BONAPARTE: victim identification
A disaster victim identification system based on Bayesian networks.
Bonaparte is software to facilitate the missing person screening and matching routines for victim identification based on DNA profiles and kinship analysis. In particular Bonaparte is designed to facilitate quick victim identification in case of mass fatalities, such as terrorist attacks, airline crashes and natural disasters.
BAYESIAN NETWORKS
Identification is achieved by using probabilistic methods to model Mendelian inheritance. In particular, Bayesian networks are very well suited to model the statistical relations of genetic material of relatives in a pedigree. They can directly be applied in kinship analysis with any type of pedigree of relatives of the missing persons. An additional advantage of a Bayesian network approach is that it makes the analysis tool more transparent and flexible, allowing to incorporate other factors that play a role - such as measurement error probability, missing data, statistics of more advanced genetic markers etc.
web browser
Bonaparte is based on client-server architecture. This means that the computational core—the part of Bonaparte that actually computes the probabilities—and the Bonaparte database run on a dedicated server and clients communicate with this server over a network. Clients use a standard web browser to access the server via a secure connection. A Java based client is currently in development.
database
Bonaparte's database is designed to support concurrent users. Furthermore, it has a "roll-back" capability--the database can be rewind to a time in the past. This feature enables the user to review a case using the same information that was available in the original situation.
outside the netherlands
The development of Bonaparte is done for and in collaboration with the Netherlands Forensic Institute (NFI). Commercial use of Bonaparte within the Netherlands is licensed exclusively to the Netherlands Forensic Institute. Therefore commercial licenses are only available for institutes and organizations that do not reside in The Netherlands.
BAYESIAN NETWORKS
Identification is achieved by using probabilistic methods to model Mendelian inheritance. In particular, Bayesian networks are very well suited to model the statistical relations of genetic material of relatives in a pedigree. They can directly be applied in kinship analysis with any type of pedigree of relatives of the missing persons. An additional advantage of a Bayesian network approach is that it makes the analysis tool more transparent and flexible, allowing to incorporate other factors that play a role - such as measurement error probability, missing data, statistics of more advanced genetic markers etc.
web browser
Bonaparte is based on client-server architecture. This means that the computational core—the part of Bonaparte that actually computes the probabilities—and the Bonaparte database run on a dedicated server and clients communicate with this server over a network. Clients use a standard web browser to access the server via a secure connection. A Java based client is currently in development.
database
Bonaparte's database is designed to support concurrent users. Furthermore, it has a "roll-back" capability--the database can be rewind to a time in the past. This feature enables the user to review a case using the same information that was available in the original situation.
outside the netherlands
The development of Bonaparte is done for and in collaboration with the Netherlands Forensic Institute (NFI). Commercial use of Bonaparte within the Netherlands is licensed exclusively to the Netherlands Forensic Institute. Therefore commercial licenses are only available for institutes and organizations that do not reside in The Netherlands.
our customer
More information
More about the Bonaparte DVI system, its Bayesian network model, advanced IT features and a live demo can be found at www.bonaparte-dvi.com
Publication
W. Wiegerinck e.a. Bayesian Networks for Expert Systems, Theory and Practical Applications. In: Interactive Collaborative Information Systems, series Studies in Computational Intelligence, R. Babuska, F.C.A. Groen, Editors, Springer, 2010. In press.
More information
More about the Bonaparte DVI system, its Bayesian network model, advanced IT features and a live demo can be found at www.bonaparte-dvi.com
Publication
W. Wiegerinck e.a. Bayesian Networks for Expert Systems, Theory and Practical Applications. In: Interactive Collaborative Information Systems, series Studies in Computational Intelligence, R. Babuska, F.C.A. Groen, Editors, Springer, 2010. In press.