Email:

nixdell (at) cs (dot) washington (dot) edu

Mail:

Computer Science and Engineering
Box 352350
Seattle, WA 98195-2350

Office:

386, Paul G. Allen Center for Computer Science and Engineering

CV:

PDF version available here

Journal

Dell N., Shapiro L. G., Brinkley J. F., VIQUEN: A Visual Query Engine for RDF, submitted to the Journal of Biomedical Informatics (JBI), submitted 2011.

Conference

Dell, N., Breit N., Borriello G., Digitizing Paper-Based Vaccine Data via Mobile Imaging Technologies, the 2nd Annual ACM Conference on Computing for Development (DEV 2012).

Dell, N., Vaidyanathan V., Medhi I., Cutrell E., Thies W., "Yours is Better!" Participant Response Bias in HCI, the ACM SIGCHI Conference on Human Factors in Computing Systems (CHI 2012).pdf

Dell, N., Venkatachalam, S., Stevens, D., Yager, P., and Borriello, G. Towards a Point-of-Care Diagnostic System: Automated Analysis of Immunoassay Test Data on a Cell Phone, 5th ACM Workshop on Networked Systems for Developing Regions, 2011. pdf

Theses

Dell, N., VIQUEN: A Visual Query Engine for RDF, Advised by Linda Shapiro and James Brinkley. University of Washington, CSE Qualifying Examination Project, 2010. pdf

Dell, N., Animation of a Dance Notation Language using Motion Capture and Vertex Interpolation. Advised by Rudy Lapeer. University of East Anglia, CS Undergraduate Honors Thesis, 2004.

Digitizing Paper-Based Data via Mobile Imaging Technologies
In rural settings within developing countries, the majority of written records are collected and maintained using paper forms. Despite a recent proliferation of digital data collection systems, paper forms remain a ubiquitous, low-cost, and well-understood medium that will continue to be extensively utilized, particularly in developing countries, in years to come.

The goal of this project is to design and field test a mobile form scanning application that uses computer vision to automate the capture and processing of data from multiple choice paper forms. The application has the potential to transform paper-based data collection into a scalable digital system that significantly lowers time and cost for data capture, produces more reliable data from the last mile, and provides quick access to data to enable critical decision making by stakeholders.

This project, in collaboration with non-profit Village Reach, was recently awarded the Gates Foundation Grand Challenges Explorations grant.

A Point-of-Care Diagnostic System: Automated Analysis of Immunoassay Test Data on a Cell Phone
Many of the diagnostic tests administered in well-funded clinical laboratories are inappropriate for point-of-care testing in low-resource environments. As a result, inexpensive, portable immunoassay tests have been developed to facilitate the rapid diagnosis of many diseases common to developing countries. However, manually analyzing the test results at the point of care may be complex and error-prone for untrained users reading test results by eye, and providing methods for automatically processing these tests could significantly increase their utility.

In this project, we have designed and developed a mobile application that uses computer vision to automatically quantify immunoassay test data on a smart phone. The speed and accuracy demonstrated by the application suggest that cell-phone based immunoassay analysis could aid disease diagnosis at the point of care.

This project is joint work with the Yager lab in the UW Department of Bioengineering.

"Yours is better!" Participant Response Bias in HCI
Although HCI researchers and practitioners frequently work with groups of people that differ significantly from themselves, little attention has been paid to the effects these differences have on the evaluation of HCI systems. Via 450 interviews in Bangalore, India, we measure the response bias as participants provide feedback to researchers with varying social distances from themselves. We find that respondents are twice as likely to prefer a technological artifact that they believe to be developed by the interviewer, even when the alternative is identical. When the social distance between interviewer and participant increases to the point of needing a translator, the bias towards the interviewer's artifact increases to 5x. In fact, the interviewer's artifact is preferred even when it is degraded to be obviously inferior to the alternative. We conclude that participant response bias should receive more attention within the HCI community, especially when designing for underprivileged populations.

This work was done during a 2011 summer internship with the Technology for Emerging Markets Lab at Microsoft Research India.

VIQUEN: A Visual Query Engine for RDF
The biological and biomedical communities have been developing highly structured, rich data sets for representing, analyzing and integrating complex biomedical knowledge on the semantic web. However, the complexity of the query languages that have been developed to access these resources makes it dicult for non-technical users to explore the data sets that have been developed, limiting the utility and widespread adoption of both the data sets and the query languages. We present VIQUEN, a graphical query engine designed to allow users to express sophisticated queries, which are then compiled into a more complex underlying query language. After the query has been executed, users may explore the resulting graph using VIQUEN's graph visualization component. Preliminary evaluation suggests that VIQUEN is capable of expressing a wide variety of real use case biomedical queries.

This project is joint work with the Structural Informatics Group in the UW Department of Biological Structure.