CSE590U - Winter 2008 (T 1:30-2:20, CSE 403)

(please add yourself to the cse590u@cs mailing list)

Presentation Schedule

Date Topic / Reading Material Presenter
08 Jan   Carl Hartung
15 Jan Usability and Feasibility of PmEB: A Mobile Phone Application for Monitoring Real Time Caloric Balance Adrienne Andrew
22 Jan Positioning and Orientation in Indoor Environments Using Camera Phones
Summary: I'll discuss our work on a system to support an augmented reality personal navigation system on camera phones. An accurate camera pose is necessary to augment the image with arrows and labels. A rough location estimate from WiFi, an image from the camera phone, and a building floorplan are used to solve for the camera pose. This basic framework has many dimensions to be explored and can support a variety of augmented reality type applications.
Harlan Hile
29 Jan Opportunities for Intelligent Interfaces Aiding Healthcare in Low-Income Countries
Summary: Child mortality is one of the most pressing health concerns . almost 10 million children die worldwide each year before reaching their fifth birthday, mostly in low-income countries. To aid overburdened and undertrained health workers the World Health Organization (WHO) and United Nations Children.s Fund (UNICEF) have developed clinical guidelines, such as the Integrated Management of Childhood Illness (IMCI) to help with the classification and treatment of common childhood illness. To help with deployment, we have developed an electronic version (e- IMCI) that runs on a PDA. From July to September 2007, we ran a pilot of e-IMCI in southern Tanzania. The system guides health workers step-by-step through the treatment algorithms and automatically calculates drug doses. Our results suggest that electronic implementations of protocols such as IMCI can reduce training time and improve adherence to the protocol. They also highlight several important challenges including varying levels of education, language and expertise, which could be most adequately addressed by implementing novel intelligent user interfaces and systems.
Brian DeRenzi
Summary: The specific goal of the ASSIST project is to develop a personal recording device to be worn by soldiers in Iraq that captures video, audio, location, and other sensor information while soldiers are on patrol. The system combines work in activity recognition, localization, speak-recognition, and other techniques. In this talk, I will present our experiences with the ASSIT project and our broader goals in our research focus on life-logging technologies.
Brian Ferris
12 Feb Project ACCESS: Assisted Cognition in Community, Employment, and Support Settings
Summary: The goal of Project ACCESS is to create novel technologies that will enhance the quality of life of people with cognitive disabilities. In our project, we continue to focus on problems associated with navigating physical surroundings. These can often be confusing as traveling from one end of a city to another for employment or even navigating a complex medical building can be quit challenging. More broadly, we want to consider several other aspects of community integration including reminders for errands, assisting in social gathering, and improving performance on the job. We have two primary objectives: (a) developing technologies to support individuals with cognitive disabilities and their caregivers that will allow for greater independence; and (b) refining and implementing participatory processes for gathering and utilizing data from consumers and caregivers that guide the development process.
Alan L. Liu
19 Feb Cascadia: A System for Specifying, Detecting, and Managing RFID Events
Summary: Cascadia is a system that provides RFID-based pervasive computing applications with an infrastructure for specifying, extracting and managing meaningful high-level events from raw RFID data. In this talk I'll present the design and implementation of Cascadia and demonstrate its performance through measurements on traces collected in our building-wide RFID deployment.
Evan Welbourne
26 Feb Secret Handshake: Context Aware Access Control
Summary: Radio Frequency IDentification (RFID) based devices are often used for communicating potentially sensitive information. RFID tags, by default, communicate with all surrounding devices, both good and malicious; this exposes several security vulnerabilities involving unwanted data reads. We propose an approach that we call "context-aware communication", which limits a tag's transmissions by inferring whether reads are authorized, based on on-chip accelerometer readings. We further show that advances in tag design enable us to completely perform this processing and sensing on passive tags. The advantage of these tags is that they do not require an internal power source, making them attractive as a light-weight, yet intelligent medium for identification.
Alexei Czeskis & Karl Koscher
04 Mar (Paper linked here)
Summary: Statistical machine learning continues to show promise as a tool for solving complex problems in a variety of domains, and as such an increasing number of developers are looking to apply statistical machine learning algorithms to build applications. To understand typical usage and possible difficulties of using statistical machine learning as a component within a larger application, we interviewed researchers experienced in integrating machine learning into their development process. Based on our first study, we conducted an experiment to observe some of the behavior described in our interviews through laboratory studies of developers attempting to build a simple application that uses machine learning. In this paper, we discuss three obstacles faced by developers and propose solutions for improving the accessibility of statistical machine learning algorithms.
Kayur Patel
11 Mar Demonstrating the Feasibility of Using Forearm Electromyography for Muscle-Computer Interfaces
Summary: We explore the feasibility of muscle-computer interfaces (muCIs): an interaction methodology that directly senses and decodes human muscular activity rather than relying on physical device actuation or user actions that are externally visible or audible. As a first step towards realizing the mu- CI concept, we conducted an experiment to explore the potential of exploiting muscular sensing and processing technologies for muCIs. We present results demonstrating accurate gesture classification with an off-the-shelf electromyography (EMG) device. Specifically, using 10 sensors worn in a narrow band around the upper forearm, we were able to differentiate position and pressure of finger presses, as well as classify tapping and lifting gestures across all five fingers. We conclude with discussion of the implications of our results for future muCI designs.
Scott Saponas

This schedule is also available as a google calendar: http://www.google.com/calendar/ical/70h8fpf0ekger89v4comda2ff8%40group.calendar.google.com/public/basic.ics