[Colloquium] REMINDER: 12/4 TTIC Colloquium: Heather Zheng, University of Chicago

[Mary Marre via Colloquium]

When:     Monday, December 4th at 11:00 a.m.

Where:    TTIC, 6045 S. Kenwood Avenue, 5th Floor, Room 526

Who:       Heather Zheng, University of Chicago


Title:        Mobile Sensing at the Edge

Abstract:
Mobile networking systems are undergoing an exciting transformation, moving
from being the base of connectivity to become an integrated platform with a
wide variety of capabilities. From environmental sensing, activity
tracking, health monitoring, to autonomous device navigation, mobile
devices will offer rich functionalities well beyond the boundary of
traditional networking. As we further strengthen both radio technologies
and ML capabilities of mobile devices,  building powerful applications and
managing the resulting complex ecosystems is an exciting long-term research
challenge.

In this talk, I will present recent projects at SANDLAB at University of
Chicago. The first is a mobile imaging system reusing the 60GHz networking
radio, allowing mobile devices to locate and recognize nearby objects and
potentially the surrounding environments.  We discovered that at 60GHz,
conventional radar designs provide poor results that are highly sensitive
to device positioning errors and movement. We proposed and prototyped new
60GHz imaging algorithms using a single mobile device,  imaging an object
using just signal strength measurements recorded along the device’s moving
trajectory. Our current design provides position of nearby objects, and
their surface orientation, curvature, boundaries, and even their surface
material.  The second project is to design, implement and experiment with a
citywide outdoor object and event recognition system. Operating on the
array-of-thing platform (being deployed across the city of Chicago), our
system aims to detect key objects and major outdoor events in urban areas.
Our key challenge is each AoT node has limited computation and
communication power, while raw video/audio data cannot leave individual AoT
nodes for privacy. To address these challenges, we are developing resource
constrained learning framework and privacy-preserving distributed learning
mechanisms.   Finally, I will conclude by giving a general overview of the
research projects in our lab.

Host: Karen Livescu <klivescu at ttic.edu>


For more information on the colloquium series or to subscribe to the
mailing list, please see http://www.ttic.edu/colloquium.php




Mary C. Marre
Administrative Assistant
*Toyota Technological Institute*
*6045 S. Kenwood Avenue*
*Room 504*
*Chicago, IL  60637*
*p:(773) 834-1757*
*f: (773) 357-6970*
*mmarre at ttic.edu <mmarre at ttic.edu>*

On Mon, Nov 27, 2017 at 2:33 PM, Mary Marre <mmarre at ttic.edu> wrote:

> When:     Monday, December 4th at 11:00 a.m.
>
> Where:    TTIC, 6045 S. Kenwood Avenue, 5th Floor, Room 526
>
> Who:       Heather Zheng, University of Chicago
>
>
> Title:        Mobile Sensing at the Edge
>
> Abstract:
> Mobile networking systems are undergoing an exciting transformation,
> moving from being the base of connectivity to become an integrated platform
> with a wide variety of capabilities. From environmental sensing, activity
> tracking, health monitoring, to autonomous device navigation, mobile
> devices will offer rich functionalities well beyond the boundary of
> traditional networking. As we further strengthen both radio technologies
> and ML capabilities of mobile devices,  building powerful applications and
> managing the resulting complex ecosystems is an exciting long-term research
> challenge.
>
> In this talk, I will present recent projects at SANDLAB at University of
> Chicago. The first is a mobile imaging system reusing the 60GHz networking
> radio, allowing mobile devices to locate and recognize nearby objects and
> potentially the surrounding environments.  We discovered that at 60GHz,
> conventional radar designs provide poor results that are highly sensitive
> to device positioning errors and movement. We proposed and prototyped new
> 60GHz imaging algorithms using a single mobile device,  imaging an object
> using just signal strength measurements recorded along the device’s moving
> trajectory. Our current design provides position of nearby objects, and
> their surface orientation, curvature, boundaries, and even their surface
> material.  The second project is to design, implement and experiment with a
> citywide outdoor object and event recognition system. Operating on the
> array-of-thing platform (being deployed across the city of Chicago), our
> system aims to detect key objects and major outdoor events in urban areas.
> Our key challenge is each AoT node has limited computation and
> communication power, while raw video/audio data cannot leave individual AoT
> nodes for privacy. To address these challenges, we are developing resource
> constrained learning framework and privacy-preserving distributed learning
> mechanisms.   Finally, I will conclude by giving a general overview of the
> research projects in our lab.
>
> Host: Karen Livescu <klivescu at ttic.edu>
>
>
> For more information on the colloquium series or to subscribe to the
> mailing list, please see http://www.ttic.edu/colloquium.php
>
>
>
>
>
> Mary C. Marre
> Administrative Assistant
> *Toyota Technological Institute*
> *6045 S. Kenwood Avenue*
> *Room 504*
> *Chicago, IL  60637*
> *p:(773) 834-1757 <(773)%20834-1757>*
> *f: (773) 357-6970 <(773)%20357-6970>*
> *mmarre at ttic.edu <mmarre at ttic.edu>*
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20171203/683b9942/attachment.html>