<p dir="ltr">This dissertation introduces a novel graph embedding paradigm, leveraging a force-directed scheme for graph embedding. In the field of graph embedding, an "embedding" refers to the process of transforming elements of a graph such as nodes, or edges, or potentially other structural information of the graph into a low-dimensional space, typically a vector space, while preserving the graph's structural properties as much as possible. The dimensions of the space are supposed to be much smaller than the elements of the graph that are to be embedded. This transformation results in a set of vectors, with each vector representing a node (or edge) in the graph. The goal is to capture the essence of the graph's topology, node connectivity, and other relevant features in a way that facilitates easier processing by machine learning algorithms, which often perform better with input data in a continuous vector space.</p><p dir="ltr">The main premise of kinematics-based force-directed graph embedding is that the nodes are considered as massive mobile objects that can be moved around in the embedding space under force. In this PhD thesis, we devised a general theoretical framework for the proposed graph embedding paradigm and provided the mathematical proof of convergence given the required constraints. From this point on, the objective was to explore force functions and parameters and methods of applying them in terms of their efficacy regarding graph embedding applications. We found some force functions that outperformed the state-of-the-art methods.</p><p dir="ltr">The author of this manuscript believes that the proposed paradigm will open a new chapter, specifically in the field of graph embedding and generally in the field of embedding.</p>

<p dir="ltr">Current artificial intelligence (AI) systems are proficient at tasks in a closed-world setting where the rules are often rigid. However, in real-world applications, the environment is usually open and dynamic. In this work, we investigate the effects of such dynamic environments on AI systems and develop ways to mitigate those effects. Central to our exploration is the concept of \textit{novelties}. Novelties encompass structural changes, unanticipated events, and environmental shifts that can confound traditional AI systems. We categorize novelties based on their representation, anticipation, and impact on agents, laying the groundwork for systematic detection and adaptation strategies. We explore novelties in the context of stochastic games. Decision-making in stochastic games exercises many aspects of the same reasoning capabilities needed by AI agents acting in the real world. A multi-agent stochastic game allows for infinitely many ways to introduce novelty. We propose an extension of the deep reinforcement learning (DRL) paradigm to develop agents that can detect and adapt to novelties in these environments. To address the sample efficiency challenge in DRL, we introduce a hybrid approach that combines fixed-policy methods with traditional DRL techniques, offering enhanced performance in complex decision-making tasks. We present a novel method for detecting anticipated novelties in multi-agent games, leveraging information theory to discern patterns indicative of collusion among players. Finally, we introduce DABLER, a pioneering deep reinforcement learning architecture that dynamically adapts to changing environmental conditions through broad learning approaches and environment recognition. Our findings underscore the importance of developing AI systems equipped to navigate the uncertainties of the open world, offering promising pathways for advancing AI research and application in real-world settings.</p>

<p>The availability of abundant multimodal data, including textual, visual, and sensor-based information, holds the potential to improve decision-making in diverse domains. Extracting data-driven decision-making information from heterogeneous and changing datasets in real-world data-centric applications requires achieving complementary functionalities of multimodal data integration, knowledge extraction and mining, situationally-aware data recommendation to different users, and uncertainty management in the open-world setting. To achieve a system that encompasses all of these functionalities, several challenges need to be effectively addressed: (1) How to represent and analyze heterogeneous source contents and application context for multimodal data recommendation? (2) How to predict and fulfill current and future needs as new information streams in without user intervention? (3) How to integrate disconnected data sources and learn relevant information to specific mission needs? (4) How to scale from processing petabytes of data to exabytes? (5) How to deal with uncertainties in open-world that stem from changes in data sources and user requirements?</p> <p><br></p> <p>This dissertation tackles these challenges by proposing novel frameworks, learning-based data integration and retrieval models, and algorithms to empower decision-makers to extract valuable insights from diverse multimodal data sources. The contributions of this dissertation can be summarized as follows: (1) We developed SKOD, a novel multimodal knowledge querying framework that overcomes the data representation, scalability, and data completeness issues while utilizing streaming brokers and RDBMS capabilities with entity-centric semantic features as an effective representation of content and context. Additionally, as part of the framework, a novel text attribute recognition model called HART was developed, which leveraged language models and syntactic properties of large unstructured texts. (2) In the SKOD framework, we incrementally proposed three different approaches for data integration of the disconnected sources from their semantic features to build a common knowledge base with the user information need: (i) EARS: A mediator approach using schema mapping of the semantic features and SQL joins was proposed to address scalability challenges in data integration; (ii) FemmIR: A data integration approach for more susceptible and flexible applications, that utilizes neural network-based graph matching techniques to learn coordinated graph representations of the data. It introduces a novel graph creation approach from the features and a novel similarity metric among data sources; (iii) WeSJem: This approach allows zero-shot similarity matching and data discovery by using contrastive learning<br> to embed data samples and query examples in a high-dimensional space using features as a novel source of supervision instead of relevance labels. (3) Finally, to manage uncertainties in multimodal data management for open-world environments, we characterized novelties in multimodal information retrieval based on data drift. Moreover, we proposed a novelty detection and adaptation technique as an augmentation to WeSJem.<br> </p> <p>The effectiveness of the proposed frameworks, models, and algorithms was demonstrated<br> through real-world system prototypes that solved open problems requiring large-scale human<br> endeavors and computational resources. Specifically, these prototypes assisted law enforcement officers in automating investigations and finding missing persons.<br> </p>

<p>The swift emergence and wide-ranging utilization of machine learning (ML) across various industries, including healthcare, transportation, and robotics, have underscored the escalating need for efficient, scalable, and privacy-preserving solutions. Recognizing this, we present an integrated examination of three novel frameworks, each addressing different aspects of distributed learning and privacy issues: Two Timescale Hybrid Federated Learning (TT-HF), Delay-Aware Federated Learning (DFL), and Differential Privacy Hierarchical Federated Learning (DP-HFL). TT-HF introduces a semi-decentralized architecture that combines device-to-server and device-to-device (D2D) communications. Devices execute multiple stochastic gradient descent iterations on their datasets and sporadically synchronize model parameters via D2D communications. A unique adaptive control algorithm optimizes step size, D2D communication rounds, and global aggregation period to minimize network resource utilization and achieve a sublinear convergence rate. TT-HF outperforms conventional FL approaches in terms of model accuracy, energy consumption, and resilience against outages. DFL focuses on enhancing distributed ML training efficiency by accounting for communication delays between edge and cloud. It also uses multiple stochastic gradient descent iterations and periodically consolidates model parameters via edge servers. The adaptive control algorithm for DFL mitigates energy consumption and edge-to-cloud latency, resulting in faster global model convergence, reduced resource consumption, and robustness against delays. Lastly, DP-HFL is introduced to combat privacy vulnerabilities in FL. Merging the benefits of FL and Hierarchical Differential Privacy (HDP), DP-HFL significantly reduces the need for differential privacy noise while maintaining model performance, exhibiting an optimal privacy-performance trade-off. Theoretical analysis under both convex and nonconvex loss functions confirms DP-HFL’s effectiveness regarding convergence speed, privacy performance trade-off, and potential performance enhancement with appropriate network configuration. In sum, the study thoroughly explores TT-HF, DFL, and DP-HFL, and their unique solutions to distributed learning challenges such as efficiency, latency, and privacy concerns. These advanced FL frameworks have considerable potential to further enable effective, efficient, and secure distributed learning.</p>

The convergence of various technological and operational advancements has reinstated the interest in On-Demand Air Service (ODAS) as a viable mode of transportation. ODAS enables an end-user to be transported in an aircraft between their desired origin and destination at their preferred time without advance notice. Industry, academia, and the government organizations are collaborating to create technology solutions suited for large-scale implementation of this mode of transportation. Market studies suggest reducing vehicle operating cost per passenger as one of the biggest enablers of this market. To enable ODAS, an ODAS operator controls a fleet of aircraft that are deployed across a set of nodes (e.g., airports, vertiports) to satisfy end-user transportation requests. There is a gap in the literature for a tractable and online methodology that can enable ride-sharing in the on-demand operations while maintaining a publicly acceptable level of service (such as with low waiting time). The need for an approach that not only supports a dynamic-stochastic formulation but can also handle uncertainty with unknowable properties, drives me towards the field of Reinforcement Learning (RL). In this work, a novel two-layer hierarchical RL framework is proposed that can distribute a fleet of aircraft across a nodal network as well as perform real-time scheduling for an ODAS operator. The top layer of the framework - the Fleet Distributor - is modeled as a Partially Observable Markov Decision Process whereas the lower layer - the Trip Request Manager - is modeled as a Semi-Markov Decision Process. This framework is successfully demonstrated and assessed through various studies for a hypothetical ODAS operator in the Chicago region. This approach provides a new way of solving fleet distribution and scheduling problems in aviation. It also bridges the gap between the state-of-the-art RL advancements and node-based transportation network problems. Moreover, this work provides a non-proprietary approach to reasonably model ODAS operations that can be leveraged by researchers and policy makers.

<p dir="ltr">Deep Neural Networks (DNNs) successfully perform object detection tasks, and the Con- volutional Neural Network (CNN) backbone is a commonly used feature extractor before secondary tasks such as detection, classification, or segmentation. In a DNN model, the relationship between the features learned by the model from the training data and the features leveraged by the model during test and deployment has motivated the area of feature interpretability studies. The work presented here applies equally to white-box and black-box models and to any DNN architecture. The metrics developed do not require any information beyond the feature vector generated by the feature extraction backbone. These methods are therefore the first methods capable of estimating black-box model robustness in terms of latent space complexity and the first methods capable of examining feature representations in the latent space of black box models.</p><p dir="ltr">This work contributes the following four novel methodologies and results. First, a method for quantifying the invariance and/or equivariance of a model using the training data shows that the representation of a feature in the model impacts model performance. Second, a method for quantifying an observed domain gap in a dataset using the latent feature vectors of an object detection model is paired with pixel-level augmentation techniques to close the gap between real and synthetic data. This results in an improvement in the model’s F1 score on a test set of outliers from 0.5 to 0.9. Third, a method for visualizing and quantifying similarities of the latent manifolds of two black-box models is used to correlate similar feature representation with increase success in the transferability of gradient-based attacks. Finally, a method for examining the global complexity of decision boundaries in black-box models is presented, where more complex decision boundaries are shown to correlate with increased model robustness to gradient-based and random attacks.</p>

<p dir="ltr">Axial spondyloarthritis (axSpA), a disease that due to its complexity and rarity, presents challenges in diagnosis. With a focus on integrating expert knowledge into an intelligent diagnostic system, the research explores the intricate nature of axSpA, emphasizing the challenges associated with its diverse clinical presentation. By leveraging a comprehensive knowledge base curated by domain experts, encompassing insights into pathophysiology, genetic factors, and evolving diagnostic criteria of axSpA, the expert system strives to provide a nuanced understanding of the disease. The methodology employs a hybrid reasoning approach, combining both forward and backward chaining techniques. Forward chaining iteratively processes clinical data and available evidence, applying logical rules to infer potential diagnoses and refine hypotheses, while backward chaining starts with the desired diagnostic goal and works backward through the knowledge base to validate or refute hypotheses. Additionally, certainty theory is incorporated to manage uncertainty in the diagnostic process, assigning confidence levels to conclusions based on the strength of evidence and expert knowledge. By integrating knowledge base, forward and backward chaining, and certainty theory, the research aims to enhance diagnostic precision for this less common yet impactful inflammatory rheumatic condition, emphasizing the importance of early and accurate identification for effective management and improved patient outcomes. The results indicate a significant improvement in diagnostic accuracy, sensitivity, and specificity compared to traditional methods. The system's potential to enhance early diagnosis and treatment outcomes is discussed, along with suggestions for future research to further refine and expand the system.</p>

Cognitive autonomy of an autonomous system depends on its cyber module's ability to comprehend the actions and intent of the applications and services running on that system. The autonomous system should be able to accomplish this without or with limited human intervention. These mission-critical autonomous systems are often deployed in unpredictable and dynamic environments and are vulnerable to evasive cyberattacks. In particular, some of these cyberattacks are Advanced Persistent Threats where an attacker conducts reconnaissance for a long period time to ascertain system features, learn system defenses, and adapt to successfully execute the attack while evading detection. Thus an autonomous system's cognitive autonomy and cybersecurity intelligence depend on its capability to learn, classify applications (good and bad), predict the attacker's next steps, and remain operational to carryout the mission-critical tasks even under cyberattacks. In this dissertation, we propose novel learning and prediction models for enhancing cognitive autonomy and cybersecurity in autonomous systems. We develop (1) a model using deep learning along with a model selection framework that can classify benign and malicious operating contexts of a system based on performance counters, (2) a deep learning based natural language processing model that uses instruction sequences extracted from the memory to learn and profile the behavior of evasive malware, (3) a scalable deep learning based object detection model with data pre-processing assisted by fuzzy-based clustering, (4) fundamental guiding principles for cognitive autonomy using Artificial Intelligence (AI), (5) a model for privacy-preserving autonomous data analytics, and finally (6) a model for backup and replication based on combinatorial balanced incomplete block design in order to provide continuous availability in mission-critical systems. This research provides effective and computationally efficient deep learning based solutions for detecting evasive cyberattacks and increasing autonomy of a system from application-level to hardware-level. <br>

<p>Technological advances have a profound impact on people and the world in which they live. People use a wide range of smart devices, such as the Internet of Things (IoT), smartphones, and wearable devices, on a regular basis, all of which store and use location data. With this explosion of technology, these devices have been playing an essential role in digital forensics and crime investigations. Digital forensic professionals have become more able to acquire and assess various types of data and locations; therefore, location data has become essential for responders, practitioners, and digital investigators dealing with digital forensic cases that rely heavily on digital devices that collect data about their users. It is very beneficial and critical when performing any digital/cyber forensic investigation to consider answering the six Ws questions (i.e., who, what, when, where, why, and how) by using location data recovered from digital devices, such as where the suspect was at the time of the crime or the deviant act. Therefore, they could convict a suspect or help prove their innocence. However, many digital forensic standards, guidelines, tools, and even the National Institute of Standards and Technology (NIST) Cyber Security Personnel Framework (NICE) lack full coverage of what location data can be, how to use such data effectively, and how to perform spatial analysis. Although current digital forensic frameworks recognize the importance of location data, only a limited number of data sources (e.g., GPS) are considered sources of location in these digital forensic frameworks. Moreover, most digital forensic frameworks and tools have yet to introduce geo-contextualization techniques and spatial analysis into the digital forensic process, which may aid digital forensic investigations and provide more information for decision-making. As a result, significant gaps in the digital forensics community are still influenced by a lack of understanding of how to properly curate geodata. Therefore, this research was conducted to develop a transdisciplinary framework to deal with the limitations of previous work and explore opportunities to deal with geodata recovered from digital evidence by improving the way of maintaining geodata and getting the best value from them using an iPhone case study. The findings of this study demonstrated the potential value of geodata in digital disciplinary investigations when using the created transdisciplinary framework. Moreover, the findings discuss the implications for digital spatial analytical techniques and multi-intelligence domains, including location intelligence and open-source intelligence, that aid investigators and generate an exceptional understanding of device users' spatial, temporal, and spatial-temporal patterns.</p>

<p>A thesis study investigating the development and evaluation of a computer vision (CV) system for a manufacturing assembly task is reported. The CV inference results are compared to a Manufacturing Process Plan and an automation method completes a buyoff in the software, Solumina. Research questions were created and three hypotheses were tested. A literature review was conducted recognizing little consensus of Industry 4.0 technology adoption in manufacturing industries. Furthermore, the literature review uncovered the need for additional research within the topic of CV. Specifically, literature points towards more research regarding the cognitive capabilities of CV in manufacturing. A CV system was developed and evaluated to test for 90% or greater confidence in part detection. A CV dataset was developed and the system was trained and validated with it. Dataset contextualization was leveraged and evaluated, as per literature. A CV system was trained from custom datasets, containing six classes of part. The pre-contextualization dataset and post-contextualization dataset was compared by a Two-Sample T-Test and statistical significance was noted for three classes. A python script was developed to compare as-assembled locations with as-defined positions of components, per the Manufacturing Process Plan. A comparison of yields test for CV-based True Positives (TPs) and human-based TPs was conducted with the system operating at a 2σ level. An automation method utilizing Microsoft Power Automate was developed to complete the cognitive functionality of the CV system testing, by completing a buyoff in the software, Solumina, if CV-based TPs were equal to or greater than human-based TPs.</p>