Cooperative Feature Level Data Fusion for Authentication Using Neural Networks

In traditional research, data fusion is referred to as multisensor data fusion. The theory is that data from multiple sources can be combined to provide more accurate, reliable and meaningful information than that provided by a single data source. Applications in this field of study were originally in the military domain; more recently, investigations for its application in various civilian domains (eg: computer security) have been undertaken. Multi-sensor data fusion as applied to biometric authentication is termed multi-modal biometrics. The objective of this study was to apply feature level fusion of fingerprint feature and keystroke dynamics data for authentication purposes, utilizing Artificial Neural Networks (ANNs) as a classifier. Data fusion was performed adopting the cooperative paradigm, a less researched approach. This approach necessitates feature subset selection to utilize the most discriminatory data from each source. Experimental results returned a false acceptance rate (FAR) of 0.0 and a worst case false rejection rate (FRR) of 0.0006, which were comparable to-and in some cases, slightly better than-other research using the cooperative paradigm.