PARALLEL ADAPTIVE SIMULATED ANNEALING FOR FUNCTIONAL MRI CLUSTER ANALYSIS ON A PC-CLUSTER SYSTEM

摘要

Simulated annealing (SA) is one of the most efficient heuristic algorithms for complex nonlinear optimization problems. However, it suffers from the large amount of computing time necessary to obtain a near-optimal solution. To overcome this problem, a parallel version of the algorithm is worthy of evaluation. This report presents a parallel adaptive SA (PASA) to locate the activation area of functional magnetic resonance images (fMRIs). Performance of this approach is evaluated by the receiver-operating characteristic (ROC) and Jaccard similarity analysis. Experimental results show that PASA outperforms other approaches and can also efficiently extract activities with different signal-change levels and activation-area sizes.