxonomy. It is considered to be one of the fundamental tasks in NLP and forms the basis for higher level understanding. In this thesis, we deal with fine-grained entity type recognition, which is a variant of the classic NER task where the usual types are sub-divided into fine-grained types. We show that the current approaches, which address this problem using only local context, are insufficient to completely address the problem. We systematically identify the fundamental challenges and misconceptions that underlie the assumptions, approaches and evaluation methodologies of this task and propose improvements and alternatives. We do this by first analyzing the role of context and background knowledge in the task of fine-grained entity typing. Second, we introduce a modular architecture for fine-grained typing of entities and show that a rather simple instantiation of these modules reaches the state-of-the-art performance.Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2020-05-01The student, Pavankumar Reddy Muddireddy, accepted the attached license on 2018-04-23 at 17:30.The student, Pavankumar Reddy Muddireddy, submitted this Thesis for approval on 2018-04-23 at 17:42.This Thesis was approved for publication on 2018-04-24 at 09:20.DSpace SAF Submission Ingestion Package generated from Vireo submission #12436 on 2018-08-31 at 17:21:20Made available in DSpace on 2018-09-04T20:36:52Z (GMT). No. of bitstreams: 2
MUDDIREDDY-THESIS-2018.pdf: 446805 bytes, checksum: 30dc454cac28cfff02a4762ba75d774a (MD5)
LICENSE.txt: 4224 bytes, checksum: b8203e25ef7f7ebfd07f9694a6abae27 (MD5)
Previous issue date: 2018-04-24Embargo set by: Seth Robbins for item 107298
Lift date: 2020-09-04T20:37:00Z
Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD systemEmbargo set by: Seth Robbins for item 107298
Lift date: 2020-09-04T20:42:08Z
Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD systemU of I Only Restriction Lifted for Item 107298 on 2020-09-05T09:15:29Z
Development of an automated physician review classification system: A novel semi-supervised learning approach
No full textBuilding automated text classifiers have assumed significant importance since the development of large online information platforms. Several compelling use cases have emerged in the field of artificial intelligence and analytics in recent years. However, building and training text classifiers become problematic in the healthcare context, which deals with a sensitive and limited volume of data. In this paper, we explore the development of a classifier and apply it to a specific case of classifying physician reviews into either clinical and non-clinical reviews. The primary purpose of this paper is to demonstrate the methodology using which the classifier has been developed, including a novel technique in curating datasets. We leverage unsupervised guided Latent Dirichlet Allocation (LDA) method and supervised methods such as deep neural networks, Long-Short Term Memory (LSTM) networks, and Bi-directional LSTMs. Further, we compare the various models and choose the one with the best classification performance by validating the output results with the ground truth. Our methodology provides insights into making the best use of semi-supervised and supervised algorithms along with grounded data for developing classifiers that can be generalized for other novel contexts where dataset availability is limited
A FRAMEWORK FOR NEXT GENERATION iCBT APPLICATIONS FOR SAD PATIENTS
No full textOur paper aims to develop a web-based IT system based on a framework for CCBT and iCBT applications for the treatment of mild to moderate SAD diagnoses. We place our research in the intervention area of CCBT, where the facilitation of interaction with therapists in a non-threatening environment, peer interaction, and access to self-help and educational resources, will likely lead to changes in the perception of the self and a reduction of SAD symptoms in patients. This DSR proposal contributes with a novel requirements engineering and validation process through an adaptation of Activity Theory. It also leveraged the SAD model to derive a framework that caters to SAD patients. And lastly it provides an artifact that acts like a platform to deliver CBT that can be generalized to other disorders
Three Essays on the Impact of Digital Health Interventions: A Multi-Stakeholder Perspective
No full textPh.D.The full text PDF of this dissertation is embargoed at author's request until 2022-02-19.Healthcare costs in the U.S. have been rising while the quality of and access to healthcare have been lacking. Digital health interventions are now viewed as a partial solution to addressing the triple aim of achieving better quality, lower cost, and greater access. The term “digital health” has been narrowly defined as “internet-focused applications and media to improve medical content, commerce, and connectivity.” However, the term’s definition has evolved such that its contemporary version includes a broader range of technologies and interventions with which to improve quality, increase access, and lower costs. At one end of the spectrum, digital health consists of innovative enterprise applications used in the delivery and management of healthcare, including electronic health records (EHRs), the Health Information Exchanges (HIE), lab-management systems, and home-health applications. On the other end of the spectrum, it encompasses health-specific social networks, applications, and decision-making tools that employ healthcare analytics, internet of things (IOT)-enabled devices, artificial intelligence, and other emerging technologies. The World Health Organization (WHO), using more-clinical framing, has classified digital health interventions as those for (1) clients, (2) healthcare providers, (3) health systems or resource managers, and (4) data services. This dissertation, structured as three thesis essays, attempts to provide a deeper understanding of the effects of specific digital health interventions on healthcare costs, quality, and access...**To request an accessible version of the file(s) associated with this item, contact [email protected]. Please include the item's persistent URL [http://hdl.handle.net/. . .] in your request.*
Development of an Automated Physician Review Classification System: A hybrid Machine Learning Approach
No full textPatients are increasingly turning to physician rating websites to help them make important healthcare decisions, such as selecting primary care doctors, specialists, and supplementary medical care providers. Previous research has identified a variety of topics and themes that emerge on these review platforms. However, there is little or no work that has been done to create an automated classifier that automatically categorizes these reviews into distinct topics after they have been explored in this context. Building such an automated classifier could assist IS developers and other stakeholders in automatically classifying patient reviews and understanding patient needs. Furthermore, using design science research we strategize how such machine learning systems can be built using design guidelines in turn having the potential to be generalized to other specific contextual problem spaces. Our work focuses on laying the foundation to design guidelines that need to be followed while building automated systems in specific contexts
Exploring the Research Opportunities on Designing Digital Solutions for Taboo-Driven Health Disorders
No full textTaboo-driven health disorders—such as mental health issues, reproductive health conditions, and sexually transmitted diseases—often carry deep social stigma that discourages open discussion, diagnosis, and treatment. Digital solutions, including mobile apps, telehealth platforms, and AI-based support systems, hold promise for improving accessibility, anonymity, and patient engagement in managing these sensitive health issues. However, designing effective digital interventions for taboo-driven conditions poses unique challenges, including fostering trust, ensuring privacy, and navigating complex cultural norms. Stigma frequently intersects with factors such as gender, socioeconomic status among others, compounding disparities and making a one-size-fits-all solution ineffective. Understanding of such dynamics is important for tailoring interfaces and culturally nuanced content that resonates. Despite the potential, research exploring how to design user-centered, stigma-sensitive digital solutions for these contexts remains limited. In this PDS, we aim to discuss emerging research opportunities at the intersection of digital health and taboo-driven health management
A TOGAF Based Chatbot Evaluation Metrics: Insights from Literature Review
No full textChatbots have been used for basic conversational functionalities and task performance in today\u27s world. With the surge in the use of chatbots, several design features have emerged to cater to its rising demands and increasing complexity. Researchers have grappled with the issues of modeling and evaluating these tools because of the vast number of metrics associated with their measure of successful. This paper conducted a literature survey to identify the various conversational metrics used to evaluate chatbots. The selected evaluation metrics were mapped to the various layers of The Open Group Architecture Framework (TOGAF) architecture. TOGAF architecture helped us divide the metrics based on the various facets critical to developing successful chatbot applications. Our results show that the metrics related to the business layer have been well studied. However, metrics associated with the data, information, and system layers warrant more research. As chatbots become more complex, success metrics across the intermediate layers may assume greater significance
