OVERVIEW
Phase 1
The collection of smart phones carried by people can be used for large scale sensing of the physical world by leveraging the cameras, microphones, GPSs, accelerometers, and other sensors on the phones. In order to verify that smartphone sensing is scalable, reliable, and cost-effective, we built and deployed McSense platform. For campus students to participate in the research study, McSense app is provided in Android market
(download).
Phase 2
Serious games can be applied to solve interesting computer science problems. The purpose of this research is to understand the player's involvement, behavioral patterns and strategies while playing the location-based serious game. In order to verify that the serious games are scalable, reliable, and cost-effective to solve interesting problems, we built and deployed mobile game in Android platform. For campus students to participate in the research study, game is provided in Android market.
(download).
RESEARCH DIRECTIONS
Phase 1 - Crowdsensing using the micro-payments
The main goal of this research is to set the course for mass adoption and automation of mobile people-centric sensing. We believe that mobile crowd sensing (i.e., crowd-sourced mobile sensing) with micro-payments
represents the right approach to achieve this goal, but are aware that many challenges have to be overcome to
make the vision reality. We plan to systematically explore the benefits and challenges of this people-centric
sensing paradigm.
Sensor Data Validation
Ranging from manual photo tasks to automated
sensing tasks for activity monitoring, any task can be crowd
sourced to smart phones to sense data from different locations at
reduced cost. However, the sensed data submitted by participants
is not always reliable as they can submit false data to earn money
without executing the actual task. Therefore, it is important
to validate the sensed data. Validating the context of every
sensed data point of each participant is not a scalable solution.
One alternative is to first validate the location associated with
the sensed data points in order to achieve a certain degree of
reliability about the sensed data. However, location validation
without support from the wireless carriers is difficult.
To address this problem, we propose ILR, a scheme in which
we Improve the Location Reliability of mobile crowd sensed data
with minimal human efforts.
Scheduling of Crowd Sensing Tasks
The mobile sensing infrastructure is shared among all applications
in order to enable the largest number of users possible to participate in providing sensing data.
Scheduling should maximize the number of task completions, find a good balance between real-time and
long-term tasks, and maintain monetary fairness for both clients and providers. Additionally, it has to provide
a fault-tolerance mechanism for incomplete tasks.
Our goal is to create a flexible scheduling mechanism that allows us to experiment with different scheduling
policies in order to study the effect of budget allocation and task priority on task completion and
quality of data received. The scheduler will also be responsible for re-starting incomplete tasks.
Crowd Sensing in Smart Cities
McSense ParticipAct: This project is aimed at exploiring how and to what extent the power of mobile crowd sensing can be employed in smart cities. ParticipAct is a collaborative research with University of Bologna and please refer to ParticipAct for further details on this research direction.
Phase 2 - Mobile crowdsensing game
The main goals of the crowdsensing game user study are 1) to determine
whether the mobile users are interested in playing the mobile
crowdsensing games and 2) to compare the area coverage
efficiency in mobile crowdsensing games vs crowdsensing
using the micro-payments.
The WiFi area coverage maps for the McSense user study and the Alien vs. Mobile User game study in first 2-week period can be viewed from below links.
McSense WiFi Map
Game WiFi Map
The overall WiFi area coverage map for the McSense user study can be viewed from below link.
Overall McSense WiFi Map
The overall WiFi area coverage maps for the Alien vs. Mobile User game study can be viewed from below link.
Overall Game WiFi Map
PUBLICATIONS
Fostering ParticipAction in Smart Cities: A Geo-Social CrowdSensing Platform
PDF
Giuseppe Cardone, Luca Foschini, Cristian Borcea, Paolo Bellavista, Antonio Corradi, Manoop Talasila, Reza Curtmola
To appear in IEEE Communications Magazine, Special Issue on Smart Cities, June 2013
FACULTY (Phase 1 & 2)
Cristian Borcea
Associate Professor
Department of Computer Science
New Jersey Institute of Technology
Reza Curtmola
Assistant Professor
Department of Computer Science
New Jersey Institute of Technology
Ph.D. STUDENT (Phase 1 & 2)
Manoop Talasila
Ph.D. Candidate
Department of Computer Science
New Jersey Institute of Technology
VISITING STUDENT (Phase 1)
Claudio Pellizzari
Visiting MS Student
University of Bologna
COLLABORATORS (Phase 1)
Faculty:
Antonio Corradi (Full Professor at University of Bologna)
Paolo Bellavista (Associate Professor at University of Bologna)
Luca Foschini (Assistant Professor at University of Bologna)
Ph.D. student:
Giuseppe Cardone (University of Bologna)
|
