Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
Hi-index | 0.00 |
In Comprehensive two-dimensional gas chromatography time-of-flight mass spectrometry (GC×GC/TOF-MS), two dimensional retention index(RI) can be used to aid identification for decrease false-positive rate. However, the amount of collected RI data in some column is obviously less than some popular column. Quantitative structure-retention relationship (QSRR) model is a effective method to eastimate the RI value, but the accuracy still need to improve. A RI transoformation method based on optimal mocular descriptors throught particle swarm optimization is proposed in this paper, 107 molecules with two column experimental RI (DB-17,DB-5) was used to create a dataset. The predictive performance of two methods (PSO-MLR, PSO-Transformation model) was investigated. Ten in-silicon experiments were conducted on each method. Contrasing tranditional QSRR model (PSO-MLR), the proposed method achieved more accuracy predictive results.