DOAS 2006
Updated Thursday, February 2nd
On this site you'll will find the latest information on the course DOAS.
Ambient intelligence applications heavily rely on successfully identifying people in their home environment. Current applications use complex, expensive or intrusive sensors and methods like RFID tags, retina scans or human face identification In this paper we present the Person Identification SYStem (PISYS). In contrast with previous work, PISYS uses simple, non-intrusive sensors to reason about the presense of persons in particular rooms and calculate probability values with respect to their identities. As part of the project, a home environment simulator was implemented and used to generate train and test scripts. Using this data, we present how the PISYS system can successfully identify people in a range of situations, including multiple people in the same room.
Planning
Updated Tuesday, January 30th
This is the planning so far
Finish final report
Prepare for presentation
Program
Updated Wednesday, January 30th
Final version of the Simulator program (requires Java to run) is available here
You only have to start MySQL server, the program already includes a JDBC driver to MySQL.
Java Runtime Environment is also needed to run the simulator.
The simulator is used to create data, that can be used to train the reasoning engine.
The simulator integrated with the Max-Plus Reasoning Engine can be downloaded here.
At the moment, this version only works with username 'root' and empty password in the MySQL server. The popup that appears
if the username and/or password are not correct, is only for the simulator. The Reasoning part doesn't use this information yet.
There are two screens where one screen is the simulator (see screenshot below) and the other represents the information
that the max-plus algorithm calculates. The rooms are shown in black or gray. If the room is black, this means that
someone is in the room. The gray color shows that the room is empty. The sensors are represented in blue or red. Red is a
sensor that is activated and a blue sensor is not active. The names are shown in yellow. That are the persons that the reason
engine thinks are in the rooms. Choose a person from the simulator and move around in the house and see if the Max-Plus
algorithm reasons good enough. Activating a sensor in the simulator has no influence on the outcome, because it is not
implemented. Only the cum. weight and height sensor are used.
Here is a screenshot of the PISYS simulator program:
