GVU Technical Report Series

Series

GVU Technical Report Series

Permanent Link

https://hdl.handle.net/1853/71001

Series Type

Publication Series

Associated Organization(s)

Organizational Unit

GVU Center

Full item page

Publication Search Results

Now showing 1 - 10 of 214

CENTRIST: A Visual Descriptor for Scene Categorization

(Georgia Institute of Technology, 2009-07-23) Wu, Jianxin ; Rehg, James M.

CENTRIST (CENsus TRansform hISTogram), a new visual descriptor for recognizing topological places or scene categories, is introduced in this paper. We show that place and scene recognition, especially for indoor environments, require its visual descriptor to possess properties that are different from other vision domains (e.g. object recognition). CENTRIST satisfy these properties and suits the place and scene recognition task. It is a holistic representation and has strong generalizability for category recognition. CENTRIST mainly encodes the structural properties within an image and suppresses detailed textural information. Our experiments demonstrate that CENTRIST outperforms the current state-of-the art in several place and scene recognition datasets, compared with other descriptors such as SIFT and Gist. Besides, it is easy to implement. It has nearly no parameter to tune, and evaluates extremely fast.
Recognizing Sign Language from Brain Imaging

(Georgia Institute of Technology, 2009) Mehta, Nishant A. ; Starner, Thad ; Jackson, Melody Moore ; Babalola, Karolyn O. ; James, George Andrew

The problem of classifying complex motor activities from brain imaging is relatively new territory within the fields of neuroscience and brain-computer interfaces. We report positive sign language classification results using a tournament of pairwise support vector machine classifiers for a set of 6 executed signs and also for a set of 6 imagined signs. For a set of 3 contrasted pairs of signs, executed sign and imagined sign classification accuracies were highly significant at 96.7% and 73.3% respectively. Multiclass classification results also were highly significant at 66.7% for executed sign and 50% for imagined sign. These results lay the groundwork for a brain-computer interface based on imagined sign language, with the potential to enable communication in the nearly 200,000 individuals that develop progressive muscular diseases each year.
An Ethical Governor for Constraining Lethal Action in an Autonomous System

(Georgia Institute of Technology, 2009) Arkin, Ronald C. ; Ulam, Patrick D. ; Duncan, Brittany

The design, prototype implementation, and demonstration of an ethical governor capable of restricting lethal action of an autonomous system in a manner consistent with the Laws of War and Rules of Engagement is presented.
Responsibility and Lethality for Unmanned Systems: Ethical Pre-mission Responsibility Advisement

(Georgia Institute of Technology, 2009) Arkin, Ronald C. ; Wagner, Alan R. ; Duncan, Brittany

This paper provides an overview, rationale, design, and prototype implementation of a responsibility advisor for use in autonomous systems capable of lethal target engagement. The ramifications surrounding the potential use of operator overrides is also presented. The results of this research have been integrated into the MissionLab mission specification and demonstrated on a relevant military scenario.
An Ethical Adaptor: Behavioral Modification Derived from Moral Emotions

(Georgia Institute of Technology, 2009) Arkin, Ronald C. ; Ulam, Patrick D.

This paper presents the motivation, basis and a prototype implementation of an ethical adaptor capable of using a moral affective function, guilt, as a basis for altering a robot’s ongoing behavior. While the research is illustrated in the context of the battlefield, the methods described are believed generalizable to other domains such as eldercare and are potentially extensible to a broader class of moral emotions, including compassion and empathy.
Visualization of Exception Handling Constructs to Support Program Understanding

(Georgia Institute of Technology, 2009) Shah, Hina ; Görg, Carsten ; Harrold, Mary Jean

This paper presents a new visualization technique for supporting the understanding of exception-handling constructs in Java programs. To understand the requirements for such a visualization, we surveyed a group of software developers, and used the results of that survey to guide the creation of the visualizations. The technique presents the exception-handling information using three views: the quantitative view, the flow view, and the contextual view. The quantitative view provides a high-level view that shows the throw-catch interactions in the program, along with relative numbers of these interactions, at the package level, the class level, and the method level. The flow view shows the type-throw-catch interactions, illustrating information such as which exception types reach particular throw statements, which catch statements handle particular throw statements, and which throw statements are not caught in the program. The contextual view shows, for particular type-throw-catch interactions, the packages, classes, and methods that contribute to that exception-handling construct. We implemented our technique in an Eclipse plugin called EnHanCe and conducted a usability and utility study with participants in industry.
Using In-Home Power Lines to Extend the Range of Low-Power Wireless Devices

(Georgia Institute of Technology, 2009) Stuntebeck, Erich P. ; Robertson, Thomas ; Abowd, Gregory D. ; Patel, Shwetak N.

This work demonstrates the feasibility of using existing in-home electrical wiring to extend the operational range of certain wireless devices. Specifically, a wireless keyboard operating at 27 MHz, which has an operational range of 1.5 – 2 meters on its own, was extended to work throughout a 3-story 4,000 square foot / 371 square meter home by coupling the antenna port on its receiver to the power lines. Coupling between the keyboard and the power lines occurred over the air, and coupling at the receiver was accomplished capacitively by simply wrapping a wire connected to the receiver’s antenna port several times around a standard electrical device cord plugged into a wall socket. This phenomenon of the power line as a communications infrastructure for inexpensive and lowpower wireless devices has a variety of interesting potential avenues of research in the home.
Playing Detective: Using AI for Sensemaking in Investigative Analysis

(Georgia Institute of Technology, 2009) Goel, Ashok K. ; Adams, Summer ; Cutshaw, Neil ; Sugandh, Neha

The sensemaking task in investigative analysis generates models that connect entities and events in an input stream of data. We describe two knowledge systems for aiding sensemaking in investigative analysis. The Spade system uses crime schemas to generate an explanatory hypothesis and past cases to validate the hypothesis. The STAB system represents crime schemas as hierarchical scripts with goals and states. It generates multiple explanatory hypotheses for an input data stream containing interleaved sequences of events, recognizes intent in a specific event sequence, and calculates confidence values for the generated hypotheses. We view STAB and Spade as automated cognitive assistants to human analysts: they may support sensemaking in investigative analysis by generating and managing multiple competing hypotheses.
inSpace: Co-Designing the Physical and Digital Environment to Support Workplace Collaboration

(Georgia Institute of Technology, 2008) Voida, Stephen ; McKeon, Matt ; Le Dantec, Christopher A. ; Forslund, C. ; Verma, Puja ; McMillan, B. ; Bunde-Pedersen, J. ; Edwards, W. Keith ; Mynatt, Elizabeth D. ; Mazalek, Ali

In this paper, we unpack three themes for the multidisciplinary codesign of a physical and digital meeting space environment in supporting collaboration: that social practices should dictate design, the importance of supporting fluidity, and the need for technological artifacts to have a social voice. We describe a prototype meeting space named inSpace that explores how design grounded in these themes can create a user-driven, information-rich environment supporting a variety of meeting types. Our current space includes a table with integrated sensing and ambient feedback, a shared wall display that supports multiple concurrent users, and a collection of storage and infrastructure services for communication, and that also can automatically capture traces of how artifacts are used in the space.
The Use of Different Technologies During a Medical Interview: Effects on Perceived Quality of Care

(Georgia Institute of Technology, 2007-10) Caldwell, Britt ; DeBlasio, Julia M. ; Jacko, Julie A. ; Kintz, Erin ; Lyons, Kent ; Mauney, Lisa M. ; Starner, Thad ; Walker, Bruce N.

This two-phase study examines a physician’s use of one of five different types of technology to note a patient’s symptoms during the medical interview. In this between-subjects design, 342 undergraduates viewed one of several videos that demonstrated one condition of the doctor/patient interaction. After viewing the interaction, each participant completed a series of questionnaires that evaluated their general satisfaction with the quality of care demonstrated in the medical interview. A main effect of technology condition was present in both phases. Further, in Phase 2 we found that drawing the participant’s attention to the type of technology used has a divergent effect on their general satisfaction with the doctor/patient interaction depending on the technology condition. These findings have implications for healthcare providers such as how to address technology and which type of technology to use.