Organizational Unit:

School of Computer Science

Permanent Link

https://hdl.handle.net/1853/70781

Parent Organization

Organizational Unit

College of Computing

ArchiveSpace Name Record

https://finding-aids.library.gatech.edu/agents/corporate_entities/945

Full item page

Publication Search Results

Now showing 1 - 10 of 49

DDDAS-TMRP: Dynamic, simulation-based management of surface transportation systems

(Georgia Institute of Technology, 2009-12-21) Fujimoto, Richard M. ; Leonard, John D., ll ; Guensler, Randall L. ; Schwan, Karsten ; Hunter, Michael D.
Temporal streams: programming abstractions for distributed live stream analysis applications

(Georgia Institute of Technology, 2009-10-20) Hilley, David B

Continuous live stream analysis applications are increasingly common. Video-based surveillance, emergency response, disaster recovery, and critical infrastructure monitoring are all examples of such applications. These applications are distributed and typically require significant computing resources (like a cluster of workstations) for analysis. In addition to live data, many such applications also require access to historical data that was streamed in the past and is now archived. While distributed programming support for traditional high-performance computing applications is fairly mature, existing solutions for live stream analysis applications are still in their early stages and, in our view, inadequate. We explore the system-level value of recognizing temporal properties -- a critical aspect of the application domain. We present "temporal streams", a programming model supporting a higher-level, domain-targeted programming abstraction for such applications. It provides a simple but expressive stream abstraction encompassing transport, manipulation and storage of streaming data. The semantics of the programming model are tailored to the application domain by explicitly recognizing the temporal aspects of continuous streams, providing a common interface for both time-based retrieval of current streaming data and data persistence. The unifying trait of time enables access to both current streaming data and archived historical data using the same interface; the communication and storage abstraction are the same -- a unified stream data abstraction, uniformly modeling stream data interactions. "Temporal streams" defines how distributed threads of computation interact implicitly via streams, but does not impose a particular model of computation constraining the interactions between distributed actors, targeting loosely coupled distributed systems with no centralized control. In particular, it targets stream analysis scenarios requiring significant signal processing on heavyweight streams such as audio and video. These unstructured streams are data rich but are not directly interpretable until meaningful features are extracted; consequently, feature detection and subsequent analysis are the major computational requirements. We also use the programming model as a vehicle for exploring systems software design issues, realizing "temporal streams" as a distributed runtime in the tradition of loosely coupled distributed systems with strong communication boundaries. We thoroughly examine the concrete software architecture and elements of implementation. We also describe two generations of system implementations, including the broad development philosophy, specific design principles and salient low-level details. The runtime is designed to be relatively lightweight and suitable as a substrate for higher-level, more domain-specific middleware or application functionality. Even with a relatively simple programming model, a carefully designed system architecture can provide a surprisingly rich and flexibly substrate for upper software layers. We also evaluate our system implementation in two ways; first, we present a series of quantitative experimental results designed to assess the performance of key primitives in our architecture in isolation. We also use motivating applications to evaluate "temporal streams" in the context of realistic application scenarios. We develop three motivating applications and provide quantitative and qualitative analyses of these applications in the context of "temporal streams." We show that, although it provides needed higher-level functionality to enable live stream analysis applications, our runtime does not add significant overhead to the stream computation at the core of each application. Finally, we also review the relationship of "temporal streams" (both the programming model and architecture) to other approaches, including database-oriented Stream Data Management Systems (SDMS), various stream processing engines, stream programming languages and parallel batch processing systems, as well as traditional distributed programming systems and communication frameworks.
Low-cost and efficient architectural support for correctness and performance debugging

(Georgia Institute of Technology, 2009-07-15) Venkataramani, Guru Prasadh V.

With rapid growth in computer hardware technologies and architectures, software programs have become increasingly complex and error-prone. This software complexity has resulted in program crashes and even security threats. Correctness Debugging is making sure that the program does not exhibit any unintended behavior at runtime. A fully correct program without good performance does not lend any commercial success to the software product. Performance Debugging ensures good performance on hardware platforms. A number of prior debugging solutions either suffer from huge performance overheads or incur high implementation costs. We propose low-cost and efficient hardware solutions that target three specific correctness and performance problems, namely, memory debugging, taint propagation and comprehensive cache miss classification. Experiments show that our mechanisms incur low performance overheads and can be designed with minimal changes to existing processor hardware. While architects invest time and resources into designing high-end architectures, we show that it is equally important to incorporate useful debugging features into these processors in order to enhance the ease of use for programmers.
I/O Virtualization - from self-virtualizing devices to metadata-rich information appliances

(Georgia Institute of Technology, 2009-07-12) Schwan, Karsten ; Eisenhauer, Greg S. ; Gavrilovska, Ada
Extensions of principal components analysis

(Georgia Institute of Technology, 2009-06-29) Brubaker, S. Charles

Principal Components Analysis is a standard tool in data analysis, widely used in data-rich fields such as computer vision, data mining, bioinformatics, and econometrics. For a set of vectors in n dimensions and a natural number k less than n, the method returns a subspace of dimension k whose average squared distance to that set is as small as possible. Besides saving computation by reducing the dimension, projecting to this subspace can often reveal structure that was hidden in high dimension. This thesis considers several novel extensions of PCA, which provably reveals hidden structure where standard PCA fails to do so. First, we consider Robust PCA, which prevents a few points, possibly corrupted by an adversary, from having a large effect on the analysis. When applied to learning noisy logconcave mixture models, the algorithm requires only slightly more separation between component means than is required for the noiseless case. Second, we consider Isotropic PCA, which can go beyond the first two moments in identifying ``interesting' directions in data. The method leads to the first affine-invariant algorithm that can provably learn mixtures of Gaussians in high dimensions, improving significantly on known results. Thirdly, we define the ``Subgraph Parity Tensor' of order r of a graph and reduce the problem of finding planted cliques in random graphs to the problem of finding the top principal component of this tensor.
Exploring and visualizing the impact of multiple shared displays on collocated meeting practices

(Georgia Institute of Technology, 2009-05-18) Plaue, Christopher M.

A tremendous amount of information is produced in the world around us, both as a product of our daily lives and as artifacts of our everyday work. An emerging area of Human-Computer Interaction (HCI) focuses on helping individuals manage this flood of information. Prior research shows that multiple displays can improve an individual user's ability to deal with large amounts of information, but it is unclear whether these advantages extend for teams of people. This is particularly relevant as more employees are spending large portions of their workdays in meetings My contribution to HCI research is empirical fieldwork and laboratory studies investigating how multiple shared displays improve aspects of teamwork. In particular, I present an insight-based evaluation method for analyzing how teams collaborate on a data-intensive sensemaking task. Using this method, I show how the presence and location of multiple shared displays impacted the meeting process with respect to performance, collaboration, and satisfaction. I also illustrate how multiple shared displays engaged team members who might not have otherwise contributed to the collaboration process. Finally, I present Mimosa, a software tool developed to visualize large volumes of time series data. Mimosa combines aspects of information visualization with data analysis, facilitating a deep and iterative exploration of relationships within large datasets.
Using First Order Inductive Learning as an Alternative to a Simulator in a Game Artificial Intelligence

(Georgia Institute of Technology, 2009-05-04) Long, Kathryn Anna

Currently many game artificial intelligences attempt to determine their next moves by using a simulator to predict the effect of actions in the world. However, writing such a simulator is time-consuming, and the simulator must be changed substantially whenever a detail in the game design is modified. As such, this research project set out to determine if a version of the first order inductive learning algorithm could be used to learn rules that could then be used in place of a simulator. By eliminating the need to write a simulator for each game by hand, the entire Darmok 2 project could more easily adapt to additional real-time strategy games. Over time, Darmok 2 would also be able to provide better competition for human players by training the artificial intelligences to play against the style of a specific player. Most importantly, Darmok 2 might also be able to create a general solution for creating game artificial intelligences, which could save game development companies a substantial amount of money, time, and effort.
Distributed Feature Extraction Using Cloud Computing Resources

(Georgia Institute of Technology, 2009-05-04) Dalton, Steven

The need to expand the computational resources in a massive surveillance network is clear but traditional means of purchasing new equipment for short-term tasks every year is wasteful. In this work I will provide evidence in support of utilizing a cloud computing infrastructure to perform computationally intensive feature extraction tasks on data streams. Efficient off-loading of computational tasks to cloud resources will require a minimization of the time needed to expand the cloud resources, an efficient model of communication and a study of the interplay between the in-network computational resources and remote resources in the cloud. This report provides strong evidence that the use of cloud computing resources in a near real-time distributed sensor network surveillance system, ASAP, is feasible. A face detection web service operating on an Amazon EC2 instance is shown to provide processing of 10-15 frames per second.
Improving processor efficiency by exploiting common-case behaviors of memory instructions

(Georgia Institute of Technology, 2009-01-02) Subramaniam, Samantika

Processor efficiency can be described with the help of a number of desirable effects or metrics, for example, performance, power, area, design complexity and access latency. These metrics serve as valuable tools used in designing new processors and they also act as effective standards for comparing current processors. Various factors impact the efficiency of modern out-of-order processors and one important factor is the manner in which instructions are processed through the processor pipeline. In this dissertation research, we study the impact of load and store instructions (collectively known as memory instructions) on processor efficiency, and show how to improve efficiency by exploiting common-case or predictable patterns in the behavior of memory instructions. The memory behavior patterns that we focus on in our research are the predictability of memory dependences, the predictability in data forwarding patterns, predictability in instruction criticality and conservativeness in resource allocation and deallocation policies. We first design a scalable and high-performance memory dependence predictor and then apply accurate memory dependence prediction to improve the efficiency of the fetch engine of a simultaneous multi-threaded processor. We then use predictable data forwarding patterns to eliminate power-hungry hardware in the processor with no loss in performance. We then move to studying instruction criticality to improve processor efficiency. We study the behavior of critical load instructions and propose applications that can be optimized using predictable, load-criticality information. Finally, we explore conventional techniques for allocation and deallocation of critical structures that process memory instructions and propose new techniques to optimize the same. Our new designs have the potential to reduce the power and the area required by processors significantly without losing performance, which lead to efficient designs of processors.
Evaluating Bluetooth as a Medium for Botnet Command and Control

(Georgia Institute of Technology, 2009) Jain, Nehil ; Lee, Wenke ; Sangal, Samrit ; Singh, Kapil ; Traynor, Patrick

Malware targeting mobile phones is being studied with increasing interest by the research community. While such attention has previously focused on viruses and worms, many of which use near-field communications in order to propagate, none have investigated whether more complex malware such as botnets can effectively operate in this environment. In this paper, we investigate the challenges of constructing and maintaining mobile phone-based botnets communicating nearly exclusively via Bluetooth. Through extensive large-scale simulation based on publicly available Bluetooth traces, we demonstrate that such a malicious infrastructure is possible in many areas due to the largely repetitive nature of human daily routines. In particular, we demonstrate that command and control messages can propagate to approximately 2/3 of infected nodes within 24 hours of being issued by the botmaster. We then explore how traditional defense mechanisms can be modified to take advantage of the same information to more effectively mitigate such systems. In so doing, we demonstrate that mobile phone-based botnets are a realistic threat and that defensive strategies should be modified to consider them.