Pattern recognition categories

Safety evaluation of oil depot belongs to pattern recognition category, and artificial neural network in pattern recognition has been widely used. Artificial neural network used in safety evaluation is feasible. 

The classical variants of both the pattern recognition categories - supervised and unsupervised learning - will assign the data unambiguously to one class or another to its full degree (see Chemometrics Multivariate View on Chemical Problems). Objects lying at class boundaries are less typical members of each class than those near to the cluster center. These objects may be outliers or they may be hybrids,... 

Often the goal of a data analysis problem requites more than simple classification of samples into known categories. It is very often desirable to have a means to detect oudiers and to derive an estimate of the level of confidence in a classification result. These ate things that go beyond sttictiy nonparametric pattern recognition procedures. Also of interest is the abiUty to empirically model each category so that it is possible to make quantitative correlations and predictions with external continuous properties. As a result, a modeling and classification method called SIMCA has been developed to provide these capabihties (29—31). 

The multivariate tools typically used for the NIR-CI analysis of pharmaceutical products fall into two main categories pattern recognition techniques and factor-based chemometric analysis methods. Pattern recognition algorithms such as spectral correlation or Euclidian distance calculations basically determine the similarity of a sample spectrum to a reference spectrum. These tools are especially useful for images where the individual pixels yield relatively unmixed spectra. These techniques can be used to quickly define spatial distributions of known materials based on external reference spectra. Alternatively, they can be used with internal references, to locate and classify regions with similar spectral response. 

The concept of transferability and a detailed understanding of these amide modes provides the basis for quantitative estimation of secondary structure for unknown proteins and polypeptides. The quantitative methods currently used to analyze vibrational spectra of proteins can be classified into two categories (1) methods based on decomposition of band contours into underlying components characterized by distinct frequencies, and (2) methods based on principles of pattern recognition. 

As part of their efforts to identify clinically useful antitumor compounds, the U. S. National Cancer Institute (NCI) in 1989 established a panel of 60 human tumor cell lines representing seven major categories of human cancer. They have foimd that the activity profile for various compounds is sufficiently characteristic to be employed as a means of identification, using specialized pattern-recognition algorithms. 

The first analytical application of a pattern recognition method dates back to 1969 when classification of mass spectra with respect to certain molecular mass classes was tried with the LLM. The basis for classification with the LLM is a discriminant function that divides the -dimensional space into category regions that can be further used to predict the category membership of a test sample. 

ADAPT has a variety of pattern recognition and statistical methods available for use. The object of the analysis phase is to find discriminants that separate subsets of the data into the proper categories. That is, one is trying to find mathematical models that will classify compounds as belonging to the active or inactive subset based on the molecular structure descriptors available. This phase of SAR studies Is guided by the user in a highly interactive manner in order to search through the available descriptors for the best set. 

A set of indirect measurements which describe one object is called a pattern. The determination of the obscure property is often a recognition of the class (category) to which a pattern belongs. Classification of patterns is a fundamental process in many parts of science and human being and therefore mathematical methods of pattern recognition find wide applications in very different fields. 

There are so many individual reactions in chemistry that memorizing them aU is a futile task. It is far more fruitful to try to use pattern recognition to determine the general category of a reaction, such as metathesis or oxidation-reduction. Thus, when you are faced with the challenge of predicting the outcome of a chemical reaction, ask yourself the following pertinent questions ... 

Pierce CY, Barr JR, Woolfitt AR, Moura H, Shaw El, Thompson HA, Massurtg RF, Fernandez FM. Strain and phase identification of the U.S. category B agent Coxiella burnetii by matrix assisted laser desorption/ionization time-of-flight mass spectrometry and multivariate pattern recognition. Anal Chim Acta. 2007 583 23-31. 

---