5/18-519 CITI Adv.Board Meeting template

1
Mission-oriented Project
A Platform for Location Aware Service with Human
Computation, PLASH
Ling-Jyh Chen, Meng Chang Chen, Sheng-Wei Chen,
Jan-Ming Ho, Wang-Chien Lee, Jane Liu, De-Nian
Yang
Presenter Meng Chang Chen

2
Intelligent Ubiquitous Computing Center
Technical DevelopmentMobile Networking
CommunicationMultimedia Content
Management Virtual infrastructure for interactive
cloud app.
Platforms PLASH
3
History of PLASH

• Kicked off in August 2009
• Supported by NSC NCP office
• Also supported by CITI IIS
• A 3-year project
• Personnel
• Ling-Jyh Chen, Meng Chang Chen, Sheng-Wei Chen,
  Jan-Ming Ho, Wang-Chien Lee, Jane Liu, De-Nian
  Yang
• 10 -12 Research Assistants

4
Goals and Deliveries of PLASH

• To provide a platform to allow voluntary users
  via human computation games to contribute their
  location-based observations/efforts so as to
  facilitate some difficult location aware tasks.
• (Difficult location aware tasks) City profiling
  (surface traffic estimation, telecommunication
  network performance monitoring, city trend
  analysis) trip planning, spot locating, etc.
• To explore novel technologies to support the
  location aware platform and applications.
• Massive data mining, location-based query,
  image-assisting positioning, indoor
  positioning/tomography

5
Goals of PLASH (contd.)

• To design a layered architecture to allow
  application builders to conveniently create their
  systems.
• To provide a location-based dataset benchmark for
  various research
• To build and transfer prototype to potential
  receivers.
• To promote the use of wireless communications.

6
ltVID, GPS Position, Time, other infogt
Scenario 1 traffic estimation and dynamic routing
Volunteers send information periodically
ltVID, GPS Position, Time, other infogt
7
1. System derives traffic conditions.
Jammed Area
Jammed Area
Green Area
Green Area
Green Area
Green Area
Jammed Area
4. Dynamic reroute.
3. Now it is jammed!
2. System derives a route.
Original navigation
Re-routed navigation
8
Scenario 2 available parking locating V2V
ltParking Availablegt
ltLooking for Park spacegt
9
Scenario 2 available parking locating V2I2V
3G, WiMax
Mobile AP (taxi, bus)
802.11g Users (source)
Destination
Mobile Access Cluster
10
PLASH Architecture
Applications
Map N Track
Itinerary recommendation
Friend compass
Massive data mining
Technologies
Fundamental services
Literacy Enabling Service
Service layer
Data layer
Data representation, storage and access
Geo-location query
City Profiling
V2I, V2V
Localized data assimilation
Communication layer
11
Related Works (1) Handout
Project PLASH Reality Mining GeoLife
Who CITI, AS MIT Media Lab MS Research Asia
PI(s) Meng Chang Chen, et al. Sandy Pentland Xing Xie and Yu Zheng
Data Collection Mobile Phone w/ GPS and 3G Mobile phone w/ Bluetooth Mobile phone w/ GPS /3G
Data Source Human Computation and Volunteering Contribution with Location Aware Applications Monitor 100 mobile phones over 9 months Upload by users
Data Process Real-time / Post Processing Post Processing Real-time Processing
Data Representation Mobile Phone/Web None Mobile Phone/Web
Objective Build a platform for Location Aware Service with layered architecture. Provide a standard AIP for other application builder. Create City Profiling for traffic estimation, network performance monitoring, city trend analysis, etc. Support location award applications with novel technologies e.g., massive data mining, image-assisting positioning. Provide a location-based dataset benchmark for various research. Mining human relationships and behavior Social Networking Service
12
Related Works (2) - Handout
Project PLASH ShanghaiGrid CarTel
Who CITI, AS Science Technology Department of Shanghai MIT CSAIL
PI(s) Meng Chang Chen, et al. Minglu Li and Lionel M. Ni H. Balakrishnan, et al.
Data Collection Mobile Phone w/ GPS and 3G Commercial GPS receivers/ GPRS Sensors on Vehicles / WiFi
Data Source Human Computation and Volunteering Contribution with Location Aware Applications Collected from 6,850 taxies and 3,620 buses Collected from sensors on 27 vehicles
Data Process Real-time / Post Processing Real-Time / Post Processing Prost Processing
Data Representation Mobile Phone/Web Traffic Contral Center None
Objective Build a platform for Location Aware Service with layered architecture. Provide a standard AIP for other application builder. Create City Profiling for traffic estimation, network performance monitoring, city trend analysis, etc. Support location award applications with novel technologies e.g., massive data mining, image-assisting positioning. Provide a location-based dataset benchmark for various research. Provide intelligent transportation services to improve traffic condition Mobile Sensor Networks
13
Related Works (3?) - Handout
Project PLASH CarTel Multmodal Daily Life Patterns
Who CITI, AS MIT CSAIL EPFL, Switzerland
PI(s) Meng Chang Chen, et al. H. Balakrishnan, et al. K. Farrahi and D. Gatica-Perez
Data Collection Mobile Phone w/ GPS and 3G Sensors on Vehicles / WiFi Mobile Phone
Data Source Human Computation and Volunteering Contribution with Location Aware Applications Collected from sensors on 27 vehicles Monitor 97 users over 10 months
Data Process Real-time / Post Processing Prost Processing Post Processing
Data Representation Mobile Phone/Web None None
Objective Build a platform for Location Aware Service with layered architecture. Provide a standard AIP for other application builder. Create City Profiling for traffic estimation, network performance monitoring, city trend analysis, etc. Support location award applications with novel technologies e.g., massive data mining, image-assisting positioning. Provide a location-based dataset benchmark for various research. Mobile Sensor Networks Daily Life Patterns
14
SWOT Analysis
Helpful to achieving the objective Harmful to achieving the objective
Internal Origin (Attributes of the Organization) Strong team of various background Innovative system design using human computation Lack of experienced programmers Difficult to recruit users
External Origin (Attributes of the Environment) Location aware applications bring opportunities and challenges for technologies development and research. Strong competitors Throat chokehold by Google map carriers
15
Progress of 1st Year

• Literacy Enabling Web Service for Location-Aware
  Systems
• Goal to assist identifying location by using
  image
• Geo-location Query Service
• Goal to provide on-line geo-location query
  service
• Localized Data Dissemination in V2V networks
• to develop a localized data dissemination scheme
  via exploiting the intermittent connectivity of
  vehicle networks.
• Location-related Applications
• Map NTrack Friends let your friend know where
  your travel route
• Itinerary recommendation provide personalized
  route
• Friend compass indicate where a friend is

16
Future Work

• Deploy and operate the following applications
• Track-a-friend let your friend know where your
  travel route
• Travel route recommendation provide personalized
  route
• Friend compass indicate where a friend is
• TAF (TO and FRO)
• Innovative enabling technologies and applications
• Location-aware user experience summarization
  using comic Maps
• Road anomaly detection using smart phones
• Moving object clustering
• City Profiling
• Understanding the service performance of carriers
• Surface traffic estimation
• Allow volunteers to build their application by
  using provided APIs on PLASH. Could be SaaS or
  PaaS.

17
PLASH Future Architecture
Matured application logic becomes a fundamental
service
APP 1
APP 2
APP n
Fundamental services
Service layer
Data representation, storage and access
Data layer
Communication layer
V2I, V2V
18
PLASH Future Architecture
Volunteer can use APIs to build and upload new
applications
External Application Server

• Authentication (login/logout)
• Friend relation
• Store location data
• Query location data
• Query Point of Interest
• ..
• ..
• ..
• ..
• ..

19
PLASH Future Architecture Example
Volunteer builds an e-coupon service
Coupons On the Go
Coupon Service
Coupon DB
Standard APIs
PLASH Platform
Let me know if my user is within 100 meters nd
towards me.
Geo-Range query
20
PLASH Future Architecture Example
Send the user an e-coupon
Coupons On the Go
Coupon Service
Coupon DB
Update location data
Standard APIs
PLASH Platform
Geo-Range query
Find a user satisfying the range query
21
PLASH Future Architecture
Coupon Service
APP 1
APP 2
APP n
Real-Time Traffic
Hopefully many volunteer services built on PLASH
Standard APIs
Route Suggestion
PLASH Platform
Other Location-Based Services
22
Potential PLASH Receivers

• Literacy Enabling Web Service and Comic
  Summarization
• Location-based service providers
• Location-based Human Computation Games
• Phone manufacturers, telecom carriers
• City Profiling
• Traffic authority, telecom carriers, map service
  providers
• V2V related technologies
• ITS-related industry
• PLASH platform
• Carriers