Recognizing chromatographic peaks with pattern recognition methods : Part 1. Development of a k-nearest-neighbour technique

Problems in automated peak recognition in chromatography are discussed. An algorithm based on the k-nearest neighbour technique is proposed. Recognition of a peak is done by comparing it with a predefined profile function (normally a Gaussian peak profile). The profile and a part of the chromatogram are both interpreted as points in a multi-dimensional pattern space. The distance between the two points gives the value of the peak recognition function. The effects of different properties of chromatographic peaks (i.e., peak width, peak height and noise) and of the profile parameter (i.e., dimension of the pattern space, shape and width of the function, and characteristics of the distance measure) are evaluated. The method has excellent properties for recognizing peaks with low signal/noise (S/N) ratios; an example with S/N = 1 is shown. Changing peak widths and drifting baselines have little effect on the recognition ability. Difficulties with changing peak heights can be compensated by range scaling. Problems occur when two peaks are not sufficiently separated.