Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Machine learning (5)
- Information Retrieval (3)
- Computer vision (2)
- Deep learning (2)
- Evaluation (2)
-
- Graphical models (2)
- Localization (2)
- Adaptive (1)
- Aerodynamics (1)
- Algorithms (1)
- App prediction (1)
- Approximate inference (1)
- Bayesian nonparametrics (1)
- Behavior awareness (1)
- Belief propagation (1)
- Causal discovery (1)
- Clustering (1)
- Communication intelligence (1)
- Computational complexity (1)
- Computational music analysis (1)
- Computational music theory (1)
- Computer Vision (1)
- Curve classification (1)
- Database (1)
- Deep models (1)
- Determinism (1)
- Digital Forensics (1)
- Digital libraries (1)
- Distributed computing (1)
- Domain-specific searches (1)
- Publication
- Publication Type
Articles 1 - 30 of 31
Full-Text Articles in Entire DC Network
Causal Discovery For Relational Domains: Representation, Reasoning, And Learning, Marc Maier
Causal Discovery For Relational Domains: Representation, Reasoning, And Learning, Marc Maier
Doctoral Dissertations
Many domains are currently experiencing the growing trend to record and analyze massive, observational data sets with increasing complexity. A commonly made claim is that these data sets hold potential to transform their corresponding domains by providing previously unknown or unexpected explanations and enabling informed decision-making. However, only knowledge of the underlying causal generative process, as opposed to knowledge of associational patterns, can support such tasks. Most methods for traditional causal discovery—the development of algorithms that learn causal structure from observational data—are restricted to representations that require limiting assumptions on the form of the data. Causal discovery has almost exclusively …
Inference-Based Forensics For Extracting Information From Diverse Sources, Robert J. Walls
Inference-Based Forensics For Extracting Information From Diverse Sources, Robert J. Walls
Doctoral Dissertations
Digital forensics is tasked with the examination and extraction of evidence from a diverse set of devices and information sources. While digital forensics has long been synonymous with file recovery, this label no longer adequately describes the science’s role in modern investigations. Spurred by evolving technologies and online crime, law enforcement is shifting the focus of digital forensics from its traditional role in the final stages of an investigation to assisting investigators in the earliest phases — often before a suspect has been identified and a warrant served. Investigators need new forensic techniques to investigate online crimes, such as child …
Efficient Routing And Scheduling In Wireless Networks, Anand Seetharam
Efficient Routing And Scheduling In Wireless Networks, Anand Seetharam
Doctoral Dissertations
The temporal and spatial variation in wireless channel conditions, node mobility make it challenging to design protocols for wireless networks. In this thesis, we design efficient routing and scheduling algorithms which adapt to changing network conditions caused by varying link quality or node mobility to improve user-level performance. We design and analyze routing protocols for static, mobile and heterogeneous wireless networks. We analyze the performance of opportunistic and cooperative forwarding in static mesh networks showing that opportunism outperforms cooperation; we identify interference as the main cause for mitigating the potential gains achievable with cooperative forwarding. For mobile networks, we quantitatively …
Using Formal Methods To Verify Transactional Abstract Concurrency Control, Trek S. Palmer
Using Formal Methods To Verify Transactional Abstract Concurrency Control, Trek S. Palmer
Doctoral Dissertations
Concurrent application design and implementation is more important than ever in today's multi-core processor world. Transactional Memory (TM) Concurrent application design and implementation is more important than ever in today's multi-core processor world. Transactional Memory (TM). Each has its own particular advantages and disadvantages. However, these techniques each need some extra information to `glue' the non-transactional operation into a transactional context. At the most general level, non-transactional code must be decorated in such a way that the TM run-time can determine how those non-transactional operations commute with one another, and how to `undo' the non-transactional operations in case the run-time …
Privacy-Preserving Sanitization In Data Sharing, Wentian Lu
Privacy-Preserving Sanitization In Data Sharing, Wentian Lu
Doctoral Dissertations
In the era of big data, the prospect of analyzing, monitoring and investigating all sources of data starts to stand out in every aspect of our life. The benefit of such practices becomes concrete only when analysts or investigators have the information shared from data owners. However, privacy is one of the main barriers that disrupt the sharing behavior, due to the fear of disclosing sensitive information. This dissertation describes data sanitization methods that disguise the sensitive information before sharing a dataset and our criteria are always protecting privacy while preserving utility as much as possible. In particular, we provide …
Computational Communication Intelligence: Exploring Linguistic Manifestation And Social Dynamics In Online Communication, Xiaoxi Xu
Doctoral Dissertations
We now live in an age of online communication. As social media becomes an integral part of our life, online communication becomes an essential life skill. In this dissertation, we aim to understand how people effectively communicate online. We research components of success in online communication and present scientific methods to study the skill of effective communication. This research advances the state of art in machine learning and communication studies. For communication studies, we pioneer the study of a communication phenomenon we call Communication Intelligence in online interactions. We create a theory about communication intelligence that measures participants’ ten high-order …
Retrieval Models Based On Linguistic Features Of Verbose Queries, Jae Hyun Park
Retrieval Models Based On Linguistic Features Of Verbose Queries, Jae Hyun Park
Doctoral Dissertations
Natural language expressions are more familiar to users than choosing keywords for queries. Given that, people can use natural language expressions to represent their sophisticated information needs. Instead of listing keywords, verbose queries are expressed in a grammatically well-formed phrase or sentence in which terms are used together to represent the more specific meanings of a concept, and the relationships of these concepts are expressed by function words. The goal of this thesis is to investigate methods of using the semantic and syntactic features of natural language queries to maximize the effectiveness of search. For this purpose, we propose the …
Designing Efficient And Accurate Behavior-Aware Mobile Systems, Abhinav Parate
Designing Efficient And Accurate Behavior-Aware Mobile Systems, Abhinav Parate
Doctoral Dissertations
The proliferation of sensors on smartphones, tablets and wearables has led to a plethora of behavior classification algorithms designed to sense various aspects of individual user's behavior such as daily habits, activity, physiology, mobility, sleep, emotional and social contexts. This ability to sense and understand behaviors of mobile users will drive the next generation of mobile applications providing services based on the users' behavioral patterns. In this thesis, we investigate ways in which we can enhance and utilize the understanding of user behaviors in such applications. In particular, we focus on identifying the key challenges in the following three aspects …
Searching Based On Query Documents, Youngho Kim
Searching Based On Query Documents, Youngho Kim
Doctoral Dissertations
Searches can start with query documents where search queries are formulated based on document-level descriptions. This type of searches is more common in domain-specific search environments. For example, in patent retrieval, one major search task is finding relevant information for new (query) patents, and search queries are generated from the query patents One unique characteristic of this search is that the search process can take longer and be more comprehensive, compared to general web search. As an example, to complete a single patent retrieval task, a typical user may generate 15 queries and examine more than 100 retrieved documents. In …
Defining, Evaluating, And Improving The Process Of Verifying Patient Identifiers, Junghee Jo
Defining, Evaluating, And Improving The Process Of Verifying Patient Identifiers, Junghee Jo
Doctoral Dissertations
Patient identification errors are a major cause of medication errors. During medication administration, failure to identify patients correctly can lead to patients receiving incorrect medications, perhaps resulting in adverse drug events and even death. Most medication error studies to date have focused on reporting patient misidentification statistics from case studies, on classifying types of patient identification errors, or on evaluating the impact of technology on the patient identification process, but few have proposed specific strategies or guidelines to decrease patient identification errors. This thesis aims to improve the verification of patient identifiers (VPI) process by making three key contributions to …
Adaptive Step-Sizes For Reinforcement Learning, William C. Dabney
Adaptive Step-Sizes For Reinforcement Learning, William C. Dabney
Doctoral Dissertations
The central theme motivating this dissertation is the desire to develop reinforcement learning algorithms that “just work” regardless of the domain in which they are applied. The largest impediment to this goal is the sensitivity of reinforcement learning algorithms to the step-size parameter used to rescale incremental updates. Adaptive step-size algorithms attempt to reduce this sensitivity or eliminate the step-size parameter entirely by automatically adjusting the step size throughout the learning process. Such algorithms provide an alternative to the standard “guess-and-check” methods used to find parameters known as parameter tuning. However, the problems with parameter tuning are currently masked by …
Streaming Algorithms Via Reductions, Michael S. Crouch
Streaming Algorithms Via Reductions, Michael S. Crouch
Doctoral Dissertations
In the "streaming algorithms" model of computation we must process data "in order" and without enough memory to remember the entire input. We study reductions between problems in the streaming model with an eye to using reductions as an algorithm design technique. Our contributions include: * "Linear Transformation" reductions, which compose with existing linear sketch techniques. We use these for small-space algorithms for numeric measurements of distance-from-periodicity, finding the period of a numeric stream, and detecting cyclic shifts. * The first streaming graph algorithms in the "sliding window'" model, where we must consider only the most recent L elements for …
Model-Driven Analytics Of Energy Meter Data In Smart Homes, Sean K. Barker
Model-Driven Analytics Of Energy Meter Data In Smart Homes, Sean K. Barker
Doctoral Dissertations
The proliferation of smart meter deployments has led to significant interest in analyzing home energy use as part of the emerging 'smart grid'. As buildings account for nearly 40% of society's energy use, data from smart meters provides significant opportunities for both utilities and consumers to optimize energy use, minimize waste, and provide insight into how modern homes and devices use energy. Meter data is often difficult to analyze, however, owing to the aggregation of many disparate and complex loads as well as relatively coarse measurement granularities. At utility scales, analysis is further complicated by the vast quantity of data, …
Subtyping With Generics: A Unified Approach, John G. Altidor
Subtyping With Generics: A Unified Approach, John G. Altidor
Doctoral Dissertations
Reusable software increases programmers' productivity and reduces repetitive code and software bugs. Variance is a key programming language mechanism for writing reusable software. Variance is concerned with the interplay of parametric polymorphism (i.e., templates, generics) and subtype (inclusion) polymorphism. Parametric polymorphism enables programmers to write abstract types and is known to enhance the readability, maintainability, and reliability of programs. Subtyping promotes software reuse by allowing code to be applied to a larger set of terms. Integrating parametric and subtype polymorphism while maintaining type safety is a difficult problem. Existing variance mechanisms enable greater subtyping between parametric types, but they suffer …
Scaling Mcmc Inference And Belief Propagation To Large, Dense Graphical Models, Sameer Singh
Scaling Mcmc Inference And Belief Propagation To Large, Dense Graphical Models, Sameer Singh
Doctoral Dissertations
With the physical constraints of semiconductor-based electronics becoming increasingly limiting in the past decade, single-core CPUs have given way to multi-core and distributed computing platforms. At the same time, access to large data collections is progressively becoming commonplace due to the lowering cost of storage and bandwidth. Traditional machine learning paradigms that have been designed to operate sequentially on single processor architectures seem destined to become obsolete in this world of multi-core, multi-node systems and massive data sets. Inference for graphical models is one such example for which most existing algorithms are sequential in nature and are difficult to scale …
Unsupervised Joint Alignment, Clustering And Feature Learning, Mohamed Marwan Mattar
Unsupervised Joint Alignment, Clustering And Feature Learning, Mohamed Marwan Mattar
Doctoral Dissertations
Joint alignment is the process of transforming instances in a data set to make them more similar based on a pre-defined measure of joint similarity. This process has great utility and applicability in many scientific disciplines including radiology, psychology, linguistics, vision, and biology. Most alignment algorithms suffer from two shortcomings. First, they typically fail when presented with complex data sets arising from multiple modalities such as a data set of normal and abnormal heart signals. Second, they require hand-picking appropriate feature representations for each data set, which may be time-consuming and ineffective, or outside the domain of expertise for practitioners. …
Reliable And Efficient Multithreading, Tongping Liu
Reliable And Efficient Multithreading, Tongping Liu
Doctoral Dissertations
The advent of multicore architecture has increased the demand for multithreaded programs. It is notoriously far more challenging to write parallel programs correctly and efficiently than sequential ones because of the wide range of concurrency errors and performance problems. In this thesis, I developed a series of runtime systems and tools to combat concurrency errors and performance problems of multithreaded programs. The first system, Dthreads, automatically ensures determinism for unmodified C/C++ applications using the pthreads library without requiring programmer intervention and hardware support. Dthreads greatly simplifies the understanding and debugging of multithreaded programs. Dthreads often matches or even exceeds the …
Incorporating Boltzmann Machine Priors For Semantic Labeling In Images And Videos, Andrew Kae
Incorporating Boltzmann Machine Priors For Semantic Labeling In Images And Videos, Andrew Kae
Doctoral Dissertations
Semantic labeling is the task of assigning category labels to regions in an image. For example, a scene may consist of regions corresponding to categories such as sky, water, and ground, or parts of a face such as eyes, nose, and mouth. Semantic labeling is an important mid-level vision task for grouping and organizing image regions into coherent parts. Labeling these regions allows us to better understand the scene itself as well as properties of the objects in the scene, such as their parts, location, and interaction within the scene. Typical approaches for this task include the conditional random field …
Making Networks Robust To Component Failures, Daniel Gyllstrom
Making Networks Robust To Component Failures, Daniel Gyllstrom
Doctoral Dissertations
In this thesis, we consider instances of component failure in the Internet and in networked cyber-physical systems, such as the communication network used by the modern electric power grid (termed the smart grid). We design algorithms that make these networks more robust to various component failures, including failed routers, failures of links connecting routers, and failed sensors. This thesis divides into three parts: recovery from malicious or misconfigured nodes injecting false information into a distributed system (e.g., the Internet), placing smart grid sensors to provide measurement error detection, and fast recovery from link failures in a smart grid communication …
A Proportionality-Based Approach To Search Result Diversification, Van Bac Dang
A Proportionality-Based Approach To Search Result Diversification, Van Bac Dang
Doctoral Dissertations
Search result diversification addresses the problem of queries with unclear information needs. The aim of using diversification techniques is to find a ranking of documents that covers multiple possible interpretations, aspects, or topics for a given query. By explicitly providing diversity in search results, this approach can increase the likelihood that users will find documents relevant to their specific intent, thereby improving effectiveness. This dissertation introduces a new perspective on diversity: diversity by proportionality. We consider a result list more diverse, with respect to some set of topics related to the query, when the ratio between the number of relevant …
Entity-Based Enrichment For Information Extraction And Retrieval, Jeffrey Dalton
Entity-Based Enrichment For Information Extraction And Retrieval, Jeffrey Dalton
Doctoral Dissertations
The goal of this work is to leverage cross-document entity relationships for improved understanding of queries and documents. We define an entity to be a thing or concept that exists in the world, such as a politician, a battle, a film, or a color. Entity-based enrichment (EBE) is a new expansion model for both queries and documents using features from similar entitymentions in the document collection and external knowledge resources. It uses task-specific features from entities beyond words that include: name aliases, fine-grained entity types, categories, and relationships to other entities. EBE addresses the problem of sparse or noisy local …
Private Void Death / Death, Zack Hardy
Efficient Representation And Matching Of Texts And Images In Scanned Book Collections, Ismet Zeki Yalniz
Efficient Representation And Matching Of Texts And Images In Scanned Book Collections, Ismet Zeki Yalniz
Doctoral Dissertations
Millions of books from public libraries and private collections have been scanned by various organizations in the last decade. The motivation is to preserve the written human heritage in electronic format for durable storage and efficient access. The information buried in these large book collections has always been of major interest for scholars from various disciplines. Several interesting research problems can be defined over large collections of scanned books given their corresponding optical character recognition (OCR) outputs. At the highest level, one can view the entire collection as a whole and discover interesting contextual relationships or linkages between the books. …
Indexing Proximity-Based Dependencies For Information Retrieval, Samuel Huston
Indexing Proximity-Based Dependencies For Information Retrieval, Samuel Huston
Doctoral Dissertations
Research into term dependencies for information retrieval has demonstrated that dependency retrieval models are able to consistently improve retrieval effectiveness over bag-of-words models. However, the computation of term dependency statistics is a major efficiency bottleneck in the execution of these retrieval models. This thesis investigates the problem of improving the efficiency of dependency retrieval models without compromising the effectiveness benefits of the term dependency features. Despite the large number of published comparisons between dependency models and bag-of-words approaches, there has been a lack of direct comparisons between alternate dependency models. We provide this comparison and investigate different types of proximity …
Improving Text Recognition In Images Of Natural Scenes, Jacqueline Feild
Improving Text Recognition In Images Of Natural Scenes, Jacqueline Feild
Doctoral Dissertations
The area of scene text recognition focuses on the problem of recognizing arbitrary text in images of natural scenes. Examples of scene text include street signs, business signs, grocery item labels, and license plates. With the increased use of smartphones and digital cameras, the ability to accurately recognize text in images is becoming increasingly useful and many people will benefit from advances in this area. The goal of this thesis is to develop methods for improving scene text recognition. We do this by incorporating new types of information into models and by exploring how to compose simple components into highly …
Probabilistic Models For Motion Segmentation In Image Sequences, Manjunath Narayana
Probabilistic Models For Motion Segmentation In Image Sequences, Manjunath Narayana
Doctoral Dissertations
Motion segmentation is the task of assigning a binary label to every pixel in an image sequence specifying whether it is a moving foreground object or stationary background. It is often an important task in many computer vision applications such as automatic surveillance and tracking systems. Depending on whether the camera is stationary or moving, different approaches are possible for segmentation. Motion segmentation when the camera is stationary is a well studied problem with many effective algorithms and systems in use today. In contrast, the problem of segmentation with a moving camera is much more complex. In this thesis, we …
A Probabilistic Model Of Hierarchical Music Analysis, Phillip Benjamin Kirlin
A Probabilistic Model Of Hierarchical Music Analysis, Phillip Benjamin Kirlin
Doctoral Dissertations
Schenkerian music theory supposes that Western tonal compositions can be viewed as hierarchies of musical objects. The process of Schenkerian analysis reveals this hierarchy by identifying connections between notes or chords of a composition that illustrate both the small- and large-scale construction of the music. We present a new probabilistic model of this variety of music analysis, details of how the parameters of the model can be learned from a corpus, an algorithm for deriving the most probable analysis for a given piece of music, and both quantitative and human-based evaluations of the algorithm's performance. In addition, we describe the …
Exploiting Energy Harvesting For Passive Embedded Computing Systems, Jeremy Joel Gummeson
Exploiting Energy Harvesting For Passive Embedded Computing Systems, Jeremy Joel Gummeson
Doctoral Dissertations
The key limitation in mobile computing systems is energy - without a stable power supply, these systems cannot process, store, or communicate data. This problem is of particular interest since the storage density of battery technologies do not follow scaling trends similar to Moore's law. This means that depending on application performance requirements and lifetime objectives, a battery may dominate the overall system weight and form factor; this could result in an overall size that is either inconvenient or unacceptable for a particular application. As device features have scaled down in size, entire embedded systems have been implemented on a …
Free Wake Potential Flow Vortex Wind Turbine Modeling: Advances In Parallel Processing And Integration Of Ground Effects, Nathaniel B. Develder
Free Wake Potential Flow Vortex Wind Turbine Modeling: Advances In Parallel Processing And Integration Of Ground Effects, Nathaniel B. Develder
Masters Theses 1911 - February 2014
Potential flow simulations are a great engineering type, middle-ground approach to modeling complex aerodynamic systems, but quickly become computationally unwieldy for large domains. An N-body problem with N-squared interactions to calculate, this free wake vortex model of a wind turbine is well suited to parallel computation. This thesis discusses general trends in wind turbine modeling, a potential flow model of the rotor of the NREL 5MW reference turbine, various forms of parallel computing, current GPU hardware, and the application of ground effects to the model. In the vicinity of 200,000 points, current GPU hardware was found to be nearly 17 …
Multi-Sensor Mobile Robot Localization For Diverse Environments, Joydeep Biswas, Manuela M. Veloso
Multi-Sensor Mobile Robot Localization For Diverse Environments, Joydeep Biswas, Manuela M. Veloso
Computer Science Department Faculty Publication Series
Mobile robot localization with different sensors and algorithms is a widely studied problem, and there have been many approaches proposed, with considerable degrees of success. However, every sensor and algorithm has limitations, due to which we believe no single localization algorithm can be “perfect,” or universally applicable to all situations. Laser rangefinders are commonly used for localization, and state-of-theart algorithms are capable of achieving sub-centimeter accuracy in environments with features observable by laser rangefinders. Unfortunately, in large scale environments, there are bound to be areas devoid of features visible by a laser rangefinder, like open atria or corridors with glass …