Martin, Fred: October 2012 Archives

From the Chair, Prof. Jie (Jed) Wang:

“I am delighted to welcome three new faculty members to join the department. They are Dr. Anne Mulhern (Lecturer), Dr. Anna Rumshisky (Assistant Professor), and Dr. Kate Saenko (Assistant Professor).
Dr. Mulhern will be primarily teaching lower-level undergraduate core courses.
Dr. Rumshisky is an expert in natural language processing and Dr. Saenko is an expert in computer vision. These two areas have many important applications and funding opportunities from federal funding agencies and industries.
All three bring much needed new talents to the department that will benefit our students and help increase our visibility.”
Here is a brief introduction to our new faculty:

Dr. Mulhern received her doctorate from the University of Wisconsin-Madison in 2010. Her principal interests are logic and languages. She finds the Curry-Howard isomorphism, which describes a fundamental relationship between logics and programming language type-systems a fascinating subject.

She has been teaching various computer science topics since her first semester at the University of Wisconsin when she was one of a large squad of Teaching Assistants for the introductory programming class which had an enrollment of more than a thousand students. Pleasantly surprised to find herself both good at and interested in teaching she has continued to teach at regular intervals ever since.

Dr. Anna Rumshisky's primary area of research is natural language processing, with applications in clinical informatics, computational lexical semantics, and text processing for digital humanities and social science.

Her work focuses on the development of data-informed unsupervised learning methods as well as on leveraging existing resources and information-harvesting techniques.

Dr. Rumshisky received her Ph.D. in Computer Science from Brandeis University in 2009. She received postdoctoral training at MIT CSAIL. She has received undergraduate training at Moscow State University.

Dr. Kate Saenko received a BSc in Computer Science from the University of British Columbia, Canada in 2000 and a PhD in Electrical Engineering and Computer Science from the Massachusetts Institute of Technology in 2009.

Between 2009 and 2012 she was a postdoctoral researcher appointed jointly at UC Berkeley and Harvard.

Kate's interests are in developing machine learning methods for computer vision applications, including object recognition, transfer learning and adaptation, color models and joint semantics of images and language. 

Mulhern200b.jpg arum200.jpg saenko200.jpg
(L-R) Profs. Mulhern, Rumshisky, and Saenko.

Five students from the Institute for Visualization and Perception Research (IVPR) at UMass Lowell were accepted into the Google Summer of Code program this summer.

Google Summer of Code (GSoC) is an international program that awards stipends to software developers to write code for open-source software projects. GSoC pairs students with mentors who are experienced in real-world software development. At the end of the summer, source code created during the program is released as open-source.

Each student worked to improve Weave, the free open-source data visualization and analysis platform that was developed by the IVPR and released in 2011:

  • Sanjay Anbalagan (doctoral student): Extending the Open-source Weave Analysis and Visualization Platform for the Biological Community. Sanjay designed a process that accesses multiple publicly available gene expression data sets, imports that data into Weave and uses Weave analysis features to examine, visualize and compare gene expression profiles.
  • Andrew Dufilie (doctoral student): Asynchronous Rendering to Support Large Data Sets in Weave. Andy improved Weave performance by developing a threading system for its single-threaded ActionScript code base. This means the interface remains highly responsive even when visualizing large data sets of 300,000 records or more.
  • John Fallon (senior): Collaboration in Visualization. John created, implemented and tested the first version of collaboration in the Weave environment, allowing multiple users to work together, simultaneously and remotely, when creating visualizations and performing data analysis in Weave.
  • Heather Granz (doctoral student): An Accessibility Module for Visualizations Using Weave, an Open- source Visualization Platform. Heather developed and tested a Weave-to-JAWS interface that provides descriptions of Weave visualizations in text format. This work is a first step in a larger, more ambitious project that will eventually allow Weave to generate natural language text descriptions of interactive visualizations that are compatible with the JAWS screen-reading system.
  • Sebastin Kolman (doctoral student): InfoMaps: A Tool for Personal Information Management and Analysis. Sebastin implemented InfoMaps, a visualization tool for personal information management, in the Weave environment and extended its support for document visualization and analysis including local file systems.
All five students felt they had benefited from the Google program.

According to senior John Fallon, “It was a positive experience -- getting to contribute to an open-source project, working with experienced programmers and having a professor as a mentor the whole way through”.

Doctoral student, Andy Dufilie, the Weave project engineer, noted, “The major architectural changes I made produced unexpected consequences, requiring much more work than originally planned. The takeaway is to always expect the unexpected when estimating development time.”

The Institute for Visualization and Perception Research at UMass Lowell is led by Prof. Georges Grinstein.

GSOC  IVPR students.jpg
(L-R) 2012 Google Summer of Code alumni Sanjay Anbalagan, Sebastin Kolman, Andy Dufilie, Heather Granz and John Fallon. Their work expanded and improved Weave, the open-source data visualization and analysis platform.
On September 6, 2012, Harshavardhan (Harsh) Achrekar, a computer science graduate student, under the guidance of Dr. Benyuan Liu, successfully defended his Ph.D. thesis titled “Online Social Network Flu Tracker – a Novel Sensory Approach to Predict Flu Trends.” He is currently employed with the Community Analytics division of eClinicalWorks®, a market leader in ambulatory clinical systems.

Achrekar’s PhD research involved online social network (OSN) analysis, with a focus on predicting flu trends and information extraction from messages posted on OSN's. He was utilizing information posted on online social networks such as Twitter and Facebook to help improve the prediction of influenza levels within US population and was tracking of its spread.

He spend three years developing and perfecting an in-house framework called the Social Network-Enabled Flu Trends (SNEFT). The software that uses continuous data-collection mechanism to monitor flu-related messages, extract relevant user demographic and location information, classify messages in real time, and predict the current influenza levels.

Starting 2009, Achrekar tapped into Twitter and Facebook and extracted tens of millions of influenza-related user posts till date, to provide an almost-instantaneous snapshot of current epidemic conditions and building comprehensive mathematical models that improves the estimate of nationwide flu activity.

Achrekar's approach can significantly enhance public health preparedness against influenza and other large-scale pandemics.

For this research, Achrekar was supported with a $200,000 grant from the National Institutes of Health under a Small Business Innovation Research Award.

His results have been presented in various scientific publications:

  • His paper “Twitter improves Seasonal Influenza Prediction" at the fifth annual International Conference on Health Informatics, Portugal, February 2012, received the Best Student Paper Award. This is a prestigious and competitive conference with a 9% full-paper acceptance ratio.
  • His paper titled “Predicting Flu Trends using Twitter Data” at the International Workshop on Cyber-Physical Networking Systems (CPNS) 2011, in conjunction with IEEE INFOCOM 2011, held in Shanghai, China, April 10–15, 2011, is considered to be a foundational research for flu tracking with OSN data and has received many citations.
  • The paper titled “A Spatio-Temporal Approach to the Discovery of Online Social Trends” at the fifth Annual International Conference on Combinatorial Optimization and Applications (COCOA), Zhangjiajie, China in August 2011 provides insights into using online social network data to discover trends in other domains. 
  • Also “Vision: Towards Real Time Epidemic Vigilance through Online Social Networks” was his first ACM Workshop paper at Mobile Cloud Computing & Services: Social Networks and Beyond (MCS), in conjunction with ACM MobiSys, San Francisco, California, June 2010, that explains the SNEFT architecture for flu tracking and pandemic outburst detection using online social network data.

Dr. Achrekar’s committee included Cindy Chen (Computer Science), Georges Grinstein (Computer Science), Yan Luo (Electrical and Computer Engineering), and Jie Wang (Computer Science).

Harshavardhan (Harsh) Achrekar at his doctoral defense on September 6, 2012.

About this Archive

This page is a archive of recent entries written by Martin, Fred in October 2012.

Martin, Fred: June 2012 is the previous archive.

Martin, Fred: December 2012 is the next archive.

Find recent content on the main index or look in the archives to find all content.

Subscribe to feed Subscribe to this blog's feed