BYU CS Graduate News

Jonathan Whetten's MS Thesis Defense

Computer Science Department — Thu, 19 Nov 2009 09:50:11 -0700

Strength in Numbers: Leveraging Operator Teams to Control Large Numbers of Remote Robots

ABSTRACT:

Robots and other automated systems have potential use in many different ﬁelds. As the scope of robot applications that robots are used for increases, there is a growing desire to have human operators manage multiple robots. Typical methods of enabling operators to multi-task in this way involve some combination of user interfaces that support human cognition and advanced robot autonomy. Our research explores a complementary method of managing multiple robots by utilizing operator teams. The evidence suggests that for appropriate task scenarios, two cooperating operators can be more than twice as effective as one operator working alone.

Colloquium with David Page Thursday, November 19th at 11:00 am in 1170 TMCB

Computer Science Department — Tue, 17 Nov 2009 10:14:25 -0700

Colloquium: Machine Learning for Healthcare

Abstract:

Machine learning has great potential for impact on society through its use in predictive personalized medicine (PPM). In PPM, predictive models can be used to better make treatment decisions, including diagnosis, selection of drugs and drug dosages, and preventive medicine. This talk will present the use of machine learning for building predictive models from clinical and genetic data. It will also present advantages in particular of statistical relational learning (SRL) for analyzing such data. The talk will include applications to mammography, coumadin (warfarin) therapy, and drug adverse events. It will discuss a particular SRL approach called "View Learning", where the SRL system learns to define a new view of the database being analyzed. It will also present plans of the Wisconsin Genomics Initiative for PPM.

Biography:

David Page received his Ph.D. in computer science from the University of Illinois at Urbana-Champaign in 1993. He was a research scientist in the Oxford University Computing Laboratory from 1993 to 1997, where he also served as a visiting member of the Faculty of Mathematics from 1995-1997. David is now a professor at the University of Wisconsin-Madison, in the Dept. of Biostatistics and Medical Informatics (School of Medicine and Public Health) and Dept. of Computer Sciences. He is also a member of the University of Wisconsin Comprehensive Cancer Center and the Genome Center of Wisconsin, and he is a member of the scientific advisory boards for the Wisconsin Genomics Initiative and the Observational Medical Outcomes Partnership. David's primary research interests are in machine learning analysis of combined clinical and genetic data and in learning statistical models from multi-relational data.

Richard Arthur's PhD Dissertation Proposal

Computer Science Department — Wed, 11 Nov 2009 16:30:52 -0700

Powerful Portable Interaction via Device Annexation

ABSTRACT:

People are mobile and their computing is increasingly nomadic. However, portable devices have limited interactive power because of their physical size. This proposal advocates annexing display servers to compensate for the limited interactivity of portable devices. Display servers provide increased interactive power by supplying screens as well as input devices. The personal device must annex display servers wirelessly to maximize flexibility. The protocol for wirelessly communicating input and output must be established. In addition to establishing a communication protocol, this research will explore some newly opened interactive needs. First, the personal device must protect the user’s privacy by ensuring sensitive data is not shown on distrusted screens. Second, users should annex display servers and apply their own window management techniques without interacting with the display server or learning the display server’s software on the spot. Third, multiple users may opt to simultaneously annex a single display server. And fourth, a user may opt to simultaneously annex multiple display servers.

Richard Arthur's Research Area Exam

Computer Science Department — Wed, 11 Nov 2009 16:25:16 -0700

(Please also attend his Dissertation Proposal on Friday, November 20, 2009 at 10:00 am in the CS Conference Room (3365 TMCB). See Proposal announcement for details.)

Aaron Dennis' MS Thesis Defense/PhD Qualifying Presentation

Computer Science Department — Tue, 10 Nov 2009 09:26:57 -0700

Noninvasive Estimation of Pulmonary Artery Pressure Using Heart Sound Analysis

ABSTRACT:

Right-heart catheterization is the most accurate method for estimating pulmonary artery pressure (PAP). Because it is an invasive procedure it is expensive, exposes patients to the risk of infection, and is not suited for long-term monitoring situations. Medical researchers have shown that PAP inﬂuences the characteristics of heart sounds. This suggests that heart sound analysis is a potential noninvasive solution to the PAP estimation problem.

This thesis describes the development of a prototype system, called PAPEr, which estimates PAP noninvasively using heart sound analysis. PAPEr uses patient data with machine learning algorithms to build models of how PAP aﬀects heart sounds. Data from 20 patients was used to build the models and data from another 31 patients was used as a validation set. PAPEr diagnosed these 31 patients for pulmonary hypertension with an accuracy of 77 percent.

Michael R. Smith's MS Thesis Defense/PhD Qualifying Presentation

Computer Science Department — Wed, 04 Nov 2009 11:53:30 -0700

An Empirical Study of Instance Hardness

ABSTRACT:

Most widely accepted measures of performance for learning algorithms, such as accuracy and area under the ROC curve, provide information about behavior at the data set level. They say nothing about which instances are misclassified, whether two learning algorithms with the same classification accuracy on a data set misclassify the same instances, or whether there are instances misclassified by all learning algorithms. These questions about behavior at the instance level motivate our empirical analysis of instance hardness, a measure of expected classification accuracy for an instance. We analyze the classification of 57 data sets using 9 learning algorithms. Of the over 175000 instances investigated, 5% are misclassified by all 9 of the considered learning algorithms, and 15% are misclassified by at least half. We find that the major cause of misclassification for hard instances is class overlap, manifested as outliers and border points which can be exacerbated by class skew. We analyze these causes and show to what extent each leads to misclassifications, both in isolation and jointly. 19.8% of all misclassified instances are outliers, 71.3% are border points, and 21% belong to a minority class. We also find that 91.6% of all outliers and 38.3% of all border points are misclassified whereas only 3.5% of instances without class overlap are misclassified. We propose a set of heuristics to predict when an instance will be hard to correctly classify. Additionally, we analyze how different learning algorithms perform on tasks with varying degrees of outliers, border points and class skew.

Daniel Adams' MS Thesis Defense

Computer Science Department — Wed, 04 Nov 2009 11:47:56 -0700

Feature-Based Interactive Terrain Sketching

ABSTRACT:

Procedural generation techniques are able to quickly and cheaply produce large areas of terrain. However, these techniques produce results that are not easily directable and often require artists to edit the results by hand to achieve the desired layout. This paper proposes a sketch-based system for controlling fractal terrain that allows for a wide variety of terrain feature types. Artists sketch features rather than constrained points or elevations. The system is interactive, provides quick on-demand previews of the terrain, and allows for iterative design modifications. Interaction between features is handled in a realistic fashion. An arbitrary vertex insertion order midpoint displacement algorithm is also described which provides the necessary flexibility and constraints for the terrain generation system.

Tim van der Horst's PhD Dissertation Defense

Computer Science Department — Mon, 26 Oct 2009 11:24:27 -0600

Convenient Decentralized Authentication using Passwords

ABSTRACT:

Proof of email address ownership is typically required to create an account and to reset a password when it is forgotten. Despite its shortcomings (e.g., latency, vulnerability to passive attack), this approach is a practical solution to the difficult problem of authenticating strangers on the Internet.

This research utilizes this emergent, lightweight relationship with email providers to offload primary user authentication from service providers; thus reducing the need for service provider-specific passwords. Our goal is to provide decentralized authentication that maintains the convenience and portability of passwords, while improving its assurances (especially against phishing). Also, as existing approaches to online decentralized authentication are typically geared for web-based logins, our new protocols are designed to unify user authentication across the application and network (especially wireless) layers.

Kenneth Sundberg's PhD Dissertation Proposal

Computer Science Department — Wed, 30 Sep 2009 16:35:25 -0600

Partition Based Phylogenetic Search

ABSTRACT:

Evolutionary relationships are of critical importance in modern biology. Thus the process of inferring these relationships, phylogenetic search, is an important problem. This problem is known to be NP-Hard, and so heuristic methods are needed. This work proposes a new understanding of the solution space and exploiting this understanding looks to develop new search techniques.

Kenneth Sundberg's Research Area Exam

Computer Science Department — Wed, 30 Sep 2009 16:25:51 -0600

ABSTRACT:

Phylogenetic Search, a computationally difficult problem (NP-Hard), is of use to a wide variety of biological problems. This problem has been attacked through a number of heuristic methods,most notably hill climbing. Other heuristics such as genetic algorithms and simulated annealing have also been applied. However, work continues as there remain problems of interest that lie outside of current capabilities. A new direction in the field is the study of treespace as a whole, in an effort to devise new search techniques. This review contains a discussion of all these techniques, the major programs which implement them, and an in depth review of the most commonly used algorithm TBR.