Intelligent Algorithm Based Fingerprint-Spectrum-Similitude-Estimation Supported By Optimized Grid

Fingerprint-Spectrum (FS) -Similitude (FSS) -Estimation (FSSA) is a key stage of medicine services and manages, which decides the truth, reliability, accuracy, safety, and availability of a medicine product. During developing this method people have meat problems such as too large data-volume, 2-dimensional (x- and y-axis) -float, complicated disturbance, and dependence on human-intervening, facing the Chinese medicine products[1][11][12] with complicated compositions from different natural arias. The currently used methods for FSSA mainly consists in the multi-element-analysis based on statistics, such as classification partial-LS-regression, and main-frequency-analysis, which need to cut down the dimensions of the signals, thus much information must be lost, and the membership function is very difficult to be set up. Based on the consideration mentioned above, a full computer-execution-process of FSSA including a specially composed method consists in a combination of Genetic-algorithm (GA) with exchanging code and a fuzzy-reformed BP-neural-network[2] [3] [4] [5], supported by Grid-computing system which is optimally equipped by work-flow-engine (WEEP)[6] and a multi-functional intelligent-algorithm-base, suits to distributed algorithm, shortly called as FCMQEG, is developed by the cooperation of CEFSP 200805# (Chinese Education Foundation Science Project, Number 5 ) and CAD-grid 2# (China-Austria-Grid- Computing-Cooperation-Project, Number 2)[7], and proposed in this paper. This proposed method solves the problem mentioned above in the comprehensives, full-automatic, intelligent, fuzzy, and non-linear aspects, thus, more accurate, independent, and stable similitude/quality estimation can be realized and applied into the field such as medicine/industry-diagnosis, biological-information- analysis, case-analysis, and so on.