Agents that act as user assistants will become invaluable as the number of information sources continue to proliferate. Such agents can support the work of users by learning to automate time-consuming tasks and filter information to manageable levels. Although considerable advances have been made in this area, it remains a fertile area for further development. One application of agents under careful scrutiny is the automated negotiation of conflicts between different user's needs and desires. Many techniques require explicit user models in order to function. This dissertation explores a technique for dynamically constructing user models and the impact of using them to anticipate the need for negotiation. Negotiation is reduced by including an advising aspect to the agent that can use this anticipation of conflict to adjust user behavior.
The increasingly popular cloud-computing paradigm provides on-demand access to computing and storage with the appearance of unlimited resources. Users are given access to a variety of data and software utilities to manage their work. Users rent virtual resources and pay for only what they use. In spite of the many benefits that cloud computing promises, the lack of dependability in shared virtualized infrastructures is a major obstacle for its wider adoption, especially for mission-critical applications. Virtualization and multi-tenancy increase system complexity and dynamicity. They introduce new sources of failure degrading the dependability of cloud computing systems. To assure cloud dependability, in my dissertation research, I develop autonomic failure identification and diagnosis techniques that are crucial for understanding emergent, cloud-wide phenomena and self-managing resource burdens for cloud availability and productivity enhancement. We study the runtime cloud performance data collected from a cloud test-bed and by using traces from production cloud systems. We define cloud signatures including those metrics that are most relevant to failure instances. We exploit profiled cloud performance data in both time and frequency domain to identify anomalous cloud behaviors and leverage cloud metric subspace analysis to automate the diagnosis of observed failures. We implement a prototype of the anomaly identification system and conduct the experiments in an on-campus cloud computing test-bed and by using the Google datacenter traces. Our experimental results show that our proposed anomaly detection mechanism can achieve 93% detection sensitivity while keeping the false positive rate as low as 6.1% and outperform other tested anomaly detection schemes. In addition, the anomaly detector adapts itself by recursively learning from these newly verified detection results to refine future detection.
Abstract Probabilistic reasoning under uncertainty suits well to analysis of disease dynamics. The stochastic nature of disease progression is modeled by applying the principles of Bayesian learning. Bayesian learning predicts the disease progression, including prevalence and incidence, for a geographic region and demographic composition. Public health resources, prioritized by the order of risk levels of the population, will efficiently minimize the disease spread and curtail the epidemic at the earliest. A Bayesian network representing the outbreak of influenza and pneumonia in a geographic region is ported to a newer region with different demographic composition. Upon analysis for the newer region, the corresponding prevalence of influenza and pneumonia among the different demographic subgroups is inferred for the newer region. Bayesian reasoning coupled with disease timeline is used to reverse engineer an influenza outbreak for a given geographic and demographic setting. The temporal flow of the epidemic among the different sections of the population is analyzed to identify the corresponding risk levels. In comparison to spread vaccination, prioritizing the limited vaccination resources to the higher risk groups results in relatively lower influenza prevalence. HIV incidence in Texas from 1989-2002 is analyzed using demographic based epidemic curves. Dynamic Bayesian networks are integrated with probability distributions of HIV surveillance data coupled with the census population data to estimate the proportion of HIV incidence among the different demographic subgroups. Demographic based risk analysis lends to observation of varied spectrum of HIV risk among the different demographic subgroups. A methodology using hidden Markov models is introduced that enables to investigate the impact of social behavioral interactions in the incidence and prevalence of infectious diseases. The methodology is presented in the context of simulated disease outbreak data for influenza. Probabilistic reasoning analysis enhances the understanding of disease progression in order to identify the critical points of surveillance, …
In many real-world applications, it is common to have uneven number of examples among multiple classes. The data imbalance, however, usually complicates the learning process, especially for the minority classes, and results in deteriorated performance. Boosting methods were proposed to handle the imbalance problem. These methods need elongated training time and require diversity among the classifiers of the ensemble to achieve improved performance. Additionally, extending the boosting method to handle multi-class data sets is not straightforward. Examples of applications that suffer from imbalanced multi-class data can be found in face recognition, where tens of classes exist, and in capsule endoscopy, which suffers massive imbalance between the classes. This dissertation introduces RegBoost, a new boosting framework to address the imbalanced, multi-class problems. This method applies a weighted stratified sampling technique and incorporates a regularization term that accommodates multi-class data sets and automatically determines the error bound of each base classifier. The regularization parameter penalizes the classifier when it misclassifies instances that were correctly classified in the previous iteration. The parameter additionally reduces the bias towards majority classes. Experiments are conducted using 12 diverse data sets with moderate to high imbalance ratios. The results demonstrate superior performance of the proposed method compared to several state-of-the-art algorithms for imbalanced, multi-class classification problems. More importantly, the sensitivity improvement of the minority classes using RegBoost is accompanied with the improvement of the overall accuracy for all classes. With unpredictability regularization, a diverse group of classifiers are created and the maximum accuracy improvement reaches above 24%. Using stratified undersampling, RegBoost exhibits the best efficiency. The reduction in computational cost is significant reaching above 50%. As the volume of training data increase, the gain of efficiency with the proposed method becomes more significant.
Publicly available datasets in health science are often large and observational, in contrast to experimental datasets where a small number of data are collected in controlled experiments. Variables' causal relationships in the observational dataset are yet to be determined. However, there is a significant interest in health science to discover and analyze causal relationships from health data since identified causal relationships will greatly facilitate medical professionals to prevent diseases or to mitigate the negative effects of the disease. Recent advances in Computer Science, particularly in Bayesian networks, has initiated a renewed interest for causality research. Causal relationships can be possibly discovered through learning the network structures from data. However, the number of candidate graphs grows in a more than exponential rate with the increase of variables. Exact learning for obtaining the optimal structure is thus computationally infeasible in practice. As a result, heuristic approaches are imperative to alleviate the difficulty of computations. This research provides effective and efficient learning tools for local causal discoveries and novel methods of learning causal structures with a combination of background knowledge. Specifically in the direction of constraint based structural learning, polynomial-time algorithms for constructing causal structures are designed with first-order conditional independence. Algorithms of efficiently discovering non-causal factors are developed and proved. In addition, when the background knowledge is partially known, methods of graph decomposition are provided so as to reduce the number of conditioned variables. Experiments on both synthetic data and real epidemiological data indicate the provided methods are applicable to large-scale datasets and scalable for causal analysis in health data. Followed by the research methods and experiments, this dissertation gives thoughtful discussions on the reliability of causal discoveries computational health science research, complexity, and implications in health science research.
POD (Point of Dispensing)-based emergency response plans involving mass prophylaxis may seem feasible when considering the choice of dispensing points within a region, overall population density, and estimated traffic demands. However, the plan may fail to serve particular vulnerable sub-populations, resulting in access disparities during emergency response. Federal authorities emphasize on the need to identify sub-populations that cannot avail regular services during an emergency due to their special needs to ensure effective response. Vulnerable individuals require the targeted allocation of appropriate resources to serve their special needs. Devising schemes to address the needs of vulnerable sub-populations is essential for the effectiveness of response plans. This research focuses on data-driven computational methods to quantify and address vulnerabilities in response plans that require the allocation of targeted resources. Data-driven methods to identify and quantify vulnerabilities in response plans are developed as part of this research. Addressing vulnerabilities requires the targeted allocation of appropriate resources to PODs. The problem of resource allocation to PODs during public health emergencies is introduced and the variants of the resource allocation problem such as the spatial allocation, spatio-temporal allocation and optimal resource subset variants are formulated. Generating optimal resource allocation and scheduling solutions can be computationally hard problems. The application of metaheuristic techniques to find near-optimal solutions to the resource allocation problem in response plans is investigated. A vulnerability analysis and resource allocation framework that facilitates the demographic analysis of population data in the context of response plans, and the optimal allocation of resources with respect to the analysis are described.
Managing large-scale dynamical systems (e.g., transportation systems, complex information systems, and power networks, etc.) in real-time is very challenging considering their complicated system dynamics, intricate network interactions, large scale, and especially the existence of various uncertainties. To address this issue, intelligent techniques which can quickly design decision-making strategies that are robust to uncertainties are needed. This dissertation aims to conquer these challenges by exploring a data-driven decision-making framework, which leverages big-data techniques and scalable uncertainty evaluation approaches to quickly solve optimal control problems. In particular, following techniques have been developed along this direction: 1) system modeling approaches to simplify the system analysis and design procedures for multiple applications; 2) effective simulation and analytical based approaches to efficiently evaluate system performance and design control strategies under uncertainty; and 3) big-data techniques that allow some computations of control strategies to be completed offline. These techniques and tools for analysis, design and control contribute to a wide range of applications including air traffic flow management, complex information systems, and airborne networks.
Environmental monitoring represents a major application domain for wireless sensor networks (WSN). However, despite significant advances in recent years, there are still many challenging issues to be addressed to exploit the full potential of the emerging WSN technology. In this dissertation, we introduce the design and implementation of low-power wireless sensor networks for long-term, autonomous, and near-real-time environmental monitoring applications. We have developed an out-of-box solution consisting of a suite of software, protocols and algorithms to provide reliable data collection with extremely low power consumption. Two wireless sensor networks based on the proposed solution have been deployed in remote field stations to monitor soil moisture along with other environmental parameters. As parts of the ever-growing environmental monitoring cyberinfrastructure, these networks have been integrated into the Texas Environmental Observatory system for long-term operation. Environmental measurement and network performance results are presented to demonstrate the capability, reliability and energy-efficiency of the network.
There are several types of disorders that affect our colon’s ability to function properly such as colorectal cancer, ulcerative colitis, diverticulitis, irritable bowel syndrome and colonic polyps. Automatic detection of these diseases would inform the endoscopist of possible sub-optimal inspection during the colonoscopy procedure as well as save time during post-procedure evaluation. But existing systems only detects few of those disorders like colonic polyps. In this dissertation, we address the automatic detection of another important disorder called ulcerative colitis. We propose a novel texture feature extraction technique to detect the severity of ulcerative colitis in block, image, and video levels. We also enhance the current informative frame filtering methods by detecting water and bubble frames using our proposed technique. Our feature extraction algorithm based on accumulation of pixel value difference provides better accuracy at faster speed than the existing methods making it highly suitable for real-time systems. We also propose a hybrid approach in which our feature method is combined with existing feature method(s) to provide even better accuracy. We extend the block and image level detection method to video level severity score calculation and shot segmentation. Also, the proposed novel feature extraction method can detect water and bubble frames in colonoscopy videos with very high accuracy in significantly less processing time even when clustering is used to reduce the training size by 10 times.
Online/offline signature schemes are useful in many situations, and two such scenarios are considered in this dissertation: bursty server authentication and embedded device authentication. In this dissertation, new techniques for online/offline signing are introduced, those are applied in a variety of ways for creating online/offline signature schemes, and five different online/offline signature schemes that are proved secure under a variety of models and assumptions are proposed. Two of the proposed five schemes have the best offline or best online performance of any currently known technique, and are particularly well-suited for the scenarios that are considered in this dissertation. To determine if the proposed schemes provide the expected practical improvements, a series of experiments were conducted comparing the proposed schemes with each other and with other state-of-the-art schemes in this area, both on a desktop class computer, and under AVR Studio, a simulation platform for an 8-bit processor that is popular for embedded systems. Under AVR Studio, the proposed SGE scheme using a typical key size for the embedded device authentication scenario, can complete the offline phase in about 24 seconds and then produce a signature (the online phase) in 15 milliseconds, which is the best offline performance of any known signature scheme that has been proven secure in the standard model. In the tests on a desktop class computer, the proposed SGS scheme, which has the best online performance and is designed for the bursty server authentication scenario, generated 469,109 signatures per second, and the Schnorr scheme (the next best scheme in terms of online performance) generated only 223,548 signatures. The experimental results demonstrate that the SGE and SGS schemes are the most efficient techniques for embedded device authentication and bursty server authentication, respectively.
Trusted platform modules (TPMs) are hardware modules that are bound to a computer's motherboard, that are being included in many desktops and laptops. Augmenting computers with these hardware modules adds powerful functionality in distributed settings, allowing us to reason about the security of these systems in new ways. In this dissertation, I study the functionality of TPMs from a theoretical as well as an experimental perspective. On the theoretical front, I leverage various features of TPMs to construct applications like random oracles that are impossible to implement in a standard model of computation. Apart from random oracles, I construct a new cryptographic primitive which is basically a non-interactive form of the standard cryptographic primitive of oblivious transfer. I apply this new primitive to secure mobile agent computations, where interaction between various entities is typically required to ensure security. I prove these constructions are secure using standard cryptographic techniques and assumptions. To test the practicability of these constructions and their applications, I performed an experimental study, both on an actual TPM and a software TPM simulator which has been enhanced to make it reflect timings from a real TPM. This allowed me to benchmark the performance of the applications and test the feasibility of the proposed extensions to standard TPMs. My tests also show that these constructions are practical.
In recent years, social media platforms such as Twitter and Facebook have emerged as effective tools for broadcasting messages worldwide during disaster events. With millions of messages posted through these services during such events, it has become imperative to identify valuable information that can help the emergency responders to develop effective relief efforts and aid victims. Many studies implied that the role of social media during disasters is invaluable and can be incorporated into emergency decision-making process. However, due to the "big data" nature of social media, it is very labor-intensive to employ human resources to sift through social media posts and categorize/classify them as useful information. Hence, there is a growing need for machine intelligence to automate the process of extracting useful information from the social media data during disaster events. This dissertation addresses the following questions: In a social media stream of messages, what is the useful information to be extracted that can help emergency response organizations to become more situationally aware during and following a disaster? What are the features (or patterns) that can contribute to automatically identifying messages that are useful during disasters? We explored a wide variety of features in conjunction with supervised learning algorithms to automatically identify messages that are useful during disaster events. The feature design includes sentiment features to extract the geo-mapped sentiment expressed in tweets, as well as tweet-content and user detail features to predict the likelihood of the information contained in a tweet to be quickly spread in the network. Further experimentation is carried out to see how these features help in identifying the informative tweets and filter out those tweets that are conversational in nature.
Abstract This dissertation investigates authentication techniques in some emerging areas. Specifically, authentication schemes have been proposed that are well-suited for embedded systems, and privacy-respecting pay Web sites. With embedded systems, a person could own several devices which are capable of communication and interaction, but these devices use embedded processors whose computational capabilities are limited as compared to desktop computers. Examples of this scenario include entertainment devices or appliances owned by a consumer, multiple control and sensor systems in an automobile or airplane, and environmental controls in a building. An efficient public key cryptosystem has been devised, which provides a complete solution to an embedded system, including protocols for authentication, authenticated key exchange, encryption, and revocation. The new construction is especially suitable for the devices with constrained computing capabilities and resources. Compared with other available authentication schemes, such as X.509, identity-based encryption, etc, the new construction provides unique features such as simplicity, efficiency, forward secrecy, and an efficient re-keying mechanism. In the application scenario for a pay Web site, users may be sensitive about their privacy, and do not wish their behaviors to be tracked by Web sites. Thus, an anonymous authentication scheme is desirable in this case. That is, a user can prove his/her authenticity without revealing his/her identity. On the other hand, the Web site owner would like to prevent a bunch of users from sharing a single subscription while hiding behind user anonymity. The Web site should be able to detect these possible malicious behaviors, and exclude corrupted users from future service. This dissertation extensively discusses anonymous authentication techniques, such as group signature, direct anonymous attestation, and traceable signature. Three anonymous authentication schemes have been proposed, which include a group signature scheme with signature claiming and variable linkability, a scheme for direct anonymous attestation in trusted computing platforms …
The presence of naturally occurring and man-made public health threats necessitate the design and implementation of mitigation strategies, such that adequate response is provided in a timely manner. Since multiple variables, such as geographic properties, resource constraints, and government mandated time-frames must be accounted for, computational methods provide the necessary tools to develop contingency response plans while respecting underlying data and assumptions. A typical response scenario involves the placement of points of dispensing (PODs) in the affected geographic region to supply vaccines or medications to the general public. Computational tools aid in the analysis of such response plans, as well as in the strategic placement of PODs, such that feasible response scenarios can be developed. Due to the sensitivity of bio-emergency response plans, geographic information, such as POD locations, must be kept confidential. The generation of synthetic geographic regions allows for the development of emergency response plans on non-sensitive data, as well as for the study of the effects of single geographic parameters. Further, synthetic representations of geographic regions allow for results to be published and evaluated by the scientific community. This dissertation presents methodology for the analysis of bio-emergency response plans, methods for plan optimization, as well as methodology for the generation of synthetic geographic regions.
Software applications’ performance is hindered by a variety of factors, but most notably by the well-known CPU-memory speed gap (often known as the memory wall). This results in the CPU sitting idle waiting for data to be brought from memory to processor caches. The addressing used by caches cause non-uniform accesses to various cache sets. The non-uniformity is due to several reasons, including how different objects are accessed by the code and how the data objects are located in memory. Memory allocators determine where dynamically created objects are placed, thus defining addresses and their mapping to cache locations. It is important to evaluate how different allocators behave with respect to the localities of the created objects. Most allocators use a single attribute, the size, of an object in making allocation decisions. Additional attributes such as the placement with respect to other objects, or specific cache area may lead to better use of cache memories. In this dissertation, we proposed and implemented a framework that allows for the development and evaluation of new memory allocation techniques. At the root of the framework is a memory tracing tool called Gleipnir, which provides very detailed information about every memory access, and relates it back to source level objects. Using the traces from Gleipnir, we extended a commonly used cache simulator for generating detailed cache statistics: per function, per data object, per cache line, and identify specific data objects that are conflicting with each other. The utility of the framework is demonstrated with a new memory allocator known as equivalence class allocator. The new allocator allows users to specify cache sets, in addition to object size, where the objects should be placed. We compare this new allocator with two well-known allocators, viz., Doug Lea and Pool allocators.
In the United States, smartphone ownership surpassed 69.5 million in February 2011 with a large portion of those users (20%) downloading applications (apps) that enhance the usability of a device by adding additional functionality. a large percentage of apps are written specifically to utilize the geographical position of a mobile device. One of the prime factors in developing location prediction models is the use of historical data to train such a model. with larger sets of training data, prediction algorithms become more accurate; however, the use of historical data can quickly become a downfall if the GPS stream is not collected or processed correctly. Inaccurate or incomplete or even improperly interpreted historical data can lead to the inability to develop accurately performing prediction algorithms. As GPS chipsets become the standard in the ever increasing number of mobile devices, the opportunity for the collection of GPS data increases remarkably. the goal of this study is to build a comprehensive system that addresses the following challenges: (1) collection of GPS data streams in a manner such that the data is highly usable and has a reduction in errors; (2) processing and reduction of the collected data in order to prepare it and make it highly usable for the creation of prediction algorithms; (3) creation of prediction/labeling algorithms at such a level that they are viable for commercial use. This study identifies the key research problems toward building the CaPPture (collection, processing, prediction) system.
Hard real-time systems in robotics, space and military missions, and control devices are specified with stringent and critical time constraints. On the other hand, soft real-time applications arising from multimedia, telecommunications, Internet web services, and games are specified with more lenient constraints. Real-time systems can also be distinguished in terms of their implementation into preemptive and non-preemptive systems. In preemptive systems, tasks are often preempted by higher priority tasks. Non-preemptive systems are gaining interest for implementing soft-real applications on multithreaded platforms. In this dissertation, I propose a new algorithm that uses a two-level scheduling strategy for scheduling non-preemptive soft real-time tasks. Our goal is to improve the success ratios of the well-known earliest deadline first (EDF) approach when the load on the system is very high and to improve the overall performance in both underloaded and overloaded conditions. Our approach, known as group-EDF (gEDF), is based on dynamic grouping of tasks with deadlines that are very close to each other, and using a shortest job first (SJF) technique to schedule tasks within the group. I believe that grouping tasks dynamically with similar deadlines and utilizing secondary criteria, such as minimizing the total execution time can lead to new and more efficient real-time scheduling algorithms. I present results comparing gEDF with other real-time algorithms including, EDF, best-effort, and guarantee scheme, by using randomly generated tasks with varying execution times, release times, deadlines and tolerances to missing deadlines, under varying workloads. Furthermore, I implemented the gEDF algorithm in the Linux kernel and evaluated gEDF for scheduling real applications.
With the advances in very large scale integration (VLSI) technology, hundreds of billions of transistors can be packed into a single chip. With the increased hardware budget, how to take advantage of available hardware resources becomes an important research area. Some researchers have shifted from control flow Von-Neumann architecture back to dataflow architecture again in order to explore scalable architectures leading to multi-core systems with several hundreds of processing elements. In this dissertation, I address how the performance of modern processing systems can be improved, while attempting to reduce hardware complexity and energy consumptions. My research described here tackles both central processing unit (CPU) performance and memory subsystem performance. More specifically I will describe my research related to the design of an innovative decoupled multithreaded architecture that can be used in multi-core processor implementations. I also address how memory management functions can be off-loaded from processing pipelines to further improve system performance and eliminate cache pollution caused by runtime management functions.
Epidemiologists rely on human interaction networks for determining states and dynamics of disease propagations in populations. However, such networks are empirical snapshots of the past. It will greatly benefit if human interaction networks are statistically predicted and dynamically created while an epidemic is in progress. We develop an application framework for the generation of human interaction networks and running epidemiological processes utilizing research on human mobility patterns and agent-based modeling. The interaction networks are dynamically constructed by incorporating different types of Random Walks and human rules of engagements. We explore the characteristics of the created network and compare them with the known theoretical and empirical graphs. The dependencies of epidemic dynamics and their outcomes on patterns and parameters of human motion and motives are encountered and presented through this research. This work specifically describes how the types and parameters of random walks define properties of generated graphs. We show that some configurations of the system of agents in random walk can produce network topologies with properties similar to small-world networks. Our goal is to find sets of mobility patterns that lead to empirical-like networks. The possibility of phase transitions in the graphs due to changes in the parameterization of agent walks is the focus of this research as this knowledge can lead to the possibility of disruptions to disease diffusions in populations. This research shall facilitate work of public health researchers to predict the magnitude of an epidemic and estimate resources required for mitigation.
Extensive research has been conducted by the grid community to enable large-scale collaborations in pre-configured environments. grid collaborations can vary in scale and motivation resulting in a coarse classification of grids: national grid, project grid, enterprise grid, and volunteer grid. Despite the differences in scope and scale, all the traditional grids in practice share some common assumptions. They support mutually collaborative communities, adopt a centralized control for membership, and assume a well-defined non-changing collaboration. To support grid applications that do not confirm to these assumptions, we propose the concept of ad hoc grids. In the context of this research, we propose a novel architecture for ad hoc grids that integrates a suite of component frameworks. Specifically, our architecture combines the community management framework, security framework, abstraction framework, quality of service framework, and reputation framework. The overarching objective of our integrated architecture is to support a variety of grid applications in a self-controlled fashion with the help of a self-organizing ad hoc community. We introduce mechanisms in our architecture that successfully isolates malicious elements from the community, inherently improving the quality of grid services and extracting deterministic quality assurances from the underlying infrastructure. We also emphasize on the technology-independence of our architecture, thereby offering the requisite platform for technology interoperability. The feasibility of the proposed architecture is verified with a high-quality ad hoc grid implementation. Additionally, we have analyzed the performance and behavior of ad hoc grids with respect to several control parameters.
Dynamic memory management required by allocation-intensive (i.e., Object Oriented and linked data structured) applications has led to a large number of research trends. Memory performance due to the cache misses in these applications continues to lag in terms of execution cycles as ever increasing CPU-Memory speed gap continues to grow. Sophisticated prefetcing techniques, data relocations, and multithreaded architectures have tried to address memory latency. These techniques are not completely successful since they require either extra hardware/software in the system or special properties in the applications. Software needed for prefetching and data relocation strategies, aimed to improve cache performance, pollutes the cache so that the technique itself becomes counter-productive. On the other hand, extra hardware complexity needed in multithreaded architectures decelerates CPU's clock, since "Simpler is Faster." This dissertation, directed to seek the cause of poor locality behavior of allocation--intensive applications, studies allocators and their impact on the cache performance of these applications. Our study concludes that service functions, in general, and memory management functions, in particular, entangle with application's code and become the major cause of cache pollution. In this dissertation, we present a novel technique that transfers the allocation and de-allocation functions entirely to a separate processor residing in chip with DRAM (Intelligent Memory Manager). Our empirical results show that, on average, 60% of the cache misses caused by allocation and de-allocation service functions are eliminated using our technique.
Abstract Due to the vast amount of information we are faced with, summarization has become a critical necessity of everyday human life. Given that a large fraction of the electronic documents available online and elsewhere consist of short texts such as Web pages, news articles, scientific reports, and others, the focus of natural language processing techniques to date has been on the automation of methods targeting short documents. We are witnessing however a change: an increasingly larger number of books become available in electronic format. This means that the need for language processing techniques able to handle very large documents such as books is becoming increasingly important. This thesis addresses the problem of summarization of novels, which are long and complex literary narratives. While there is a significant body of research that has been carried out on the task of automatic text summarization, most of this work has been concerned with the summarization of short documents, with a particular focus on news stories. However, novels are different in both length and genre, and consequently different summarization techniques are required. This thesis attempts to close this gap by analyzing a new domain for summarization, and by building unsupervised and supervised systems that effectively take into account the properties of long documents, and outperform the traditional extractive summarization systems typically addressing news genre.
Segmentation, recognition and 3D reconstruction of objects have been cutting-edge research topics, which have many applications ranging from environmental and medical to geographical applications as well as intelligent transportation. In this dissertation, I focus on the study of segmentation, recognition and 3D reconstruction of objects using LiDAR data/MRI. Three main works are that (I). Feature extraction algorithm based on sparse LiDAR data. A novel method has been proposed for feature extraction from sparse LiDAR data. The algorithm and the related principles have been described. Also, I have tested and discussed the choices and roles of parameters. By using correlation of neighboring points directly, statistic distribution of normal vectors at each point has been effectively used to determine the category of the selected point. (II). Segmentation and 3D reconstruction of objects based on LiDAR/MRI. The proposed method includes that the 3D LiDAR data are layered, that different categories are segmented, and that 3D canopy surfaces of individual tree crowns and clusters of trees are reconstructed from LiDAR point data based on a region active contour model. The proposed method allows for delineations of 3D forest canopy naturally from the contours of raw LiDAR point clouds. The proposed model is suitable not only for a series of ideal cone shapes, but also for other kinds of 3D shapes as well as other kinds dataset such as MRI. (III). Novel algorithms for recognition of objects based on LiDAR/MRI. Aimed to the sparse LiDAR data, the feature extraction algorithm has been proposed and applied to classify the building and trees. More importantly, the novel algorithms based on level set methods have been provided and employed to recognize not only the buildings and trees, the different trees (e.g. Oak trees and Douglas firs), but also the subthalamus nuclei (STNs). By using the novel algorithms based …
This research addresses the problem of automatic keyphrase extraction from large documents and back of the book indexing. The potential benefits of automating this process are far reaching, from improving information retrieval in digital libraries, to saving countless man-hours by helping professional indexers creating back of the book indexes. The dissertation introduces a new methodology to evaluate automated systems, which allows for a detailed, comparative analysis of several techniques for keyphrase extraction. We introduce and evaluate both supervised and unsupervised techniques, designed to balance the resource requirements of an automated system and the best achievable performance. Additionally, a number of novel features are proposed, including a statistical informativeness measure based on chi statistics; an encyclopedic feature that taps into the vast knowledge base of Wikipedia to establish the likelihood of a phrase referring to an informative concept; and a linguistic feature based on sophisticated semantic analysis of the text using current theories of discourse comprehension. The resulting keyphrase extraction system is shown to outperform the current state of the art in supervised keyphrase extraction by a large margin. Moreover, a fully automated back of the book indexing system based on the keyphrase extraction system was shown to lead to back of the book indexes closely resembling those created by human experts.
While pragmatics, through its integration of situational awareness and real world relevant knowledge, offers a high level of analysis that is suitable for real interpretation of natural dialogue, semantics, on the other end, represents a lower yet more tractable and affordable linguistic level of analysis using current technologies. Generally, the understanding of semantic meaning in literature has revolved around the famous quote ``You shall know a word by the company it keeps''. In this thesis we investigate the role of context constituents in decoding the semantic meaning of the engulfing context; specifically we probe the role of salient concepts, defined as content-bearing expressions which afford encyclopedic definitions, as a suitable source of semantic clues to an unambiguous interpretation of context. Furthermore, we integrate this world knowledge in building a new and robust unsupervised semantic model and apply it to entail semantic relatedness between textual pairs, whether they are words, sentences or paragraphs. Moreover, we explore the abstraction of semantics across languages and utilize our findings into building a novel multi-lingual semantic relatedness model exploiting information acquired from various languages. We demonstrate the effectiveness and the superiority of our mono-lingual and multi-lingual models through a comprehensive set of evaluations on specialized synthetic datasets for semantic relatedness as well as real world applications such as paraphrase detection and short answer grading. Our work represents a novel approach to integrate world-knowledge into current semantic models and a means to cross the language boundary for a better and more robust semantic relatedness representation, thus opening the door for an improved abstraction of meaning that carries the potential of ultimately imparting understanding of natural language to machines.
The major goal of information integration is to provide efficient and easy-to-use access to multiple heterogeneous data sources with a single query. At the same time, one of the current trends is to use standard technologies for implementing solutions to complex software problems. In this dissertation, I used XML and XQuery as the standard technologies and have developed an extended projection algorithm to provide a solution to the information integration problem. In order to demonstrate my solution, I implemented a prototype mediation system called Omphalos based on XML related technologies. The dissertation describes the architecture of the system, its metadata, and the process it uses to answer queries. The system uses XQuery expressions (termed metaqueries) to capture complex mappings between global schemas and data source schemas. The system then applies these metaqueries in order to rewrite a user query on a virtual global database (representing the integrated view of the heterogeneous data sources) to a query (termed an outsourced query) on the real data sources. An extended XML document projection algorithm was developed to increase the efficiency of selecting the relevant subset of data from an individual data source to answer the user query. The system applies the projection algorithm to decompose an outsourced query into atomic queries which are each executed on a single data source. I also developed an algorithm to generate integrating queries, which the system uses to compose the answers from the atomic queries into a single answer to the original user query. I present a proof of both the extended XML document projection algorithm and the query integration algorithm. An analysis of the efficiency of the new extended algorithm is also presented. Finally I describe a collaborative schema-matching tool that was implemented to facilitate maintaining metadata.
An increasingly promising and widespread topic of research in distributed computing is the mobile agent paradigm: code travelling and performing computations on remote hosts in an autonomous manner. One of the biggest challenges faced by this new paradigm is security. The issue of protecting sensitive code and data carried by a mobile agent against tampering from a malicious host is particularly hard but important. Based on secure multi-party computation, a recent research direction shows the feasibility of a software-only solution to this problem, which had been deemed impossible by some researchers previously. The best result prior to this dissertation is a single-agent protocol which requires the participation of a trusted third party. Our research employs multi-agent protocols to eliminate the trusted third party, resulting in a protocol with minimum trust assumptions. This dissertation presents one of the first formal definitions of secure mobile agent computation, in which the privacy and integrity of the agent code and data as well as the data provided by the host are all protected. We present secure protocols for mobile agent computation against static, semi-honest or malicious adversaries without relying on any third party or trusting any specific participant in the system. The security of our protocols is formally proven through standard proof technique and according to our formal definition of security. Our second result is a more practical agent protocol with strong security against most real-world host attacks. The security features are carefully analyzed, and the practicality is demonstrated through implementation and experimental study on a real-world mobile agent platform. All these protocols rely heavily on well-established cryptographic primitives, such as encrypted circuits, threshold decryption, and oblivious transfer. Our study of these tools yields new contributions to the general field of cryptography. Particularly, we correct a well-known construction of the encrypted circuit and give …
Emergency Medical Dispatch Protocols are guidelines that a 9-1-1 dispatcher uses to evaluate the nature of emergency, resources to send and the nature of help provided to the 9-1-1 caller. The current Dispatch Protocols are based on voice only call. But the Next Generation 9-1-1 (NG9-1-1) architecture will allow multimedia emergency calls. In this thesis I analyze and model the Emergency Medical Dispatch Protocols for NG9-1-1 architecture. I have identified various technical aspects to improve the NG9-1-1 Dispatch Protocols. The devices (smartphone) at the caller end have advanced to a point where they can be used to send and receive video, pictures and text. There are sensors embedded in them that can be used for initial diagnosis of the injured person. There is a need to improve the human computer (smartphone) interface to take advantage of technology so that callers can easily make use of various features available to them. The dispatchers at the 9-1-1 call center can make use of these new protocols to improve the quality and the response time. They will have capability of multiple media streams to interact with the caller and the first responders.The specific contributions in this thesis include developing applications that use smartphone sensors. The CPR application uses the smartphone to help administer effective CPR even if the person is not trained. The application makes the CPR process closed loop, i.e., the person who administers the CPR as well as the 9-1-1 operator receive feedback and prompt from the application about the correctness of the CPR. The breathing application analyzes the quality of breathing of the affected person and automatically sends the information to the 9-1-1 operator. In order to improve the Human Computer Interface at the caller and the operator end, I have analyzed Fitts law and extended it so that it …
The history of mitigation programs to contain vector-borne diseases is a story of successes and failures. Due to the complex interplay among multiple factors that determine disease dynamics, the general principles for timely and specific intervention for incidence reduction or eradication of life-threatening diseases has yet to be determined. This research discusses computational methods developed to assist in the understanding of complex relationships affecting vector-borne disease dynamics. A computational framework to assist public health practitioners with exploring the dynamics of vector-borne diseases, such as malaria and dengue in homogenous and heterogeneous populations, has been conceived, designed, and implemented. The framework integrates a stochastic computational model of interactions to simulate horizontal disease transmission. The intent of the computational modeling has been the integration of stochasticity during simulation of the disease progression while reducing the number of necessary interactions to simulate a disease outbreak. While there are improvements in the computational time reducing the number of interactions needed for simulating disease dynamics, the realization of interactions can remain computationally expensive. Using multi-threading technology to improve performance upon the original computational model, multi-threading experimental results have been tested and reported. In addition, to the contact model, the modeling of biological processes specific to the corresponding pathogen-carrier vector to increase the specificity of the vector-borne disease has been integrated. Last, automation for requesting, retrieving, parsing, and storing specific weather data and geospatial information from federal agencies to study the differences between homogenous and heterogeneous populations has been implemented.
Multi-modal image fusion is an active research area with many civilian and military applications. Fusion is defined as strategic combination of information collected by various sensors from different locations or different types in order to obtain a better understanding of an observed scene or situation. Fusion of multi-modal images cannot be completed unless these two modalities are spatially aligned. In this research, I consider two important problems. Multi-modal, multi-perspective image registration and decision level fusion of multi-modal images. In particular, LiDAR and visual imagery. Multi-modal image registration is a difficult task due to the different semantic interpretation of features extracted from each modality. This problem is decoupled into three sub-problems. The first step is identification and extraction of common features. The second step is the determination of corresponding points. The third step consists of determining the registration transformation parameters. Traditional registration methods use low level features such as lines and corners. Using these features require an extensive optimization search in order to determine the corresponding points. Many methods use global positioning systems (GPS), and a calibrated camera in order to obtain an initial estimate of the camera parameters. The advantages of our work over the previous works are the following. First, I used high level-features, which significantly reduce the search space for the optimization process. Second, the determination of corresponding points is modeled as an assignment problem between a small numbers of objects. On the other side, fusing LiDAR and visual images is beneficial, due to the different and rich characteristics of both modalities. LiDAR data contain 3D information, while images contain visual information. Developing a fusion technique that uses the characteristics of both modalities is very important. I establish a decision-level fusion technique using manifold models.
Ambiguity is inherent to human language. In particular, word sense ambiguity is prevalent in all natural languages, with a large number of the words in any given language carrying more than one meaning. Word sense disambiguation is the task of automatically assigning the most appropriate meaning to a polysemous word within a given context. Generally the problem of resolving ambiguity in literature has revolved around the famous quote “you shall know the meaning of the word by the company it keeps.” In this thesis, we investigate the role of context for resolving ambiguity through three different approaches. Instead of using a predefined monolingual sense inventory such as WordNet, we use a language-independent framework where the word senses and sense-tagged data are derived automatically from Wikipedia. Using Wikipedia as a source of sense-annotations provides the much needed solution for knowledge acquisition bottleneck. In order to evaluate the viability of Wikipedia based sense-annotations, we cast the task of disambiguating polysemous nouns as a monolingual classification task and experimented on lexical samples from four different languages (viz. English, German, Italian and Spanish). The experiments confirm that the Wikipedia based sense annotations are reliable and can be used to construct accurate monolingual sense classifiers. It is a long belief that exploiting multiple languages helps in building accurate word sense disambiguation systems. Subsequently, we developed two approaches that recast the task of disambiguating polysemous nouns as a multilingual classification task. The first approach for multilingual word sense disambiguation attempts to effectively use a machine translation system to leverage two relevant multilingual aspects of the semantics of text. First, the various senses of a target word may be translated into different words, which constitute unique, yet highly salient signal that effectively expand the target word’s feature space. Second, the translated context words themselves embed co-occurrence information …
The Internet and networks in general have become essential tools for disseminating in-formation. Search engines have become the predominant means of finding information on the Web and all other data repositories, including local resources. Domain scientists regularly acquire and analyze images generated by equipment such as microscopes and cameras, resulting in complex image files that need to be managed in a convenient manner. This type of integrated environment has been recently termed a netcentric sci-entific research repository. I developed a number of data manipulation tools that allow researchers to manage their information more effectively in a netcentric environment. The specific contributions are: (1) A unique interface for management of data including files and relational databases. A wrapper for relational databases was developed so that the data can be indexed and searched using traditional search engines. This approach allows data in databases to be searched with the same interface as other data. Fur-thermore, this approach makes it easier for scientists to work with their data if they are not familiar with SQL. (2) A Web services based architecture for integrating analysis op-erations into a repository. This technique allows the system to leverage the large num-ber of existing tools by wrapping them with a Web service and registering the service with the repository. Metadata associated with Web services was enhanced to allow this feature to be included. In addition, an improved binary to text encoding scheme was de-veloped to reduce the size overhead for sending large scientific data files via XML mes-sages used in Web services. (3) Integrated image analysis operations with SQL. This technique allows for images to be stored and managed conveniently in a relational da-tabase. SQL supplemented with map algebra operations is used to select and perform operations on sets of images.
Computational modeling is of fundamental significance in mapping possible disease spread, and designing strategies for its mitigation. Conventional contact networks implement the simulation of interactions as random occurrences, presenting public health bodies with a difficult trade off between a realistic model granularity and robust design of intervention strategies. Recently, researchers have been investigating the use of agent-based models (ABMs) to embrace the complexity of real world interactions. At the same time, theoretical approaches provide epidemiologists with general optimization models in which demographics are intrinsically simplified. The emerging study of affiliation networks and co-affiliation networks provide an alternative to such trade off. Co-affiliation networks maintain the realism innate to ABMs while reducing the complexity of contact networks into distinctively smaller k-partite graphs, were each partition represent a dimension of the social model. This dissertation studies the optimization of intervention strategies for infectious diseases, mainly distributed in school systems. First, concepts of synthetic populations and affiliation networks are extended to propose a modified algorithm for the synthetic reconstruction of populations. Second, the definition of multi-coaffiliation networks is presented as the main social model in which risk is quantified and evaluated, thereby obtaining vulnerability indications for each school in the system. Finally, maximization of the mitigation coverage and minimization of the overall cost of intervention strategies are proposed and compared, based on centrality measures.
The promise of service oriented computing, and the availability of Web services promote the delivery and creation of new services based on existing services, in order to meet new demands and new markets. As Web and internet based services move into Clouds, inter-dependency of services and their complexity will increase substantially. There are standards and frameworks for specifying and composing Web Services based on functional properties. However, mechanisms to individually address non-functional properties of services and their compositions have not been well established. Furthermore, the Cloud ontology depicts service layers from a high-level, such as Application and Software, to a low-level, such as Infrastructure and Platform. Each component that resides in one layer can be useful to another layer as a service. It hints at the amount of complexity resulting from not only horizontal but also vertical integrations in building and deploying a composite service. To meet the requirements and facilitate using Web services, we first propose a WSDL extension to permit specification of non-functional or Quality of Service (QoS) properties. On top of the foundation, the QoS-aware framework is established to adapt publicly available tools for Web services, augmented by ontology management tools, along with tools for performance modeling to exemplify how the non-functional properties such as response time, throughput, or utilization of services can be addressed in the service acquisition and composition process. To facilitate Web service composition standards, in this work we extended the framework with additional qualitative information to the service descriptions using Business Process Execution Language (BPEL). Engineers can use BPEL to explore design options, and have the QoS properties analyzed for the composite service. The main issue in our research is performance evaluation in software system and engineering. We researched the Web service computation as the first half of this dissertation, and performance antipattern …
One in seven people in the world use online social networking for a variety of purposes -- to keep in touch with friends and family, to share special occasions, to broadcast announcements, and more. The majority of society has been bought into this new era of communication technology, which allows everyone on the internet to share information with friends. Since social networking has rapidly become a main form of communication, holes in privacy have become apparent. It has come to the point that the whole concept of sharing information requires restructuring. No longer are online social networks simply technology available for a niche market; they are in use by all of society. Thus it is important to not forget that a sense of privacy is inherent as an evolutionary by-product of social intelligence. In any context of society, privacy needs to be a part of the system in order to help users protect themselves from others. This dissertation attempts to address the lack of privacy management in online social networks by designing models which understand the social science behind how we form social groups and share information with each other. Social relationship strength was modeled using activity patterns, vocabulary usage, and behavioral patterns. In addition, automatic configuration for default privacy settings was proposed to help prevent new users from leaking personal information. This dissertation aims to mobilize a new era of social networking that understands social aspects of human network, and uses that knowledge to honor users' privacy.
The recent transformation of consumer graphics (CG) cards into powerful 3D rendering processors is due in large measure to the success of game developers in delivering mass market entertainment software that feature highly immersive and captivating virtual environments. Despite this success, 3D CG application development is becoming increasingly handicapped by the inability of traditional content creation methods to keep up with the demand for content. The term content is used here to refer to any data operated on by application code that is meant for viewing, including 3D models, textures, animation sequences and maps or other data-intensive descriptions of virtual environments. Traditionally, content has been handcrafted by humans. A serious problem facing the interactive graphics software development community is how to increase the rate at which content can be produced to keep up with the increasingly rapid pace at which software for interactive applications can now be developed. Research addressing this problem centers around procedural content creation systems. By moving away from purely human content creation toward systems in which humans play a substantially less time-intensive but no less creative part in the process, procedural content creation opens new doors. From a qualitative standpoint, these types of systems will not rely less on human intervention but rather more since they will depend heavily on direction from a human in order to synthesize the desired content. This research draws heavily from the entertainment software domain but the research is broadly relevant to 3D graphics applications in general.
In recent years there has been growing interest in limitless realism in computer graphics applications. Among those, my foremost concentration falls into the complex physical simulations and modeling with diverse applications for the gaming industry. Different simulations have been virtually successful by replicating the details of physical process. As a result, some were strong enough to lure the user into believable virtual worlds that could destroy any sense of attendance. In this research, I focus on fire simulations and its deformation process towards various virtual objects. In most game engines model loading takes place at the beginning of the game or when the game is transitioning between levels. Game models are stored in large data structures. Since changing or adjusting a large data structure while the game is proceeding may adversely affect the performance of the game. Therefore, developers may choose to avoid procedural simulations to save resources and avoid interruptions on performance. I introduce a process to implement a real-time model deformation while maintaining performance. It is a challenging task to achieve high quality simulation while utilizing minimum resources to represent multiple events in timely manner. Especially in video games, this overwhelming criterion would be robust enough to sustain the engaging player's willing suspension of disbelief. I have implemented and tested my method on a relatively modest GPU using CUDA. My experiments conclude this method gives a believable visual effect while using small fraction of CPU and GPU resources.
The spread of infectious diseases has been a public concern throughout human history. Historic recorded data has reported the severity of infectious disease epidemics in different ages. Ancient Greek physician Hippocrates was the first to analyze the correlation between diseases and their environment. Nowadays, health authorities are in charge of planning strategies that guarantee the welfare of citizens. The simulation of contagion scenarios contributes to the understanding of the epidemic behavior of diseases. Computational models facilitate the study of epidemics by integrating disease and population data to the simulation. The use of detailed demographic and geographic characteristics allows researchers to construct complex models that better resemble reality and the integration of these attributes permits us to understand the rules of interaction. The interaction of individuals with similar characteristics forms synthetic structures that depict clusters of interaction. The synthetic environments facilitate the study of the spread of infectious diseases in diverse scenarios. The characteristics of the population and the disease concurrently affect the local and global epidemic progression. Every cluster’ epidemic behavior constitutes the global epidemic for a clustered population. By understanding the correlation between structured populations and the spread of a disease, current dissertation research makes possible to identify risk groups of specific characteristics and devise containment strategies that facilitate health authorities to improve mitigation strategies.
The widely used mobile phone, as well as its related technologies had opened opportunities for a complete change on how people interact and build relationship across geographic and time considerations. The convenience of instant communication by mobile phones that broke the barrier of space and time is evidently the key motivational point on why such technologies so important in people's life and daily activities. Mobile phones have become the most popular communication tools. Mobile phone technology is apparently changing our relationship to each other in our work and lives. The impact of new technologies on people's lives in social spaces gives us the chance to rethink the possibilities of technologies in social interaction. Accordingly, mobile phones are basically changing social relations in ways that are intricate to measure with any precision. In this dissertation I propose a socioscope model for social network, relationship and human behavior analysis based on mobile phone call detail records. Because of the diversities and complexities of human social behavior, one technique cannot detect different features of human social behaviors. Therefore I use multiple probability and statistical methods for quantifying social groups, relationships and communication patterns, for predicting social tie strengths and for detecting human behavior changes and unusual consumption events. I propose a new reciprocity index to measure the level of reciprocity between users and their communication partners. The experimental results show that this approach is effective. Among other applications, this work is useful for homeland security, detection of unwanted calls (e.g., spam), telecommunication presence, and marketing. In my future work I plan to analyze and study the social network dynamics and evolution.
Existing cache organization suffers from the inability to distinguish different types of localities, and non-selectively cache all data rather than making any attempt to take special advantage of the locality type. This causes unnecessary movement of data among the levels of the memory hierarchy and increases in miss ratio. In this dissertation I propose a split data cache architecture that will group memory accesses as scalar or array references according to their inherent locality and will subsequently map each group to a dedicated cache partition. In this system, because scalar and array references will no longer negatively affect each other, cache-interference is diminished, delivering better performance. Further improvement is achieved by the introduction of victim cache, prefetching, data flattening and reconfigurability to tune the array and scalar caches for specific application. The most significant contribution of my work is the introduction of novel cache architecture for embedded microprocessor platforms. My proposed cache architecture uses reconfigurability coupled with split data caches to reduce area and power consumed by cache memories while retaining performance gains. My results show excellent reductions in both memory size and memory access times, translating into reduced power consumption. Since there was a huge reduction in miss rates at L-1 caches, further power reduction is achieved by partially or completely shutting down L-2 data or L-2 instruction caches. The saving in cache sizes resulting from these designs can be used for other processor activities including instruction and data prefetching, branch-prediction buffers. The potential benefits of such techniques for embedded applications have been evaluated in my work. I also explore how my cache organization performs for non-numeric data structures. I propose a novel idea called "Data flattening" which is a profile based memory allocation technique to compress sparsely scattered pointer data into regular contiguous memory locations and explore the …
Voice over IP (VoIP) is a key enabling technology for the migration of circuit-switched PSTN architectures to packet-based IP networks. However, this migration is successful only if the present problems in IP networks are addressed before deploying VoIP infrastructure on a large scale. One of the important issues that the present VoIP networks face is the problem of unwanted calls commonly referred to as SPIT (spam over Internet telephony). Mostly, these SPIT calls are from unknown callers who broadcast unwanted calls. There may be unwanted calls from legitimate and known people too. In this case, the unwantedness depends on social proximity of the communicating parties. For detecting these unwanted calls, I propose a framework that analyzes incoming calls for unwanted behavior. The framework includes a VoIP spam detector (VSD) that analyzes incoming VoIP calls for spam behavior using trust and reputation techniques. The framework also includes a nuisance detector (ND) that proactively infers the nuisance (or reluctance of the end user) to receive incoming calls. This inference is based on past mutual behavior between the calling and the called party (i.e., caller and callee), the callee's presence (mood or state of mind) and tolerance in receiving voice calls from the caller, and the social closeness between the caller and the callee. The VSD and ND learn the behavior of callers over time and estimate the possibility of the call to be unwanted based on predetermined thresholds configured by the callee (or the filter administrators). These threshold values have to be automatically updated for integrating dynamic behavioral changes of the communicating parties. For updating these threshold values, I propose an automatic calibration mechanism using receiver operating characteristics curves (ROC). The VSD and ND use this mechanism for dynamically updating thresholds for optimizing their accuracy of detection. In addition to unwanted calls …
The advent of sensory and communication technologies enables the generation and consumption of large volumes of streaming data. Many of these data streams are geo-referenced. Existing spatio-temporal databases and data stream management systems are not capable of handling real time queries on spatial extents. In this thesis, we investigated several fundamental research issues toward building a data-type-based real time geospatial data stream management system. The thesis makes contributions in the following areas: geo-stream data models, aggregation, window-based nearest neighbor operators, and query optimization strategies. The proposed geo-stream data model is based on second-order logic and multi-typed algebra. Both abstract and discrete data models are proposed and exemplified. I further propose two useful geo-stream operators, namely Region By and WNN, which abstract common aggregation and nearest neighbor queries as generalized data model constructs. Finally, I propose three query optimization algorithms based on spatial, temporal, and spatio-temporal constraints of geo-streams. I show the effectiveness of the data model through many query examples. The effectiveness and the efficiency of the algorithms are validated through extensive experiments on both synthetic and real data sets. This work established the fundamental building blocks toward a full-fledged geo-stream database management system and has potential impact in many applications such as hazard weather alerting and monitoring, traffic analysis, and environmental modeling.
As video capturing devices become more ubiquitous from surveillance cameras to smart phones, the demand of automated video analysis is increasing as never before. One obstacle in this process is to efficiently locate where a human operator’s attention should be, and another is to determine the specific types of activities or actions without ambiguity. It is the special interest of this dissertation to locate spatial and temporal regions of interest in videos and to develop a better action representation for video-based activity analysis. This dissertation follows the scheme of “locating then recognizing” activities of interest in videos, i.e., locations of potentially interesting activities are estimated before performing in-depth analysis. Theoretical properties of regions of interest in videos are first exploited, based on which a unifying framework is proposed to locate both spatial and temporal regions of interest with the same settings of parameters. The approach estimates the distribution of motion based on 3D structure tensors, and locates regions of interest according to persistent occurrences of low probability. Two contributions are further made to better represent the actions. The first is to construct a unifying model of spatio-temporal relationships between reusable mid-level actions which bridge low-level pixels and high-level activities. Dense trajectories are clustered to construct mid-level actionlets, and the temporal relationships between actionlets are modeled as Action Graphs based on Allen interval predicates. The second is an effort for a novel and efficient representation of action graphs based on a sparse coding framework. Action graphs are first represented using Laplacian matrices and then decomposed as a linear combination of primitive dictionary items following sparse coding scheme. The optimization is eventually formulated and solved as a determinant maximization problem, and 1-nearest neighbor is used for action classification. The experiments have shown better results than existing approaches for regions-of-interest detection and action …
This dialog allows you to filter your current search.
Each of the World Regions listed note their name and the number of records that will be limited down to if you choose that option.
This dialog allows you to filter your current search.
Each of the Countries listed note their name and the number of records that will be limited down to if you choose that option.
This dialog allows you to filter your current search.
Each of the Decades listed note their name and the number of records that will be limited down to if you choose that option.
This dialog allows you to filter your current search.
Each of the Years listed note their name and the number of records that will be limited down to if you choose that option.
The list can be sorted by name or the count.
This dialog allows you to filter your current search.
Each of the Months listed note their name and the number of records that will be limited down to if you choose that option.
This dialog allows you to filter your current search.
Each of the Rights Access listed note their name and the number of records that will be limited down to if you choose that option.