| Abstract
| - Two different soft computing (SC) techniques (a competitive learning neural network and an integratedneural network−fuzzy logic−genetic algorithm approach) are employed in the analysis of a database subsetobtained from the Cambridge Structural Database. The chemical problem chosen for study is relevant to therelationship between various metric parameters in transition metal imido (LnMdNZ, Z = carbon-basedsubstituent) complexes and the chemical consequences of such relationships. The SC techniques confirmedand quantified the suspected relationship between the metal−nitrogen bond length and the metal−nitrogen−substituent bond angle for transition metal imidos: increased metal−nitrogen−carbon angles correlate withshortened metal−nitrogen distances. The mining effort also yielded an unexpected correlation between theNC distance and the MNC angleshorter NC correlate with larger MNC. A fuzzy inference system is usedto construct an MNred−NC−MNC hypersurface. This hypersurface suggests a complicated interdependenceamong NC, MNred, and the angle subtended by these two bonds. Also, major portions of the hypersurfaceare very flat, in regions where MNC is approaching linearity. The relationships are also seen to be influencedby whether the imido substituent is an alkyl or aryl group. Computationally, the present results are of particularinterest in two respects. First, SC classification was able to isolate an “outlier” cluster. Identification ofoutliers is important as they may correspond to unreported experimental errors in the database or novelchemical entities, both of which warrant further investigation. Second, the SC database mining not onlyconfirmed and quantified a suspected relationship (MNred versus MNC) within the data but also yielded atrend that was not suspected (NC versus MNC).
|
