-
Prospective Students
-
Faculty and Staff
-
Current Students
-
Alumni and Friends
Machine learning has risen to the forefront of scientific research due to its unparalleled predictive capabilities. As a result, researchers have become increasingly interested in uncovering the underlying causal structures that govern the relationships between variables in a system. These causal structures, often represented as directed acyclic graphs (DAGs), provide insights into how changes in one variable may directly or indirectly affect other variables, enabling a deeper understanding of the complex interactions within the system. While it is essential to constrain a model by minimizing spurious correlations and conducting "What-If" analyses, learning causal relationships from observational data, known as causal discovery, remains an active and challenging research area. This is due to factors like finite sampling, unobserved confounding factors, and measurement errors. Current approaches, including constraint-based and score-based methods, often struggle with high computational complexity because of the combinatorial nature of estimating DAGs. Inspired by the workshop on the Causality Challenge 'Cause-Effect Pair' at the Neural Information Processing Systems in 2013, this dissertation adopts a novel approach, generating a probability distribution over all possible graphs based on cause-effect pair features proposed in response to the workshop challenge.
The primary goal of this study is to develop new methods that leverage this probabilistic information and assess their performance. Furthermore, this work introduces a novel causal feature selection (CFS) algorithm using this approach and the establishment of a new evaluation criterion for CFS. To further enhance experimental performance, this dissertation proposes the use of a Graph Neural Networks (GNNs)--based probabilistic predictive framework for causal discovery. Conventional causal discovery algorithms face significant challenges in dealing with large-scale observational datasets and capturing global structural information. The GNN-based approach addresses these limitations, enabling the learning of complex causal structures directly from data augmented with statistical and information-theoretic measures. The proposed framework represents a significant leap forward in causal discovery, offering improved accuracy and scalability in both synthetic and real-world datasets, as well as introducing a novel synergy between probabilistic learning and causal graph analysis.
In addition to the methodological advancements, this dissertation includes an application of counterfactual analysis to study affective polarization on social media. By comparing scenarios with and without specific influencer-led conversations on platforms like Twitter, I analyze the impact of these conversations on public sentiment. This application highlights the practical implications of the proposed causal modeling techniques, demonstrating their utility in understanding real-world issues and contributing to the broader field of social media analysis.
Electrical fires caused by arc faults necessitate advanced detection methods for improved safety and reliability in AC and DC power systems. This research introduces innovative artificial intelligence (AI)-based methods for the efficient detection of arc faults, enhancing both safety and reliability in electrical systems. For AC systems, we developed a convolutional neural network (CNN)-based arc fault detection algorithm that autonomously extracts arc fault features without manual thresholding. Using raw current as input, the algorithm achieves an arc fault detection accuracy of 99.47%. Additionally, this research determined an optimal sampling rate of 10 kHz for the input current. The model's efficacy was verified using the Raspberry Pi 3B platform.
While traditional CNN algorithms have high accuracy, they require optimization for real-time arc fault detection on resource-limited hardware. To address this, we proposed a lightweight CNN architecture combined with a model compression technique using a knowledge distillation-based teacher-student algorithm. This model maintains a high detection accuracy of 99.31% and operates with an impressively minimal runtime of 0.20 milliseconds per sample when implemented on the Raspberry Pi 3B platform. This performance demonstrates its suitability for commercial embedded microcontrollers (MCUs) with limited computational capability.
Extending our research to DC systems, we introduced a cost-effective, AI-driven Arc Fault Circuit Interrupter (AFCI) for DC applications. Utilizing an STM32 MCU and a silicon carbide (SiC) MOSFET-based solid-state circuit breaker (SSCB), the proposed method achieves a detection accuracy of 98.15% with a remarkable arc fault interruption time of 25 milliseconds. This AFCI solution stands out for its rapid response and high reliability, promising significant improvements in safety for DC systems.
Together, these contributions signify a leap forward in electrical safety, presenting viable solutions for the timely detection and interruption of arc faults in AC and DC systems. The outcomes of this research are expected to influence future standards and practices in electrical safety management across residential, commercial, and industrial sectors.
Social media has emerged as a common platform for knowledge sharing and exchange in online communities. However, it has also become a hotbed for the diffusion of irregular content. Content moderation is crucial for maintaining a safe and healthy online environment by regulating the distribution of user-generated content (UGC).
Engaging users in content moderation fosters a sense of shared responsibility and empowers them to actively shape the environment of online communities. Leveraging the expertise of moderators leads to a deeper contextual understanding of content, thereby improving the overall consistency and legitimacy of content moderation in compliance with community or platform guidelines. Nevertheless, the collaborative effort of a more inclusive and community-driven moderation process remains unexplored by previous studies. While there is increasing attention to fairness, transparency, and ethics in content moderation, prior research often assesses content moderation perceptions of users, platforms, moderators, and bystanders in isolation. This results in a lack of comprehensive understanding of user perceptions in content moderation decision-making.
To address these limitations, this research proposes UMCollab, a user-moderator collaborative content moderation framework that incorporates the dynamics of user engagement and the domain knowledge of moderators into deep learning models to facilitate content moderation decision-making. Additionally, this research empirically investigates user perceptions of content moderation from the perspectives of content familiarity, content diversity, and user roles.
UMCollab leverages graph learning to model user engagement, which is further enhanced by the credibility and stance of users' online discussions. It also employs attention mechanisms to learn the domain knowledge of moderators based on their decisions regarding UGC per online community rules. Moreover, this study conducts an online user study by asking participants with diverse online engagement backgrounds and roles to complete a series of content moderation decision-making tasks and evaluate their perceptions of content moderation.
The findings of this dissertation research hold significant promise for promoting effectiveness, fairness, transparency, and community ownership in moderating UGC in social media, offering opportunities to improve the safety and success of online communities.
The advancement of medical imaging has significantly enhanced the ability to diagnose, monitor, and treat cancer. This dissertation focuses on the development of deep learning methodologies for the segmentation and registration of medical images, specifically Positron Emission Tomography (PET), Computed Tomography (CT), Magnetic Resonance Imaging (MRI), and pathology images, to improve the accuracy and efficiency of cancer diagnosis and treatment planning.
Segmentation, the process of delineating anatomical structures and pathological regions, is a crucial step in medical image analysis. This work introduces novel high-precision deep learning models for the automatic segmentation of tumors and organs at risk (OARs). These models utilize convolutional neural networks (CNNs) and transformer-based architectures to handle the complexities and variations inherent in PET, CT, and MRI. The segmentation models are trained on multi-modal imaging datasets, incorporating advanced techniques such as data augmentation, transfer learning, and ensemble learning to enhance robustness and generalization. Evaluation on various datasets demonstrates that these models achieve superior performance compared to traditional methods, with significant improvements in accuracy and reliability.
Registration, which aligns images from different modalities or time points, is another critical component in the analysis of medical images. This dissertation presents advanced deep learning approaches for the registration of CT, MRI, and pathology images, leveraging deep neural networks (DNNs) and unsupervised learning techniques. The proposed registration methods employ spatial transformer networks (STNs) and other novel architectures to learn complex spatial transformations directly from the data, enabling accurate alignment of multi-modal images. These approaches are designed to be computationally efficient and scalable, facilitating their integration into clinical workflows.
Our final goal is to streamline these deep learning methods to real clinical applications. This dissertation explores the practical applications of the developed models, including their deployment in microservices for common radiotherapy imaging tasks. The models are made accessible via Python scripts for clinical treatment planning software such as RayStation, allowing seamless integration into existing clinical systems. Evaluation using images and treatment planning data for prostate cancer underscores the potential of these models to enhance the quality of treatment planning and streamline the overall process of planning, response assessment, and adaptation. Additionally, this dissertation investigates the potential of federated learning for collaborative model training across multiple institutions without sharing sensitive patient data. This approach could enhance model robustness and generalizability by leveraging diverse datasets from various sources.
In conclusion, this dissertation explores the critical component of medical imaging for cancer diagnosis, monitoring, and treatment with advanced deep learning methods. We hope these innovative techniques developed in this research pave the way for more precise, efficient, and individualized patient care in oncology.
People adopt security technologies and make security decisions based on their perceptions, or mental models, of what risks they have and what they can do to protect their devices. Thus, people rely on their mental models to decide how to use their computing devices and the consequences of these actions. Understanding why users make security decisions and addressing the misconceptions in their mental models, specifically regarding security risks, can help prevent security mistakes made by users and help determine how to help users make good security decisions. This dissertation seeks to understand how users perceive security risks, why they make security-related decisions, and where they have misconceptions. In my dissertation, I examine how users' mental models of security and privacy differ by device platform, how that impacts how people use and interact with applications on each platform, and how user’s mental models can be used to influence adoption of good device security practices. I will present the results of three user studies exploring user mental models of security and privacy and how users need an increasing awareness of security risks and measures across all types of computing platforms in order to adopt appropriate practices to protect themselves and their information.
Physical activity offers a range of health benefits but can be difficult to initiate and maintain. Self-regulatory processes are one route to understanding health behavior change. While affective mechanisms like positive affect and reward processing provide a valuable neurobiological pathway to elucidate individual motivations for physical activity. Theories and models that emphasize the role of affect and intrinsic and extrinsic motivations are applied in the current study to deepen our understanding of physical activity behaviors. Psychosocial sources of individual motivations, such as improving mood or changing one’s physical appearance, can provide insight into ways to alter affective-cognitive mechanisms to encourage sustainable physical activity behaviors. The present study applied a mixed-method approach to elucidate themes of affect and motivation in social media content. A sample of 2,585 Twitter posts were collected in mid-July 2022. A motivational and health behavior change qualitative codebook was first developed to guide thematic coding analyses. Thematic coding results revealed a high frequency of extrinsic motivation and goal and change-oriented facilitators of physical activity. Intrinsic motivation included the highest percentage of positive attitudes compared to other motivation types. Health-oriented themes, satisfaction, dissatisfaction with physical appearance, and weight loss were also relevant. LIWC-22 analyses supported the role of positive affect and informed health themes. BERT topic modeling analyses provided overarching physical activity topic themes for motivation and physical activity. Interpretations of the current results were presented, and future directions were suggested.
Due to inherent restrictions in human driving behavior and information access, freeway congestion and stop-and-go behavior are nearly unavoidable. The adverse impacts include increased safety risks, longer travel times, and excessive fuel consumption. Various techniques (e.g., Variable Speed Limit (VSL), which is also known as Dynamic Speed Harmonization (DSH)), have been proposed to dampen traffic oscillation and smooth traffic speed. However, the effectiveness of the VSL is related to the compliance rates of drivers. Fortunately, new opportunities are emerging with the development of Connected and Automated Vehicles (CAVs) that can completely comply with the control system. The objective of this study is to investigate the effects of coordinated speed control in mixed traffic flow involving Human-Driven Vehicles (HDVs) and CAVs on the freeway. Therefore, a control strategy based on Deep Reinforcement learning (DRL) is developed to better understand how CAVs can improve operational performance. To evaluate and quantify the impact, a comprehensive performance framework is formulated. A series of numerical experiments will be conducted under different market penetration rates (MPRs) under various simulated scenarios. The overall intent of this study is to inform practitioners about the potential interactions between MOEs in implementing specific control strategies in a CAV environment.
Nanotechnology has the potential to revolutionize various fields, addressing complex issues such as cancer treatment, waste remediation, and energy storage. To achieve this, precise engineering of nanocrystals at the atomic level is essential, going beyond mere control of size and shape. The unique properties of nanomaterials, which differ from their bulk counterparts, are influenced by surface chemistry, defects, and local structure. These characteristics are determined by the synthesis methods used, making a deep mechanistic understanding of these processes crucial for engineering nanoscale structures and properties.
To contribute to the rapidly evolving field of nanoscience, this dissertation focuses on the solution-based synthesis of vanadium oxide nanocrystals. Vanadium oxides are promising candidates for applications in catalysis, sensing, cathode materials for high-density lithium batteries, smart windows, neuromorphic computing, and optical switching. However, vanadium oxides exhibit multiple oxidation states (+2 to +5) and polymorphs. Consequently, the colloidal synthesis of high-quality vanadium oxide nanocrystals in a specific oxidation state and stoichiometry remains challenging.
This dissertation advances the synthesis of vanadium oxide nanocrystals, emphasizing the effects of synthetic parameters on their oxidation state and crystal structure. Key findings include the successful synthesis of anosovite V₃O₅ nanocrystals via a hot-injection method, marking the first colloidal synthesis of this rare phase from a readily available precursor. By adjusting vanadium precursor-to-alcohol-to-amine ratio, controlled reduction of vanadium was achieved to selectively synthesize V₃O₅ and V₂O₃ nanocrystals. The dissertation also presents an alcohol-mediated valence-state controlled synthesis method for selective preparation of pure corundum-structured V₂O₃ and anosovite V₃O₅ nanocrystals. Comprehensive characterization, including spectroscopic ellipsometry and diffuse reflectance spectroscopy, reveals unique optical properties deviating from bulk behavior, attributed to the nanoscale size effects. In addition, a heat-up method was developed for synthesizing VOx nanocrystals by thermal decomposition of vanadyl acetylacetonate, demonstrating the formation of vanadium monoxide nanocrystals. The reaction pathways for the formation of these nanocrystals via hot-injection method and heat-up methods were analyzed with ATR-FTIR spectroscopy. The findings will advance the fundamental understanding of vanadium oxide nanocrystal synthesis and pave the way for their application as advanced functional nanomaterials.
Edge computing-assisted artificial intelligence (edge-AI) has enabled a new paradigm of smart applications that have very stringent latency requirements, especially for applications on mobile devices (e.g., smartphones, wearable devices, and autonomous vehicles). However, the high mobility of users and instability in wireless networks decrease the overall Quality-of-Service (QoS) of an edge-AI application running on mobile devices with non-linear battery discharge properties. The objective of this research is to provide mobile AI applications with an energy-efficient wireless infrastructure to enhance the overall QoS.
This dissertation presents a comprehensive experimental study of mobile AI applications, including a novel performance analysis modeling framework and a Gaussian process regression-based general predictive energy model, focusing on computational resource utilization, delay, and energy consumption. To enhance mobile AI performance, this dissertation presents a novel periodic predictive AoI-based service aggregation method for high-mobility AI applications, which processes information updates according to their update cycles with satisfactory latency. Furthermore, an H.264 video encoding-based edge-AI system is proposed to overcome the challenges posed by unstable wireless networks. Finally, a novel deep reinforcement learning-based smart edge-AI system is proposed in this research, where the edge server provides smart and dynamic offloading and data processing decisions.
The invention of advanced Ni-containing concentrated solid solution alloys has significantly broadened the compositional space of alloy design. Unlike conventional alloys that typically consist of a principal solvent element with minor additions of various solute atoms, concentrated solid solution alloys involve multiple elements in equal or near-equal compositions. These concentrated solid solution alloys have exhibited remarkable properties such as exceptional toughness and superior radiation resistance. The exceptional performance of these concentrated solid solution alloys is generally attributed to specific intrinsic properties of concentrated solid solution alloys such as high entropy effect, severe lattice distortion and short ordering effect. However, being relatively new emerging materials, the theoretical understanding and experimental exploration of these alloys are still ongoing and not comprehensively understood.
This dissertation work will provide a systematic investigation on surface properties including mechanical properties and radiation damage of Ni-based concentrated solid solution alloys by using ex-situ and in-situ indentation techniques. The study explores the surface properties of a batch of Ni-containing concentrated solid solution alloys with addition of different 3d transition elements including binary NiCo, NiFe, Ni80Cr20, Ni80Mn20 and quaternary NiCoFeCr. First, initial investigations use ex-situ nanoindentation to obtain mechanical properties of five alloys including hardness, elastic modulus and strain rate sensitivity. A complete methodology is developed to acquire accurate property information directly from nanoindentation in a high throughput manner, which considers the indentation size effect and pile-up effect. Furthermore, the strengthening in Ni-concentrated solid solution alloys is attributed to being driven by solid solution strengthening induced by mismatch in atomic size. Notably, the intrinsic properties of alloying elements play a more critical role in strengthening than the number of alloying elements. Second, based on previous work, nanoindentation is further employed to evaluate the early-stage irradiation induced hardening in NiCo, NiFe and NiCoFeCr. It proposes using nanoindentation to detect early-stage irradiation-induced defects and hypothesizes that interactions between these defects and dislocations carried by deformation during indentation can quantify irradiation-induced defects. This approach successfully quantifies irradiation-induced hardening in NiCo, NiFe, and NiCoFeCr. Quantitative analysis reveals that irradiation-induced defects harden NiFe and NiCoFeCr, but no significant hardening is observed in NiCo. Additionally, irradiation-induced hardening is associated with the evolution of geometrically necessary dislocations and is interpreted by changes in the plastic zone during indentation. Finally, in-situ flat-punch indentation provides real-time observations of deformation behaviors, aiming to derive accurate stress-strain curves. A new protocol addresses thermal drift effects and contact issues, often neglected in measurements.
This comprehensive study on Ni-based concentrated solid solution alloys enhances understanding of their mechanical properties and irradiation resistance by using ex-situ and in-situ nano-mechanical techniques. Methodologies are developed for nanoindentations to acquire meaningful property information directly from surface in a high throughput manner. This systematic work offers valuable insights into the strengthening mechanisms and irradiation hardening mechanisms of Ni-based concentrated solid solution alloys. The robust experimental evidence supports that the exceptional properties of concentrated solid solution alloys are not solely determined by the number of elements but also determined by the intrinsic performance of alloying elements. These results provide new insights for alloying design strategy of concentrated solid solution alloys.
