Computer Engineering Commons^™

Learning To Rig Characters, Zhan Xu

Doctoral Dissertations

With the emergence of 3D virtual worlds, 3D social media, and massive online games, the need for diverse, high-quality, animation-ready characters and avatars is greater than ever. To animate characters, artists hand-craft articulation structures, such as animation skeletons and part deformers, which require significant amount of manual and laborious interaction with 2D/3D modeling interfaces. This thesis presents deep learning methods that are able to significantly automate the process of character rigging. First, the thesis introduces RigNet, a method capable of predicting an animation skeleton for an input static 3D shape in the form of a polygon mesh. The predicted skeletons …

Deep Learning Based Power System Stability Assessment For Reduced Wecc System, Yinfeng Zhao

Doctoral Dissertations

Power system stability is the ability of power system, for a giving initial operating condition, to reach a new operation condition with most of the system variables bounded in normal range after subjecting to a short or long disturbance. Traditional power system stability mainly uses time-domain simulation which is very time consuming and only appropriate for offline assessment.

Nowadays, with increasing penetration of inverter based renewable, large-scale distributed energy storage integration and operation uncertainty brought by weather and electricity market, system dynamic and operating condition is more dramatic, and traditional power system stability assessment based on scheduling may not be …

Toward Generating Efficient Deep Neural Networks, Chengcheng Li

Doctoral Dissertations

Recent advances in deep neural networks have led to tremendous applications in various tasks, such as object classification and detection, image synthesis, natural language processing, game playing, and biological imaging. However, deploying these pre-trained networks on resource-limited devices poses a challenge, as most state-of- the-art networks contain millions of parameters, making them cumbersome and slow in real-world applications. To address this problem, numerous network compression and acceleration approaches, also known as efficient deep neural networks or efficient deep learning, have been investigated, in terms of hardware and software (algorithms), training, and inference. The aim of this dissertation is to study …

Learning With Limited Labeled Data For Image And Video Understanding, Razieh Kaviani Baghbaderani

Doctoral Dissertations

Deep learning-based algorithms have remarkably improved the performance in many computer vision tasks. However, deep networks often demand a large-scale and carefully annotated dataset and sufficient sample coverage of every training category. However, it is not practical in many real-world applications where only a few examples may be available, or the data annotation is costly and require expert knowledge. To mitigate this issue, learning with limited data has gained considerable attention and is investigated thorough different learning methods, including few-shot learning, weakly/semi supervised learning, open-set learning, etc.

In this work, the classification problem is investigated under an open-world assumption to …

Improving The Programmability Of Networked Energy Systems, Noman Bashir

Doctoral Dissertations

Global warming and climate change have underscored the need for designing sustainable energy systems. Sustainable energy systems, e.g., smart grids, green data centers, differ from the traditional systems in significant ways and present unique challenges to system designers and operators. First, intermittent renewable energy resources power these systems, which break the notion of infinite, reliable, and controllable power supply. Second, these systems come in varying sizes, spanning over large geographical regions. The control of these dispersed and diverse systems raises scalability challenges. Third, the performance modeling and fault detection in sustainable energy systems is still an active research area. Finally, …

Federated Agentless Detection Of Endpoints Using Behavioral And Characteristic Modeling, Hansaka Angel Dias Edirisinghe Kodituwakku

Doctoral Dissertations

During the past two decades computer networks and security have evolved that, even though we use the same TCP/IP stack, network traffic behaviors and security needs have significantly changed. To secure modern computer networks, complete and accurate data must be gathered in a structured manner pertaining to the network and endpoint behavior. Security operations teams struggle to keep up with the ever-increasing number of devices and network attacks daily. Often the security aspect of networks gets managed reactively instead of providing proactive protection. Data collected at the backbone are becoming inadequate during security incidents. Incident response teams require data that …

Towards Secure Deep Neural Networks For Cyber-Physical Systems, Jiangnan Li

Doctoral Dissertations

In recent years, deep neural networks (DNNs) are increasingly investigated in the literature to be employed in cyber-physical systems (CPSs). DNNs own inherent advantages in complex pattern identifying and achieve state-of-the-art performances in many important CPS applications. However, DNN-based systems usually require large datasets for model training, which introduces new data management issues. Meanwhile, research in the computer vision domain demonstrated that the DNNs are highly vulnerable to adversarial examples. Therefore, the security risks of employing DNNs in CPSs applications are of concern.

In this dissertation, we study the security of employing DNNs in CPSs from both the data domain …

Utility Scale Building Energy Modeling And Climate Impacts, Brett C. Bass

Doctoral Dissertations

Energy consumption is steadily increasing year over year in the United States (US). Climate change and anthropogenically forced shifts in weather have a significant impact on energy use as well as the resilience of the built environment and the electric grid. With buildings accounting for about 40% of total energy use in the US, building energy modeling (BEM) at a large scale is critical. This work advances that effort in a number of ways. First, current BEM approaches, their ability to scale to large geographical areas, and global climate models are reviewed. Next, a methodology for large-scale BEM is illustrated, …

An Analysis Of Modern Password Manager Security And Usage On Desktop And Mobile Devices, Timothy Oesch

Doctoral Dissertations

Security experts recommend password managers to help users generate, store, and enter strong, unique passwords. Prior research confirms that managers do help users move towards these objectives, but it also identified usability and security issues that had the potential to leak user data or prevent users from making full use of their manager. In this dissertation, I set out to measure to what extent modern managers have addressed these security issues on both desktop and mobile environments. Additionally, I have interviewed individuals to understand their password management behavior.

I begin my analysis by conducting the first security evaluation of the …

Towards Optimized Traffic Provisioning And Adaptive Cache Management For Content Delivery, Aditya Sundarrajan

Doctoral Dissertations

Content delivery networks (CDNs) deploy hundreds of thousands of servers around the world to cache and serve trillions of user requests every day for a diverse set of content such as web pages, videos, software downloads and images. In this dissertation, we propose algorithms to provision traffic across cache servers and manage the content they host to achieve performance objectives such as maximizing the cache hit rate, minimizing the bandwidth cost of the network and minimizing the energy consumption of the servers. Traffic provisioning is the process of determining the set of content domains hosted on the servers. We propose …

Function And Dissipation In Finite State Automata - From Computing To Intelligence And Back, Natesh Ganesh

Doctoral Dissertations

Society has benefited from the technological revolution and the tremendous growth in computing powered by Moore's law. However, we are fast approaching the ultimate physical limits in terms of both device sizes and the associated energy dissipation. It is important to characterize these limits in a physically grounded and implementation-agnostic manner, in order to capture the fundamental energy dissipation costs associated with performing computing operations with classical information in nano-scale quantum systems. It is also necessary to identify and understand the effect of quantum in-distinguishability, noise, and device variability on these dissipation limits. Identifying these parameters is crucial to designing …

Sparsity In Machine Learning: An Information Selecting Perspective, Siwei Feng

Doctoral Dissertations

Today we are living in a world awash with data. Large volumes of data are acquired, analyzed and applied to tasks through machine learning algorithms in nearly every area of science, business, and industry. For example, medical scientists analyze the gene expression data from a single specimen to learn the underlying causes of disease (e.g. cancer) and choose the best treatment; retailers can know more about customers' shopping habits from retail data to adjust their business strategies to better appeal to customers; suppliers can enhance supply chain success through supply chain systems built on knowledge sharing. However, it is also …

Modeling Temporal Structures In Time-Varying Networks, Kun Tu

Doctoral Dissertations

A dynamic network is a network whose structure changes because of the emergence and disappearance of node or edges. It can be used to study complex systems where individuals in a system are represented as nodes and their relations/interactions are represented as edges. Studying dynamic network structures helps to better understand changes in relationships. Considerable work has been conducted on learning network structure. However, due to the complexity of dynamic networks, there is considerable room for improvement to obtain better analysis results. This thesis studies different aspects of characteristic and dynamics of a network, focusing on their application in link …

Multi-Sensor Localization And Tracking In Disaster Management And Indoor Wayfinding For Visually Impaired Users, Zhuorui Yang

Doctoral Dissertations

This dissertation proposes a series of multi-sensor localization and tracking algorithms particularly developed for two important application domains, which are disaster management and indoor wayfinding for blind and visually impaired (BVI) users. For disaster management, we developed two different localization algorithms, one each for Radio Frequency Identification (RFID) and Bluetooth Low Energy (BLE) technology, which enable the disaster management system to track patients in real-time. Both algorithms work in the absence of any pre-deployed infrastructure along with smartphones and wearable devices. Regarding indoor wayfinding for BVI users, we have explored several types of indoor positioning techniques including BLE-based, inertial, visual …

Transiency-Driven Resource Management For Cloud Computing Platforms, Prateek Sharma

Doctoral Dissertations

Modern distributed server applications are hosted on enterprise or cloud data centers that provide computing, storage, and networking capabilities to these applications. These applications are built using the implicit assumption that the underlying servers will be stable and normally available, barring for occasional faults. In many emerging scenarios, however, data centers and clouds only provide transient, rather than continuous, availability of their servers. Transiency in modern distributed systems arises in many contexts, such as green data centers powered using renewable intermittent sources, and cloud platforms that provide lower-cost transient servers which can be unilaterally revoked by the cloud operator. Transient …

Power Laws In Complex Graphs: Parsimonious Generative Models, Similarity Testing Algorithms, And The Origins, Shan Lu

Doctoral Dissertations

This dissertation mainly discussed topics related to power law graphs, including graph similarity testing algorithms and power law generative models. For graph similarity testing, we proposed a method based on the mathematical theory of diffusion over manifolds using random walks over graphs. We show that our method not only distinguishes between graphs with different degree distributions, but also graphs with the same degree distributions. We compare the undirected power law graphs generated by Barabasi-Albert model and directed power law graphs generated by Krapivsky's model to the random graphs generated by Erdos-Renyi model. We also compare power law graphs generated by …

Modeling The Consumer Acceptance Of Retail Service Robots, So Young Song

Doctoral Dissertations

This study uses the Computers Are Social Actors (CASA) and domestication theories as the underlying framework of an acceptance model of retail service robots (RSRs). The model illustrates the relationships among facilitators, attitudes toward Human-Robot Interaction (HRI), anxiety toward robots, anticipated service quality, and the acceptance of RSRs. Specifically, the researcher investigates the extent to which the facilitators of usefulness, social capability, the appearance of RSRs, and the attitudes toward HRI affect acceptance and increase the anticipation of service quality. The researcher also tests the inhibiting role of pre-existing anxiety toward robots on the relationship between these facilitators and attitudes …

Computational Imaging Approach To Recovery Of Target Coordinates Using Orbital Sensor Data, Michael D. Vaughan

Doctoral Dissertations

This dissertation addresses the components necessary for simulation of an image-based recovery of the position of a target using orbital image sensors. Each component is considered in detail, focusing on the effect that design choices and system parameters have on the accuracy of the position estimate. Changes in sensor resolution, varying amounts of blur, differences in image noise level, selection of algorithms used for each component, and lag introduced by excessive processing time all contribute to the accuracy of the result regarding recovery of target coordinates using orbital sensor data.

Using physical targets and sensors in this scenario would be …

Wide-Area Measurement-Driven Approaches For Power System Modeling And Analytics, Hesen Liu

Doctoral Dissertations

This dissertation presents wide-area measurement-driven approaches for power system modeling and analytics. Accurate power system dynamic models are the very basis of power system analysis, control, and operation. Meanwhile, phasor measurement data provide first-hand knowledge of power system dynamic behaviors. The idea of building out innovative applications with synchrophasor data is promising.

Taking advantage of the real-time wide-area measurements, one of phasor measurements’ novel applications is to develop a synchrophasor-based auto-regressive with exogenous inputs (ARX) model that can be updated online to estimate or predict system dynamic responses.

Furthermore, since auto-regressive models are in a big family, the ARX model …

A Probabilistic Software Framework For Scalable Data Storage And Integrity Check, Sisi Xiong

Doctoral Dissertations

Data has overwhelmed the digital world in terms of volume, variety and velocity. Data- intensive applications are facing unprecedented challenges. On the other hand, computation resources, such as memory, suffer from shortage comparing to data scale. However, in certain applications, it is a must to process large amount of data in a time efficient manner. Probabilistic approaches are compromises between these three perspectives: large amount of data, limited computation resources and high time efficiency, in the sense that those approaches cannot guarantee 100% correctness, their error rates, however, are predictable and adjustable depending on available computation resources and time constraints. …

Image Processing And Understanding Based On Graph Similarity Testing: Algorithm Design And Software Development, Jieqi Kang

Doctoral Dissertations

Image processing and understanding is a key task in the human visual system. Among all related topics, content based image retrieval and classification is the most typical and important problem. Successful image retrieval/classification models require an effective fundamental step of image representation and feature extraction. While traditional methods are not capable of capturing all structural information on the image, using graph to represent the image is not only biologically plausible but also has certain advantages. Graphs have been widely used in image related applications. Traditional graph-based image analysis models include pixel-based graph-cut techniques for image segmentation, low-level and high-level image …

Hyperspectral Data Acquisition And Its Application For Face Recognition, Woon Cho

Doctoral Dissertations

Current face recognition systems are rife with serious challenges in uncontrolled conditions: e.g., unrestrained lighting, pose variations, accessories, etc. Hyperspectral imaging (HI) is typically employed to counter many of those challenges, by incorporating the spectral information within different bands. Although numerous methods based on hyperspectral imaging have been developed for face recognition with promising results, three fundamental challenges remain: 1) low signal to noise ratios and low intensity values in the bands of the hyperspectral image specifically near blue bands; 2) high dimensionality of hyperspectral data; and 3) inter-band misalignment (IBM) correlated with subject motion during data acquisition.

This dissertation …

Application Of Techniques For Map Estimation To Distributed Constraint Optimization Problem, Yoonheui Kim

Doctoral Dissertations

The problem of efficiently finding near-optimal decisions in multi-agent systems has become increasingly important because of the growing number of multi-agent applications with large numbers of agents operating in real-world environments. In these systems, agents are often subject to tight resource constraints and agents have only local views. When agents have non-global constraints, each of which is independent, the problem can be formalized as a distributed constraint optimization problem (DCOP). The DCOP is closely associated with the problem of inference on graphical models. Many approaches from inference literature have been adopted to solve DCOPs. We focus on the Max-Sum algorithm …

On Applications Of Relational Data, Samamon Khemmarat

Doctoral Dissertations

With the advances of technology and the popularity of the Internet, a large amount of data is being generated and collected. Much of these data is relational data, which describe how people and things, or entities, are related to one another. For example, data from sale transactions on e-commerce websites tell us which customers buy or view which products. Analyzing the known relationships from relational data can help us to discover knowledge that can benefit businesses, organizations, and our lives. For instance, learning the products that are commonly bought together allows businesses to recommend products to customers and increase their …

Physically Equivalent Intelligent Systems For Reasoning Under Uncertainty At Nanoscale, Santosh Khasanvis

Doctoral Dissertations

Machines today lack the inherent ability to reason and make decisions, or operate in the presence of uncertainty. Machine-learning methods such as Bayesian Networks (BNs) are widely acknowledged for their ability to uncover relationships and generate causal models for complex interactions. However, their massive computational requirement, when implemented on conventional computers, hinders their usefulness in many critical problem areas e.g., genetic basis of diseases, macro finance, text classification, environment monitoring, etc. We propose a new non-von Neumann technology framework purposefully architected across all layers for solving these problems efficiently through physical equivalence, enabled by emerging nanotechnology. The architecture builds …

Compressed Sensing In Resource-Constrained Environments: From Sensing Mechanism Design To Recovery Algorithms, Shuangjiang Li

Doctoral Dissertations

Compressed Sensing (CS) is an emerging field based on the revelation that a small collection of linear projections of a sparse signal contains enough information for reconstruction. It is promising that CS can be utilized in environments where the signal acquisition process is extremely difficult or costly, e.g., a resource-constrained environment like the smartphone platform, or a band-limited environment like visual sensor network (VSNs). There are several challenges to perform sensing due to the characteristic of these platforms, including, for example, needing active user involvement, computational and storage limitations and lower transmission capabilities. This dissertation focuses on the study of …

Scalable Hardware Efficient Deep Spatio-Temporal Inference Networks, Steven Robert Young

Doctoral Dissertations

Deep machine learning (DML) is a promising field of research that has enjoyed much success in recent years. Two of the predominant deep learning architectures studied in the literature are Convolutional Neural Networks (CNNs) and Deep Belief Networks (DBNs). Both have been successfully applied to many standard benchmarks with a primary focus on machine vision and speech processing domains.

Many real-world applications involve time-varying signals and, consequently, necessitate models that efficiently represent both temporal and spatial attributes. However, neither DBNs nor CNNs are designed to naturally capture temporal dependencies in observed data, often resulting in the inadequate transformation of spatio-temporal …

Integrating Non-Topical Aspects Into Information Retrieval, Elif Aktolga

Doctoral Dissertations

When users investigate a topic, they are often interested in results that are not just relevant, but also strongly opinionated or covering a range of times. To get such results, users are forced to formulate ambiguous, complex, or longer queries. Commonly this becomes a burden, since users need to issue several queries with reformulations if initial search results are not completely satisfactory. In this thesis, we focus on those two non-topical dimensions: opinionatedness and time. We develop measures for quantifying them in documents and incorporate them into search results. For improving search results with respect to non-topical dimensions, we use …

Feature Extraction And Recognition For Human Action Recognition, Jiajia Luo

Doctoral Dissertations

How to automatically label videos containing human motions is the task of human action recognition. Traditional human action recognition algorithms use the RGB videos as input, and it is a challenging task because of the large intra-class variations of actions, cluttered background, possible camera movement, and illumination variations. Recently, the introduction of cost-effective depth cameras provides a new possibility to address difficult issues. However, it also brings new challenges such as noisy depth maps and time alignment. In this dissertation, effective and computationally efficient feature extraction and recognition algorithms are proposed for human action recognition.

At the feature extraction step, …

Online Multi-Stage Deep Architectures For Feature Extraction And Object Recognition, Derek Christopher Rose

Doctoral Dissertations

Multi-stage visual architectures have recently found success in achieving high classification accuracies over image datasets with large variations in pose, lighting, and scale. Inspired by techniques currently at the forefront of deep learning, such architectures are typically composed of one or more layers of preprocessing, feature encoding, and pooling to extract features from raw images. Training these components traditionally relies on large sets of patches that are extracted from a potentially large image dataset. In this context, high-dimensional feature space representations are often helpful for obtaining the best classification performances and providing a higher degree of invariance to object transformations. …