IEEE researchers propose new cluster cloud framework for mobile biometrics
Researchers from the The Institute of Electrical and Electronics Engineers (IEEE) created a high-performance cluster cloud framework to better manage the massive amounts of data related to mobile biometric authentication, according to a report by The Stack.
The team conducted large-scale experimental tests (PDF) in which it used a cloud-based biometric authentication framework, or BAMCloud, to achieve a network speed performance that was more than eight times greater than alternate methods.
Two other benefits of BAMCloud include achieving a performance success rate of 96.23 percent as well as a lower overall cost to install and run the framework than alternate biometric authentication methods.
The increasing adoption of biometric identity verification is driving demand for mobile biometric authorization, and managing the attendant data requirements has led to the need for a cloud framework to structure biometric authentication tasks in a scalable, accurate and efficient system, the researchers said.
The BAMCloud framework is separated into several different phases, beginning with data capture conducted on mobile devices and storage of data in the HDFS cloud.
The data is then pre-processed and trained in a neural network environment, before the pre-processed data is stored on the HDFS cloud, where it can be queried.
Queries, which are conducted by Hive data warehousing software on the HDFS system, provide biometric authentication capabilities for users to access their data.
The researchers said the BAMCloud framework uses parallel algorithms for training and processing, taking advantage of the ‘infinite storage and computing capacity of the cloud’ to effectively manage infinitely large volumes of data.
The test results showed that the algorithm used for data training achieved speeds of seven times the average existing method, while the algorithm used for processing was 10 times faster.
BAMCloud’s dual-algorithm approach delivered 8.5 times faster results than comparable techniques currently in use.
Based on initial studies, researchers found that BAMCloud provides a solution for mobile biometric authentication that is scalable, cost efficient, and accurate.
The use of the new framework also allows data to be offset to a third-party cloud for storage.