A simple method for automated pretreatment of usable chromatographic profiles in pattern-recognition procedures: application to HPAEC–PAD chromatograms of honeys

Cordella, Christophe B. Y.; Milit&atild;o, Julio S. L. T.; Cabrol-Bass, Daniel
September 2003
Analytical & Bioanalytical Chemistry;Sep2003, Vol. 377 Issue 1, p214
Academic Journal
In this article a simple method for automated pretreatment of chromatograms is presented. The resulting data matrix can be used as input for multivariate statistical analysis. Application of this method to high-performance anion-exchange chromatography–pulsed amperometric detection (HPAEC–PAD) chromatograms of honeys before canonical discriminant analysis results in very good performance in the data reduction with regard to the preservation of the original information content of the data. This pretreatment of the chromatogram allows for the use of all the peaks corresponding to the sugars present in the sample. This results in a high-quality discrimination between honeys of various types. A versatile program has been developed to apply this method. This serves as a starting point for software suited for food characterization and adulteration detection by semi-automatic pattern recognition applied to chromatographic analysis.


Related Articles

  • Part 2: Multilayer Perceptron and Natural Gradient Learning. Hyeyoung Park // New Generation Computing;2006, Vol. 24 Issue 1, p79 

    Since the perceptron was developed for learning to classify input patterns, there have been plenty of studies on simple perceptrons and rnultilayer perceptrons. Despite wide and active studies in theory and applications, rnultilayer perceptrons still have many unsettled problems such as slow...

  • Vehicle Velocity Estimation Based on RSS Measurements. Theodore Stamoulakatos; Antonis Markopoulos; Miltiadis Anagnostou; Michalis Theologou // Wireless Personal Communications;Mar2007, Vol. 40 Issue 4, p523 

    Abstract??This paper presents a technique which is based on pattern recognition techniques, in order to estimate Mobile Terminal (MT) velocity. The proposed technique applies on received signal strength (RSS) measurements and more precisely on information extracted from Iub air interface, in...

  • A Problem of Pattern Recognition in Arrays of Interrelated Objects. Recognition Algorithm. Dvoenko, S.; Kopylov, A.; Mottl, V. // Automation & Remote Control;Dec2005, Vol. 66 Issue 12, p2019 

    The classical methods of pattern recognition theory presuppose the independence of elements of a recognizable set. Therefore, even in the case of interrelated objects, the decision on the class of each object is taken independent of the decision on the classes of other objects. At the same time,...

  • Combining bagging, boosting, rotation forest and random subspace methods. Kotsiantis, Sotiris // Artificial Intelligence Review;Mar2011, Vol. 35 Issue 3, p223 

    Bagging, boosting, rotation forest and random subspace methods are well known re-sampling ensemble methods that generate and combine a diversity of learners using the same learning algorithm for the base-classifiers. Boosting and rotation forest algorithms are considered stronger than bagging...

  • A Comparative Study of Optical Character Recognition for Tamil Script. Kannan, R. Jagadeesh; Prabhaskar, R. // European Journal of Scientific Research;Sep2009, Vol. 35 Issue 4, p570 

    Character Recognition (CR) has been extensively studied in the last half century and progressed to a level, sufficient to produce technology driven applications. Now, the rapidly growing computational power enables the implementation of the present CR methodologies and also creates an increasing...

  • Minimax Optimal Rates of Convergence for Multicategory Classifications. Di Rong Chen; You, Xu // Acta Mathematica Sinica;Aug2007, Vol. 23 Issue 8, p1419 

    In the problem of classification (or pattern recognition), given a set of n samples, we attempt to construct a classifier g n with a small misclassification error. It is important to study the convergence rates of the misclassification error as n tends to infinity. It is known that such a rate...

  • An integrated head pose and eye gaze tracking approach to non-intrusive visual attention measurement for wide FOV simulators. Cai, Hua; Lin, Yingzi // Virtual Reality;Mar2012, Vol. 16 Issue 1, p25 

    Eye gaze tracking is very useful for quantitatively measuring visual attention in virtual environments. However, most eye trackers have a limited tracking range, e.g., ±35° in the horizontal direction. This paper proposed a method to combine head pose tracking and eye gaze tracking...

  • Machine-Vision Needs Change with Color Imaging: Part II.  // Vision Systems Design;Jan2013, Vol. 18 Issue 1, p21 

    The article discusses the importance of understanding the characteristics of color spaces and selection of the one that yields the most effective results in machine-vision applications. The author explains that in making measurements of the visual differences between objects, the best color...

  • Glottal Excitation Feature based Gender Identification System using Ergodic HMM. Rao, R. Rajeshwara; Prasad, A. // International Journal of Computer Applications;Mar2011, Vol. 17, p31 

    In this paper, through different experimental studies it is demonstrated that the time varying glottal excitation component of speech can be exploited for text independent gender recognition studies. Linear prediction (LP) residual is used as a representation of excitation information in speech....


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics