日本データベース学会

dbjapanメーリングリストアーカイブ(2007年)

[dbjapan] CFP: Workshop on Massive Datasets


dbjapanの皆様

神戸大の寺田です.
お世話になっております.

名古屋大学の間瀬先生より,下記のワークショップの参加募集配布依頼をいただきま
したので,お送りさせていただきます.

大量データの取り扱いや可視化に関するワークショップで,
ポジションペーパを出しても良いし,ただの聴衆としての参加もよいようです.

よろしくお願いいたします.

-----

Call for Participation

First International Workshop on Massive Datasets
at the International Conference on Multimodal Interfaces
November 15, 2007
Nagoya, Japan

http://www.merl.com/wmd
http://www.acm.org/icmi/2007/
Registration open here: http://www.acm.org/icmi/2007/


Executive Summary

This workshop is intended to encourage work and discussion on the topic
of analysis, visualization, and manipulation of long-term data sets
recorded from large-scale sensor networks.  Specifically, this inaugural
workshop focuses on a dataset released by MERL comprised of one year of
data from 215 motion sensors that observe the public spaces of our 3000
square meter research facility.

The Workshop will follow a hybridized format.  There will be
presentations by researchers who have already performed analysis on the
dataset.  We will run a mini-tutorial session aimed at helping attendees
gain familiarity with the dataset.  Finally there will be an open
discussion about issues facing the community, including ways to improve
the quality and utility of this and similar datasets.

All are welcome.  Attendees wishing to have a more formal record of
their involvement may submit a two page position paper up until November
12th.  Please see the workshop web page for details: http://www.merl.com/wmd

We encourage those interested in these topics to also attend the ICMI
keynote address by Dr. Yuri A Ivanov "Interfacing Life: A year in the
life of a research lab" on November 12th at 10AM in the Nagoya Noh
Theater.  That talk will present the big ideas of the project, while
this workshop and tutorial will be focused on the details.


Vision

Are the tools we use to understand our data scalable to the tens of
millions of records, huge spans of time, minute details of behavior, and
large geographic extent that future sensor networks will generate? In
the future buildings will be studded with sensors. Every movement will
generate a few bits of data. Every fluctuation in temperature will be
recorded. Every deviation in lighting will be noticed. These large and
complex datasets will challenge the tools we use today.

Looking into the future of residential and office buildings Mitsubishi
Electric Research Labs (MERL) has been collecting motion sensor data
from a network of over 200 sensors for a year. The data is the residual
trace of year in the life of a research laboratory. It contains
interesting spatio-temporal structure ranging all the way from the
seconds of individuals walking down hallways, the minutes in lobbies
chatting with colleagues, the hours of dozens of people attending talks
and meetings, the days and weeks that drive the patterns of life, to the
months and seasons with their ebb and flow of visiting employees.

The dataset contains well over 30 million raw motion records, spanning a
calendar year and two floors of our research laboratory. As such it
presents a significant challenge for behavior analysis, search,
manipulation and visualization of the data. We have also prepared
accompanying analytics such as partial tracks and behavior detections,
as well as map data and anonymous calendar data marking the pattern of
meetings, vacations and holidays.

MERL has released this data set to the community. We invite you to
download the data and apply your analytic, visualization, and interface
tools.   The goal of the workshop is to understand the state of the art
in the context of the huge, detailed dataset of the near future.


Organizers

Christopher R. Wren
Yuri A. Ivanov
(Mitsubishi Electric Research Laboratories)


Program Committee

   * Kiyoharu Aizawa (University of Tokyo)
   * Aaron Bobick (Georgia Institute of Technology)
   * Trevor Darrell (Massachusetts Institute of Technology)
   * Irfan Essa (Georgia Institute of Technology)
   * Minkyong Kim (IBM Research)
   * David Minnen (Georgia Institute of Technology)
   * Vladimir Pavlovic (Rutgers University)
   * Thad Starner (Georgia Institute of Technology)
   * Kazuhiko Sumi (Mitsubishi Electric)
   * Andrew Wilson (Microsoft Research)

Position Papers:

   * 2 page position statement
   * future applications?
   * If you downloaded the dataset, what was difficult that you did not
     anticipate?
   * what do you see as the important problems?
   * ISBN and ACM Digital Library inclusion.


=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
寺田 努 (准教授) ◇ Terada Tsutomu (Associate Professor)
神戸大学大学院工学研究科電気電子工学専攻
〒657-8501 神戸市灘区六甲台町1-1               TEL/FAX まだ
Mail tsutomu [at] eedept.kobe-u.ac.jp              
URL  http://www-nishio.ise.eng.osaka-u.ac.jp/~tsutomu/index-jp.html
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=