UMBC Computer Science and Electrical Engineering
Ph.D. Dissertation Proposal

Paper form digitization for information systems strengthening and socio-economic development in developing countries

Huguens Jean

3:00pm Tuesday, 5 March 2013, ITE346, UMBC

In developing countries, people are now more likely to have access to a mobile phone than clean water, making cellular based technology the only viable medium for collecting, aggregating, and communicating local data so that it can be turned into useful information. While mobile phones have found broad application in reporting health, financial, and environmental data, many data collection methods still suffer from delays, inefficiency and difficulties maintaining quality. In environments with insufficient IT support and infrastructure, and among populations with limited education and experience with technology, paper forms rather than electronic methods remain the predominant means for data collection. To meet the digitization needs of paper driven data collection practices, this thesis proposes the development and study of a software platform that automatically converts unknown paper forms into digital structured data and uses human intelligence when necessary to improve its performance.

We begin by identifying a high-level system architecture for dealing with infrastructure constraints and human resources limitations. We then break the architecture into its integral pieces and organize them into three distinct functional and interacting stages: data collection, data conversion, and crowdsourcing. In the collection phase, we focus on visually detecting structurally identical form instances and transmitting the images of their raw input data to a remote server. During this phase, we present a novel framework for identifying specific form types by generating a multipart template for unknown forms and decomposing the form identification problem into three distinct tasks: similar image retrieval, learning, and duplicate matching. The conversion phase uses a mixture of Optical Character Recognition (OCR) and human annotations techniques to convert images into digital information and group structurally identical forms in their respective database table. In crowdsourcing, we investigates how to use low-end smartphones for collecting training information to improve OCR related tasks and verify the accuracy of converted input values. We pay special emphasis on identifying natural interaction forms that lower the technical and knowledge threshold for local residents. Furthermore, because crowdsourcing can also provide money to the mobile workers of its micro-tasking platform, we concurrently explore how systems that facilitate collaboration between humans and machines for improving the quality of intelligent information systems can be used a vehicle for delivering socioeconomic opportunities to developing countries.

Committee: Dr. Timothy Oates (Chair), Dr. Janet Rutledge, Dr. Fow-Sen Choa, Dr. Jesus Caban

New
York City Bus Trip

(seb)
Saturday, March
2, 2013
Bus departs The Commons Circle @ 8:00am
All Guests = $30
Ticket #: 96 of 103

PSA Norouz

Persian Student
Association
Saturday, March 2, 2013
UC Ballroom
Doors open @ 7:30pm
UMBC ID = FREE
Ticket #: 130 of 350

OZ Midnight Premiere

(seb)
Thursday, March 7, 2013
Bus departs The Commons Circle @ 11:00pm
All Guests = $5
Ticket #: 22 of 260

Medieval Times Bus Trip

(seb)
Saturday, March
9, 2013
Bus departs The Commons Circle @ 6:00pm
All Guests = $35
Ticket #: 8 of 49

Macklemore & Ryan Lewis Concert

(seb)
Sunday, April 21, 2013
8pm
Retriever Activity Center
All Guests = $15
Online Tickets = $20 (seb.umbc.edu/quadmania)
Ticket #: 1810 of 2500

—

TL;DR: We got you a fantastic course on mobile-first/responsive design from Code School. It’s available for Code School subscribers who pay $25/mo but for our dear subscribers ONLY, the course is now FREE. Go grab it and become a responsive code ninja! Click here!

—

Are you a front-end designer+developer (HTML, CSS)? Would you love to get some really awesome lessons and tips on all the hottest things happening in the “design for mobile” world?

You know how things have totally changed today and the focus is so much on three cool things: mobile-first, adaptive and responsive web designs! If you are a front-end developer, these are the things you  should definitely know. And as our loyal subscriber, we thought you must get to be the first to know about Code School and their comprehensive course on designing for mobile: Journey Into Mobile.

Journey Into Mobile is a 5-level course that will teach you everything you need to become an expert at making responsive and adaptive websites from scratch. It’s an awesome course where you can learn, practice and test – leisurely, at your own pace and from Jason, who leads the design team at Envy Labs. (so you know it’s a thorough-bred professional who’s going to teach you!).

The course covers:

• Mobile-first Design: where you get to learn the nuances of mobile-first design, relative font-sizes (you know the going gets tough when you’re doing ems instead of pxs)
• Adaptive Design: where you write code for context so the server does the work of adapting the output.
• Responsive Design: this is where it gets most interesting where you learn how to automatically and magically transform layouts according to the viewport width. You get to learn the tricks of the trade and become a magician of the mobile world, of course.

The course usually costs $25/mo (you need to be a subscriber at Code School to get it).

But as a loyal and awesome subscriber of Bootstrappist, you can access the whole course for FREE!

Yup! Click here and you’ll be taken to Code School as a special visitor. You can then sign-up and get the whole course for free. What are you waiting for? Go, go, go!

Note that this is exclusive only for our subscribers. Make use of this awesome opportunity to become a master of mobile/responsive design right away!

Click here get started!

The links to the course are affiliate links, we get a very small amount if you end up becoming a paid member, but you do NOT have to be a paid member to enjoy this free course.

The HTML Working Group has published two First Public Working Drafts today:

• Public Identifiers for entity resolution in XHTML. This document adds an additional public identifier that should be recognized by XHTML user agents and cause the HTML character entity definitions to be loaded. Unlike the identifiers already listed by the HTML5 specification, the identifier added by this extension references the set of definitions that is used by HTML.
• The srcset attribute. When authors adapt their sites for high-resolution displays, they often need to be able to use different assets representing the same image. We address this need for adaptive, bitmapped content images by adding a srcset attribute to the img element.

Learn more about the HTML Activity.

The World Bank’s Development Prospects Group (DECPG) is looking for a top-tier undergraduate student with a passion for software development to work on a part-time basis during the school year. The selected individual will play a significant role in designing, developing, testing, and launching various innovative software tools for World Bank economists. These projects are critical to DECPG’s operations and have the potential to be highly visible within The World Bank.

The selected candidate will be expected to work part-time during the school year, with the potential to continue on a full-time basis as a short-term consultant over the summer.  The location is 1818 H Street N.W., Washington, D.C.

Background

DECPG provides information, analysis and advice on the impact of trends in the world economy on developing countries, develops and documents the Bank's views on the state of the world economy, and produces some of the Bank's leading publications, including the Global Economic Prospects, the Global Development Horizons, and the Global Monitoring Report.

Selection Criteria

• Pursuing a Bachelor’s Degree in computer science, information systems, or computer engineering
• Demonstrated self-starter (Have you started your own business? Do you contribute to open source projects in your spare time?)
• Have a working knowledge of the .NET framework (preferably VB.NET). However, we are more interested in strong programming fundamentals than in knowledge of any particular programming language
• Basic understanding of database design and operation; familiarity with SQL (ideally either MySQL or MSSQL)
• Strong understanding of programming design patterns and data structures
• The ideal candidate will have some exposure to the fundamentals of macroeconomics, statistics, or econometrics. However, this is not required.
• Good interpersonal skills and ability to work in a team environment
• Must be self-motivated and inspired to learn
• Ability to deal sensitively in multi-cultural environments and build effective working relations with colleagues
• Effective verbal and written communication skills

Due to the high volume of resumes that we normally receive, we will only be able to contact short listed candidates. Please send all resumes to David Horowitz (Sorry, you need javascript to view this email address. ) with the subject "Application for STC 2013"