ISIIS Technology / Analysis & Data Storage

To enhance ISIIS's sampling and data analysis capabilities in near real-time mode, a state-of-the-art image recognition software is being developped by Dr. Gavriil Tsechpenakis of the Center for Computational Science (CCS) University of Miami (www.ccs.miami.edu/~gavriil/)

The analysis is done using MatLab base code. The software is capable of detecting all organisms of interest automatically, directly from the raw data, while filtering out noise and out-of-focus instances. Each organisms is counted and classified in a user accessible image library output. The process allows for rapid analysis as this artificial intelligence software is able to automatically extracts and classifies specimens from the digital images.

When data is ported to the ship, a dual processor computer linked to a hard drive array is necessary to record data at up to 80MB/second. For a 6 hours survey, approximately 2TB of memory is required.