Doctor of Philosophy, The Ohio State University, 2022, Computer Science and Engineering

Past decades have witnessed the great success of modern Artificial Intelligence (AI) via learning incredible statistical correlations from large-scale data. However, a knowledge gap still exists between the statistical learning of AI and the human-like learning process. Unlike machines, humans can first accumulate enormous background knowledge about how the world works and then quickly adapt it to new environments by understanding the underlying concepts. For example, given the limited life experience with mammals, a child can quickly learn the new concept of a dog to infer knowledge, like a dog is a mammal, a mammal has a heart, and thus, a dog has a heart. Then the child can generalize the concept to new cases, such as a golden retriever, a beagle, or a chihuahua. However, an AI system trained on a large-scale mammal but not dog-focused dataset cannot do such learning and generalization. AI techniques will fundamentally influence our everyday lives, and bridging this knowledge gap to empower existing AI systems with more explicit human knowledge is both timely and necessary to make them more generalizable, robust, trustworthy, interpretable, and efficient. To close this gap, we seek inspiration from how humans learn, such as the ability to abstract knowledge from data, generalize knowledge to new tasks, and reason to solve complex problems. Inspired by the human learning process, in this dissertation, we present our research efforts to address the knowledge gap between AI and human learning with a systematic study of the full life cycle of how to incorporate more explicit human knowledge in intelligent systems. Specifically, we need first to extract high-quality knowledge from the real world (knowledge acquisition), such as raw data or model parameters. We then transform various types of knowledge into neural representations (knowledge representation). We can also transfer existing knowledge between neural systems (knowledge transfer) or perform human-like co (open full item for complete abstract)

Committee: Huan Sun (Advisor); Wei-Lun Chao (Committee Member); Yu Su (Committee Member); Srinivasan Parthasarathy (Committee Member) Subjects: Computer Science; Language; Linguistics

Doctor of Philosophy (PhD), Wright State University, 2017, Computer Science and Engineering PhD

Semantic Web technologies such as RDF and OWL have become World Wide Web Consortium (W3C) standards for knowledge representation and reasoning. RDF triples about triples, or meta triples, form the basis for a contextualized knowledge graph. They represent the contextual information about individual triples such as the source, the occurring time or place, or the certainty. However, an efficient RDF representation for such meta-knowledge of triples remains a major limitation of the RDF data model. The existing reification approach allows such meta-knowledge of RDF triples to be expressed in RDF by using four triples per reified triple. While reification is simple and intuitive, this approach does not have a formal foundation and is not commonly used in practice as described in the RDF Primer. This dissertation presents the foundations for representing, querying, reasoning and traversing the contextualized knowledge graphs (CKG) using Semantic Web technologies. A triple-based compact representation for CKGs. We propose a principled approach and construct RDF triples about triples by extending the current RDF data model with a new concept, called singleton property (SP), as a triple identifier. The SP representation needs two triples to the RDF datasets and can be queried with SPARQL. A formal model-theoretic semantics for CKGs. We formalize the semantics of the singleton property and its relationships with the triple it represents. We extend the current RDF model-theoretic semantics to capture the semantics of the singleton properties and provide the interpretation at three levels: simple, RDF, and RDFS. It provides a single interpretation of the singleton property semantics across applications and systems. A sound and complete inference mechanism for CKGs. Based on the semantics we propose, we develop a set of inference rules for validating and inferring new triples based on the SP syntax. We also derive different sets of context-based inference rules using latti (open full item for complete abstract)

Committee: Amit Sheth Ph.D. (Advisor); Krishnaprasad Thirunarayan Ph.D. (Committee Member); Olivier Bodenreider Ph.D. (Committee Member); Kemafor Anyanwu Ph.D. (Committee Member); Ramanathan Guha Ph.D. (Committee Member) Subjects: Computer Science

Master of Computing and Information Systems, Youngstown State University, 2008, Department of Computer Science and Information Systems

In this paper, we explore the concept of epistemic visualization in interrogative domains. Epistemic visualization is the process and result of developing visual models that capture the structure, content, justification and acquisition of knowledge obtained by a software agent in a knowledge-based system. The knowledge is the foundation in which the agent can respond to queries against a corpus containing questions and answers. The visualizations are therefore used to examine the quality of the software agent's knowledge. The visual models will include justification and commitment artifacts as well as knowledge acquisition flow. The visualization will demarcate the a priori and posteriori knowledge. The knowledge of the software agent is stored in epistemic structures which are knowledge representation schemes that supports the basic concepts of knowledge as defined by the tripartite analysis of knowledge. Epistemic visualization is used to analyze the quality of the knowledge of a software agent in an interrogative domain. For our purpose, interrogative domains are hearings, trials, interrogations, personality test or any document source in which the primary content is questions and answers pairs. In this paper, we introduce the Epistemic Structure Es that captures the agent's knowledge and the visualization of that epistemic structure using common visualization techniques.

Committee: Alina Lazar PhD (Committee Chair); John Sullins PhD (Committee Member); Yong Zhang PhD (Committee Member) Subjects: Artificial Intelligence; Computer Science; Information Systems; Linguistics; Technology

Master of Computing and Information Systems, Youngstown State University, 2008, Department of Computer Science and Information Systems

At Ctest Laboratories we are exploring the notion of automated conversion of the semi-structured text to an epistemic structure suitable for deductive inference. In this paper we will develop an epistemic structured representation for electronic transcripts ofinterrogative domains. We propose that knowledge which is typically not visible to keyword search or string matching, can be readily extracted from the an electronic transcript when it is given an appropriate epistemic structure. We introduce an Epistemic Structure Es and a process for converting a semi-structured transcript from and interrogative domain to Es. In this paper we restrict our discussion and analysis to transcripts that have been stored as semi-structured text. In particular we are interested in any knowledge that can be deduced by an interrogative agent from the content of an electronic transcript. Further we develop the notion of an interrogative agent that relies on epistemic justification as a condition for knowledge.

Committee: Alina Lazar PhD (Committee Chair); John Sullins PhD (Committee Member); Yong Zhang PhD (Committee Member) Subjects: Artificial Intelligence; Computer Science; Information Systems; Linguistics; Technology

Doctor of Philosophy (PhD), Wright State University, 2012, Computer Science and Engineering PhD

I present a method for growing the amount of knowledge available on the Web using a hermeneutic method that involves background knowledge, Information Extraction techniques and validation through discourse and use of the extracted information. I present the metaphor of the "Circle of Knowledge on the Web". In this context, knowledge acquisition on the web is seen as analogous to the way scientific disciplines gradually increase the knowledge available in their field. Here, formal models of interest domains are created automatically or manually and then validated by implicit and explicit validation methods before the statements in the created models can be added to larger knowledge repositories, such as the Linked open Data cloud. This knowledge is then available for the next iteration of the knowledge acquisition cycle. I will both give a theoretical underpinning as well as practical methods for the acquisition of knowledge in collaborative systems. I will cover both the Knowledge Engineering angle as well as the Information Extraction angle of this problem. Unlike traditional approaches, however, this dissertation will show how Information Extraction can be incorporated into a mostly Knowledge Engineering based approach as well as how an Information Extraction-based approach can make use of engineered concept repositories. Validation is seen as an integral part of this systemic approach to knowledge acquisition. The centerpiece of the dissertation is a domain model extraction framework that implements the idea of the "Circle of Knowledge" to automatically create semantic models for domains of interest. It splits the involved Information Extraction tasks into that of Domain Definition, in which pertinent concepts are identified and categorized, and that of Domain Description, in which facts are extracted from free text that describe the extracted concepts. I then outline a social computing strategy for information validation in order to create knowledge from the (open full item for complete abstract)

Committee: Amit Sheth PhD (Advisor); Pankaj Mehra PhD (Committee Member); Shaojun Wang PhD (Committee Member); Pascal Hitzler PhD (Committee Member); Gerhard Weikum PhD (Committee Member) Subjects: Artificial Intelligence; Computer Science; Information Science

Doctor of Philosophy, The Ohio State University, 2023, Electrical and Computer Engineering

The advent of deep neural networks (DNNs) have brought exciting new possibilities for the realization of automated driving functions. These data-driven methods have been widely applied to various driving tasks, including end-to-end urban driving. However, the use of these methods beyond simulated tests remains limited due to two significant shortcomings: (i) the lack of model transparency and (ii) the difficulty of generalizing beyond the training distribution. This dissertation aims to investigate methods for addressing the transparency and safety mitigation of learning-based controllers, specifically deep reinforcement learning (DRL) methods, to enable safe and predictable driving. To enhance interpretability, an interpretable and causal state representation, coined the driving forces, is proposed. This representation captures the causal relationship between the state and the produced control action by leveraging force features to encode the influence of internal and external factors on the ego vehicle. By training a DRL agent on this representation within a highway driving environment, the ability of the driving forces to encode and interpret the state-action causalities was demonstrated. Furthermore, an alternative paradigm for online adaptation by modifying the formulation of the driving forces is proposed to mitigate the behavior of the ego vehicle. The results showed that the ego vehicle was successful in mitigating its behavior and following desired new and unseen behaviors, without requiring modification to the underlying DNN. To address model transparency in black-box DNN-based driving policies, a knowledge distillation framework that combines interpretable decision trees with rule learning algorithms is proposed. This framework learns decision rule sets that represent the decision boundaries of the original driving policy. The driving forces are utilized to abstract the original state representation and ensure the interpretability of the learned explanati (open full item for complete abstract)

Committee: Umit Ozguner (Advisor); Keith Redmill (Committee Member); Qadeer Ahmed (Committee Member); Gladys Mitchell (Committee Member) Subjects: Artificial Intelligence; Computer Engineering; Electrical Engineering; Transportation

Master of Computer Science, Miami University, 2022, Computer Science and Software Engineering

Text parsing and natural language processing are well-researched and investigated areas of natural language, however, story understanding and natural language understanding are less so. In an attempt to create an efficient and effective way for computers to gain a better understanding of stories, we aim to give an analysis of the current state and effectiveness of ALM as a knowledge representation language. We wish to develop a library of commonsense knowledge on verbs that surpasses the existing libraries in breadth and effectiveness. The library will utilize the modular action language ALM, and draw inspiration from evaluations on COREALMLib and VERBNET. In addition, the tool available for analysis of ALM, TEXT2ALM, will be reviewed on its usefulness, modularity, and accuracy of execution.

Committee: Daniela Inclezan (Advisor); Alan Ferrenberg (Committee Member); Norm Krumpe (Committee Member) Subjects: Computer Science

Doctor of Philosophy, The Ohio State University, 2020, Computer Science and Engineering

The advent and proliferation of web technologies and the boom of big data has given rise to new modes of social interactions, as well as a deluge of information across numerous domains, topics and languages. This unstructured human-generated data contains rich semantic and stylistic signals reflecting the latent intentions of people, and is remarkably valuable for knowledge discovery. In order to effectively understand and lend structure to such massive quantities of data, it is not enough to merely extract and analyze salient patterns from it. It is equally important to understand and model the functional intentions, behavioral characteristics, reactions and responses of the authors and/or consumers of the data in question. In this dissertation, we extract and study the functional meaning, intentions and knowledge patterns in modern digital content in disparate contexts, which is the focus of an area called latent pragmatic analysis. We then propose some interesting avenues of future research. Our first contribution is the development of context-aware knowledge harvesting techniques to automatically organize unstructured information into easily accessible, hierarchical schemas, thus avoiding the need for manual or expert curation. We propose a technique, ETF, that learns a ranking model utilizing semantic and graph theoretic features to insert newly emerging conceptual information into large, existing general-purpose knowledge stores like DBPedia. Second, we develop a machine learning algorithm, BOLT-K, to automatically learn ontology hierarchies for emergent topics or sub-domains. It significantly reduces the need for human supervision by augmenting the limited labeled training data, and transferring knowledge from existing, functionally related schemas. Third, to ensure the presence of factually accurate information in our constructed knowledge stores, we propose an encoder-decoder framework called FACE-KEG. It predicts the veracity of input textual informatio (open full item for complete abstract)

Committee: Srinivasan Parthasarathy (Advisor); Huan Sun (Committee Member); Eric Fosler-Lussier (Committee Member); Duane Wegener (Committee Member) Subjects: Computer Science

Doctor of Philosophy, Miami University, 2020, Educational Leadership

Through a Black Feminist and Black Girlhood Studies lens, this qualitative photovoice study explores the ways in which Black girls construct and make meaning of self and their educational experiences. Five Black adolescent girls from a leadership and mentoring after-school experience took pictures, interviewed, and participated in group discussions to co-create knowledge about themselves and their experiences. Through the analysis, there were four themes that were found. Voice, this highlighted the ways in which the co-researchers felt like they are often not listened to by educators, but also how they insert their voice on their own terms. The second theme, the politics of identity, illuminated how the co-researchers wanted to be judged as individuals, but also acknowledged that they are a part of a larger group (i.e African American and gendered as girls). The third theme, defining self/ Black girlhood displayed the ways in which, the girls chose to define themselves in comparison to how they felt others see them. Finally, the fourth theme, Space & place illustrated what the girls felt people could do in order to improve Black girls experiences in school and allow for space for them to be able to self-define and explore their identities. Through this study, the co-researchers created an emerging framework, Black Girlhood as Visual Oppositional Knowledge.

Committee: Lisa Weems (Committee Chair); Denise Taliaferro Baszile (Committee Member); Brittany Aronson (Committee Member); Gwendolyn Etter-Lewis (Committee Member) Subjects: African Americans; Education; Multicultural Education

Doctor of Philosophy (PhD), Ohio University, 2019, Electrical Engineering & Computer Science (Engineering and Technology)

Artificial intelligence (AI) is being widely applied to various practical problems, and researchers are working to address numerous issues facing the field. The organizational structure and learning mechanism of the memory is one such issue. A cognitive agent builds a representation of its environment and remembers its experiences to interpret its inputs and implements its goals through its actions. By doing so it demonstrates its intelligence (if any), and it is its learning mechanism, value system and sensory motor coordination that makes all this possible. Memory in a cognitive agent stores its knowledge, knowledge gained over a life-time of experiences in a specific environment. That is, memory includes the “facts”, the relationships between them, and the mechanism used to learn, recognize, and recall based on the agent's interaction with the world/environment. It remembers events that the agent experienced reflecting important actions and observations. It motivates the agent to do anything by providing assessment of the state of the environment and its own state. It allows it to plan and anticipate. And finally, it allows the agent to reflect on itself as an independent being. Hence, memory is critical for intelligence, for it is the memory that determines a cognitive agent's abilities and learning skills. Research has shown that while memory in humans can be classified into different types, based on factors such as their longevity and cognitive mechanisms used to create and retrieve them, they all are achieved using a similar underlying structure. The focus of this dissertation was on using this principle, i.e. different memories created using the same underlying structure, to implement memory for cognitive agents using a biologically plausible model of neuron. This work was an attempt to demonstrate the feasibility of implementing self-organizing memory structures capable of performing the various memory related tasks necessary for a cognitive agent using a c (open full item for complete abstract)

Committee: Wojciech Jadwisienczak (Advisor) Subjects: Electrical Engineering

Doctor of Philosophy (PhD), Wright State University, 2017, Computer Science and Engineering PhD

We characterize two fragments of Horn Description Logics and we define two specialized reasoning algorithms that effectively solve the standard reasoning tasks over each of such fragments. We believe our work to be of general interest since (1) a rather large proportion of real-world Horn ontologies belong to some of these two fragments and (2) the implementations based on our reasoning approach significantly outperform state-of-the-art reasoners. Claims (1) and (2) are extensively proven via empirically evaluation.

Committee: Pascal Hitzler Ph.D. (Advisor); Bernardo Cuenca Grau Ph.D. (Committee Member); Krishnaprasad Thirunarayan Ph.D. (Committee Member); MIchael Raymer Ph.D. (Committee Member) Subjects: Computer Engineering; Computer Science

Master of Sciences (Engineering), Case Western Reserve University, 2014, EECS - Computer Engineering

The integration of reusable IP blocks/cores is a common process in system-on-chip design and involves manually comparing/mapping IP specifications against system requirements. The informal nature of specification limits its automatic analysis. Ex- isting techniques fail to utilize the underlying conceptual information embedded in specifications. In this thesis, we present a methodology for specification analysis, which involves concept mining of specifications to generate domain ontologies. We employ a semi-supervised model with semantic analysis capability to create a col- laborative framework for cumulative knowledge acquisition. Our system then uses the generated ontologies to perform component retrieval and spec comparisons. We demonstrate our approach by evaluating several IP specifications.

Committee: Christos Papachristou (Advisor) Subjects: Computer Engineering; Computer Science; Information Systems; Systems Design

Master of Science (MS), Wright State University, 2008, Human Factors and Industrial/Organizational Psychology MS

Configural spatial knowledge has been tested by having people point from one object to another or by having them sketch maps from memory. Several different pointing judgments have been used, but these judgments appear to differ both in superficial characteristics and in their implied theoretical mental model of spatial representation. This experiment compares two different pointing judgments: judgments of relative direction, based on a quasi-Euclidean model of spatial representation; and object-based judgments, based on an object reference model of spatial representation. Results supported the object reference model. Object-based judgments were more accurate, were made with more confidence and had shorter latencies than judgments of relative direction. Analyses of the sketch maps were consistent with the pointing judgments, suggesting the results reflect stored memory representations and not retrieval differences. Issues of generality of the results and practical ramifications of the research are discussed.

Committee: Herbert Colle (Advisor) Subjects:

Doctor of Philosophy, The Ohio State University, 2007, Nursing

Type 2 diabetes is a growing threat to the health and well-being of Americans. Mid-life women are especially vulnerable to the devastating complications associated with diabetes. Health care professionals must facilitate effective diabetes self-management to minimize the negative consequences of the disease. Self-regulation theory provided a framework for nursing research, “Illness Representation and Glycemic Control in Women with Type 2 Diabetes” (IRT2DM). Illness representation theory proposes that a health threat is processed on cognitive and emotional levels. Emerging from this is a schema termed “illness representation”. The content of illness representation then shapes the choice of coping procedures to the threat. Using a descriptive, exploratory, cross-sectional design, the following research questions were posed: 1. What are the illness representations of a group of women with Type 2 diabetes? 2. What psycho-social factors are associated with illness representation? 3. What is the relationship between illness representation and diabetes self-management? 4. What diabetes self-management practices are associated with glycemic control? Illness representation was measured using the Illness Perception Questionnaire-Revised (IPQ-R). Diabetes knowledge was tested using the University of Michigan Diabetes Knowledge Test (DKT). Demographic and medical history data were gathered. Self-monitoring of blood glucose (SMBG) was chosen to represent effective coping procedures. Level of glycemic control was measured using HgbA1C. The average age was 57 years. The majority was White (65%) and well educated. The majority of the women (75%) reported having 2 or more co-morbidities. Only 40% reported performing SMBG daily. The average HgbA1C was 8.2% at baseline. Diabetes knowledge was high, although there was lack of knowledge about goals for blood glucose testing. Higher scores on two of the constructs in illness representation, cure/control and emotional representation, were (open full item for complete abstract)

Committee: Nancy Reynolds (Advisor) Subjects: Health Sciences, Nursing