Simplex pattern recognition applied to carbon-13 nuclear magnetic resonance spectrometry

Classification of binary carbon-13 nuclear magnetic resonance spectra

“…In previous papers, investigations of a number of heuristic pattern recognition strategies for the computer-assisted interpretation of nuclear magnetic resonance spectra were reported (1)(2)(3)(4)(5). The impetus for this work was our belief that the sensitivity of I3C chemical shifts to structure variation and the widespread availability of instrumentation for routine natural abundance 13C spectral measurements made this structure elucidation technique an imperative target of pattern recognition research.…”

“…Pattern classification using simplex pattern recognition (5,10) with initialization conditions determined by a preliminary linear learning machine analysis ( I , 5 ) was carried out using between 290 and 300 member training sets composed of equal numbers of class and non-class spectra. For simplex computations, the Fisher ratio feature selection method was used (5), selecting those features possessing the 128 largest Fisher ratios foT each category. Alternately, features visually selected from histograms (vide infra) were used.…”

“…Previously, a simplex optimization training procedure (10) was used to develop classifiers and resultant prediction performance was compared with that found for linear learning machine classifiers. As a result of examining close to 2000 unknown spectra for prediction of three common structural properties, we concluded that the simplex method, when used with binary coded data, showed promise as a superior route to the requisite high-reliability classifiers desirable for an on-line interpretation system (5). Subsequently, a report of pattern recognition analysis of 13C nuclear magnetic resonance spectra of a set of 43 norbornanes and another set of 12 polychlorinated diphenyl ethers has appeared (11).…”

“…Indeed, the computational methods employed here and previously have the potential for highlighting unrecognized patterns in the data (hence, pattern recognition) and directing the investigator's attention toward relationships which may enhance theoretical understanding. Our most ambitious research efforts involved the use of a set of 1767 spectra which comprised the largest such data set yet to be used as a test of pattern recognition interpretation of carbon NMR data (5).…”

“…In this paper, results made possible by the use of a new and larger carbon-13 NMR data base containing close to four thousand 13C NMR spectra are reported. Two similarity measures, the maximum likelihood (7,8) and a Bayes discriminant procedure (9), are compared in their performance with that of weight vectors derived using the simplex method (5,10) for the detection of presence or absence of 24 structural features.…”