Analytical chemistry of the recent years is strongly influenced by automation. Data acquisition from analytica~ instruments - and some times also controlling of instruments - by a computer are principally solved since many years. Availability of microcomputers made these tasks also feasible from the economic point of view. Besides these basic applications of computers in chemical measurements scientists developed computer programs for solving more sophisticated problems for which some kind of "intelligence" is usually supposed to be necessary. Harm less numerical experiments on this topic led to passionate discussions about the theme "which jobs cannot be done by a computer but only by human brain ?~. If this question is useful at all it should not be ans wered a priori. Application of computers in chemistry is a matter of utility, sometimes it is a social problem, but it is never a question of piety for the human brain. Automated instruments and the necessity to work on complex pro blems enhanced the development of automatic methods for the reduction and interpretation of large data sets. Numerous methods from mathematics, statistics, information theory, and computer science have been exten sively investigated for the elucidation of chemical information; a new discipline "chemometrics" has been established. Three different approaches have been used for computer-assisted interpretations of chemical data. 1. Heuristic methods try to formu late computer programs working in a similar way as a chemist would solve the problem. 2.

Machine Learning and Pattern Recognition Methods in Chemistry from Multivariate and Data Driven Modeling outlines key knowledge in this area, combining critical introductory approaches with the latest advanced techniques. Beginning with an introduction of univariate and multivariate statistical analysis, the book then explores multivariate calibration and validation methods. Soft modeling in chemical data analysis, hyperspectral data analysis, and autoencoder applications in analytical chemistry are then discussed, providing useful examples of the techniques in chemistry applications. Drawing on the knowledge of a global team of researchers, this book will be a helpful guide for chemists interested in developing their skills in multivariate data and error analysis. - Provides an introductory overview of statistical methods for the analysis and interpretation of chemical data - Discusses the use of machine learning for recognizing patterns in multidimensional chemical data - Identifies common sources of multivariate errors

This chapter describes the basic theory about classification, starting from a general description of the different approaches to classification and then illustrating in detail the principal methods which are used in the framework of assessment of food quality. Examples of application of the methods to different data sets are also provided.

The issues related to food science and authentication are of particular importance for researchers, consumers and regulatory entities. The need to guarantee quality foodstuff – where the word "quality" encompasses many different meanings, including e.g. nutritional value, safety of use, absence of alteration and adulterations, genuineness, typicalness, etc. – has led researchers to look for increasingly effective tools to investigate and deal with food chemistry problems. As even the simplest food is a complex matrix, the way to investigate its chemistry cannot be other than multivariate. Therefore, chemometrics is a necessary and powerful tool for the field of food analysis and control. For food science in general and food analysis and control in particular, there are several problems for which chemometrics are of utmost importance. Traceability, i.e. the possibility of verifying the animal/botanical, geographical and/or productive origin of a foodstuff, is, for instance, one area where the use of chemometric techniques is not only recommended but essential: indeed, at present no specific chemical and/or physico-chemical markers have been identified that can be univocally linked to the origin of a foodstuff and the only way of obtaining reliable traceability is by means of multivariate classification applied to experimental fingerprinting results. Another area where chemometrics is of particular importance is in building the bridge between consumer preferences, sensory attributes and molecular profiling of food: by identifying latent structures among the data tables, bilinear modeling techniques (such as PCA, MCR, PLS and its various evolutions) can provide an interpretable and reliable connection among these domains. Other problems include process control and monitoring, the possibility of using RGB or hyperspectral imaging techniques to nondestructively check food quality, calibration of multidimensional or hyphenated instruments etc.

This book is a systematic presentation of the methods that have been developed for the interpretation of molecular modeling to the design of new chemicals. The main feature of the compilation is the co-ordination of the various scientific disciplines required for the generation of new compounds. The five chapters deal with such areas as structure and properties of organic compounds, relationships between structure and properties, and models for structure generation. The subject is covered in sufficient depth to provide readers with the necessary background to understand the modeling techniques. The book will be of value to chemists in industries involved in the manufacture of organic chemicals such as solvents refrigerants, blood substitutes, etc. It also serves as a reference work for researchers, academics, consultants, and students interested in molecular design.

This book, Correlation Analysis in Chemistry: Recent Advances, is a sequel to our Advances in Linear Free Energy Relationships. t The change in the title is designed to reflect more accurately the nature of the field and the contents of the volume. The term LFER is still widely used, but it is often applied rather loosely to correlation equations that are not LFER in the restricted sense of a relationship involving logarithms of rate or equili brium constants on each side of the equation. The term "correlation analysis" seems to us more appropriate for the whole subject. The use of this term has compelled us also to introduce "chemistry" into the title; we have preferred not to prefix this with "organic" on the grounds that several areas of interest are not "organic chemistry" as usually understood, al though, of course, traditional applications of the basic relationships asso ciated with the names of Hammett and of Taft continue to be of interest. In the first volume we sought through our authors to provide a series of general articles covering the various aspects of the field as they seemed to us. Since the book was the first international research monograph in its field, each chapter, while giving prominence to recent developments, did not neglect earlier work, so that each article presented a comprehensive account of its own area.

Cheminformatics has emerged as an applied branch of Chemistry that involves multidisciplinary knowledge, connecting related fields such as chemistry, computer science, biology, pharmacology, physics, and mathematical statistics.The book is organized in two sections, including multiple aspects related to advances in the development of informatic tools and their specific use in compound structure databases with various applications in life sciences, mainly in medicinal chemistry, for identification and development of new therapeutically active molecules. The book covers aspects related to genomic analysis, semantic similarity, chemometrics, pattern recognition techniques, chemical reactivity prediction, drug-likeness assessment, bioavailability, biological target recognition, machine-based drug discovery and design. Results from various computational tools and methods are discussed in the context of new compound design and development, sharing promising opportunities, and perspectives.

In recent years, a new method of data processing using the support vector machine (SVM) has been introduced to the field of chemistry. Compared with other methods of data processing, the SVM has the advantage of good prediction reliability. It is especially suitable for small sample sizes, such as in chemical research on QSAR/QSPR work, materials and experimental design, phase diagram prediction, etc. The SVM is fast becoming a useful tool for chemists. This book provides a systematic approach to the principles and algorithms of the SVM, and looks at its application in many branches of chemistry.

J. W. Einax, H. W. Zwanziger S. Gei Chemometrics in Environmental Analysis Make the most of your data! This new title will serve both as an introduction and as a practical guide to those techniques of chemometrics which are applicable to environmental analysis. By describing the optimum methods of data analysis it will help all chemists in this field to save time and money. Because the authors demonstrate the most important chemometric methods with the aid of numerous examples, the reader will learn to solve a given problem by use of the appropriate method. Applications range from sampling, through laboratory analysis, to evaluation. Interpretation of the findings is explained clearly. The text covers not only basic methods such as univariate statistics, regression analysis, and statistical test planning, but also multivariate data analysis, for example, cluster analysis, principal components analysis, and factor and discriminant analysis. Case studies show the enormous possibilities, and the limits, of chemometric methods. The book will help all environmental analytical scientists, even those with only a basic knowledge of mathematics, to optimize the evaluation and interpretation of the results of their measurements.