Juan F. Ramirez Rochac @ UDC

Interdisciplinary

Created Fuzzy-classifiers for local Edge detection for Biometrics applications. The project team has explored the novel idea of using reference neighborhood window to adaptively calibrate the classifier parameters. Three variants of AFCAs, called, Kmeans-clustering AFCA, Entropy-based AFCA, and Statistical AFCA, were developed. Experiments were conducted both on synthetic images and on real fingerprint images to compare these AFCAs and Canny edge detection. The presented results show that Statistical AFCA is the best edge detection performer for latent fingerprints. This approach advances the field of biometrics personal identification and can be applied in law enforcement, national security, and other applications of information assurance and security. This study was developed at the Arctic center, and it was sponsored in part by the National Science Foundation (NSF).
Implemented a Water Flow Monitoring system using Wireless Sensors and a linear Kalman Filter. The project team has developed a lab scale integrated sensor-computer unit (emerging Small Programmable Object Technology, SPOT) and proposes to use this technology for real-time, continuous monitoring for waste water runoff. If successful, this project will produce a transformative solution to real-time and online monitoring of urban waste water runoff for planning and decision making in civil infrastructure, natural environment protection, and water pollution related emergency. This study was developed at the Informatics laboratory in conjunction with the Department of Civil and Mechanical Engineering, and it was sponsored in part by the National Science Foundation (NSF).

Spatio-temporal Databases

For storage, update, and retrieval of the GPS and other multimedia information of continuously moving/changing objects (e.g., cell phones), the project team has developed a transformative spatial-temporal data management and computation solution. The Geoboard project is committed to the development of a next-generation geo-tracking system. This system is mainly divided into two parts: client application and server application. The client application is a small program that runs on a mobile device. This mobile client continuously sends the device's GPS and other multimedia information, such as tagged image frames, to the server application.
Designed and developed a data warehouse information system to ease pattern recognition in the National Institute of Cancer of El Salvador using PostgreSQL & Java Script on a Red Hat server.

Created: August 24, 2010 | Maintained by Juan F. Ramirez Rochac | Last Update: August 23, 2013