Pedro Szekely

Information Integration & Mashups

Karma

A general approach to dynamically extracting, modeling, and integrating data by example. This work, implemented in a system called Karma, allows a user to interactively construct an integrated view of a set of sources simply by providing examples of which information to extract and how to integrate the data sources. Read more Collaborator: Craig Knoblock.

2007 - present.

User Interfaces, Visualization & Data Analytics

Temporal Queries Using a Comic-Strip Metaphor

tbd

2007 - present.

Tools for Creating Customized Visualizations

tbd

2005 - 2008.

Model-Based User Interfaces

tbd

Multi-Agent Systems, Coordination, Planning & Scheduling

Criticality-Sensitive Coordination (CSC)

The goal is creating distributed intelligent software systems that will help fielded units adapt their mission plans as the situation around them changes and impacts their plans. Intelligent software Coordinators do this by reasoning about the tasks assigned to a given unit, the task timings, how the tasks interact with those of other units, and by evaluating possible changes such as changing task timings, task assignments, or selecting from pre-planned contingencies."

2005 - 2009.

Coordinated MANETs using RF-Guided Criticality-focused Hormones (C-MARCH) 

This program will develop intelligent autonomous radio relay nodes that exploit movement to establish and manage mesh networks in urban settings. The goal is to create small, inexpensive, smart robotic radio relay nodes that dismounted warfighters drop as they deploy in urban settings. The nodes then self-configure and form a mesh network - a temporary infrastructure that establishes communications over the region. As the situation changes, the nodes will adapt the network, such as self-healing if nodes are destroyed by the enemy.

2007 - 2008.

Scheduling Operations for US Marines Aviation

tbd

Education

Living Classroom 

Data-driven differentiated instruction uses a variety of data sources to build a profile of student achievements and needs, and uses this profile to recommend learning materials and lessons. Data sources include proprietary or off-the-shelf district systems, gradebooks, classroom assessments and other historical data, along with realtime clicker and netbook data generated by students themselves. Read moreCollaborators: Yu-Han Chang, Winnie Callahan, John Callahan, Romeo Sanchez.

2009 - present.