Select a calendar:
Filter August Events by Event Type:
SUNMONTUEWEDTHUFRISAT
University Calendar
Events for August
-
PhD Defense - Marc Spraragen
Thu, Aug 08, 2013 @ 01:00 PM - 03:00 PM
Thomas Lord Department of Computer Science
University Calendar
Committee: Prof. Michael Zyda (Chair), Prof. Michael Arbib, Dr. James Blythe, Prof. Azad Madni (Outside Member)
Title: Computational Modeling of Emotional Effects on Decision-Making by Agents in Game-based Simulations
Abstract:
My research is focused on computational models of emotional effects on agent decision-making in game-based simulations.
AI agents are playing an increasingly important role in game-based simulations. Agent behavior has been improving from the purely robotic to more humanlike models based on ACT-R and other cognitive architectures. An important aspect of humanlike behavior is changing emotional states. However, effects of emotional state on decision-making have not been sufficiently addressed in agent architectures used in game-based simulations. Fortunately, such effects are well studied in cognitive science. That body of work provides a sound basis for creating computational models of emotionally sensitive agents.
The research problem I addressed is the development of computational agent models that reflect the influence of human emotional state on decision-making in game-based simulations. A motivating example is that of an agent running a nuclear power plant simulation as an operator. The agent, observing a sudden drop in cooling water pressure, needs to make several correct assumptions and decisions in
short order. Those decisions require attention focus, recall
ability, and precise choices, all of which are human processes susceptible to changes in emotional state. For instance, an operator in a positive emotional state is more likely to be optimistic and underestimate the chances of a pipe rupture or similar critical cause for the loss of water pressure, whereas an operator in a negative emotional state is more likely to suspect such a cause and act accordingly. My research hypothesis is that an emotional agent architecture that combines principles from cognitive science and computational modeling can produce realistic decision-making behaviors in tasks required for complex system simulation domains.
Location: Henry Salvatori Computer Science Center (SAL) - 222
Audiences: Everyone Is Invited
Contact: Lizsl De Leon
-
PhD Defense - Chengjie Zhang
Thu, Aug 22, 2013 @ 01:00 PM - 03:00 PM
Thomas Lord Department of Computer Science
University Calendar
Design of Cost-Efficient Multi-Sensor Collaboration in Wireless Sensor Networks
committee
Chair:
John Heidemann
Member:
Ramesh Govindan
Bhaskar Krishnamachari
Recent years have witnessed an increasing demand for monitoring tasks in industrial applications. Although effective in some applications, sensornet uptake has been slow in this emerging area, as shown by slow sensornet deployment in industry. Industries prefer well-tested but often expensive or complex sensing solutions because they provide known levels of accuracy, but this choice makes many problems uneconomic. The sensornet research community has made significant progress towards real-world applications with some pilot deployments. While sensornet research is promising, current prototypes are often not cost-effective or still in the early stages. Industry remains slow to adopt these approaches, because they are not seen to address concerns about accuracy for industry-relevant problems.
In this thesis, we propose Multi-Sensor Collaboration to achieve low-cost yet accurate event detection and enable sensornet usage in cost-sensitive industrial applications. We find that four advantages of collaboration improve cost-effectiveness. First, collaborative sensing can improve accuracy by suppressing false alarms with redundant or heterogeneous sensors. Second, collaborative sensing reduces capital cost by enabling low-cost sensors to be accurate enough to reach actionable results. Third, collaboration can reduce deployment cost, because it enables non-invasive sensing to provide sufficient accuracy with much less expensive installation. Finally, auto-tuning is important to reduce deployment costs, and collaborative sensing can assist auto-tuning by allowing sensors in different modalities to tune each other with their unique information.
The thesis of this proposed dissertation is that Multi-sensor collaboration enables sensor networks to accomplish real-world event detection tasks that are impractical for single-sensor systems. To frame the application domain, we categorize sensing applications by their two orthogonal propertiesâ collaboration scheme and sensing modality. Collaboration scheme, namely the relationship between sensors, is usually in two distinctive formsâcompetitive and complementary. Competitive collaboration means redundantly suppressing less accurate sensors’ results; complementary collaboration combines all relevant sensors’ partial results to form the final result. Modality means the type of the raw input of a sensor. To explore the application domain, we study both collaborations with either modality choice in three example applications. First, we evaluate signature matching in a vehicle classification context to study single-modal competitive collaboration. Second, we present a design of steam-choke blockage-detection system to study single-modal complementary collaboration. Finally, we implement and evaluate a detection system for oil-retrieval-line blockage to extend our complementary type study to multi-modality. We prove sensor collaboration can achieve cost-efficiency in the forgoing three specific applications. These applications are useful and allow deployment of sensing where not possible before. Further, the commonality between these applications and a large group of relevant applications strongly suggest that collaborative sensing help a larger application domain.
Location: Henry Salvatori Computer Science Center (SAL) - 322
Audiences: Everyone Is Invited
Contact: Lizsl De Leon
