The fields of similarity and preference are still broadening due to the exploration of new fields of application. This is caused by the strong impact of vagueness, imprecision, uncertainty and dominance on human and agent information, communication, planning, decision, action, and control as well as by the technical progress of the information technology itself. The topics treated in this book are of interest to computer scientists, statisticians, operations researchers, experts in AI, cognitive psychologists and economists.

The fields of similarity and preference are still broadening due to the exploration of new fields of application. This is caused by the strong impact of vagueness, imprecision, uncertainty and dominance on human and agent information, communication, planning, decision, action, and control as well as by the technical progress of the information technology itself. The topics treated in this book are of interest to computer scientists, statisticians, operations researchers, experts in AI, cognitive psychologists and economists.

This book focuses on exploratory data analysis, learning of latent structures in datasets, and unscrambling of knowledge. Coverage details a broad range of methods from multivariate statistics, clustering and classification, visualization and scaling as well as from data and time series analysis. It provides new approaches for information retrieval and data mining and reports a host of challenging applications in various fields.

This volume contains papers read at the 7th International Workshop entitled "Intelligent Agents: Decision-Support and Planning", Udine, Italy, Sep 30th - Oct 2nd, 2004. All papers were reviewed after they were presented, and revised for final publication. As its preceding ones, this workshop took place under the auspices of the International School for the Synthesis of Expert Knowledge (ISSEK) and was held in the picturesque Palazzo del Torso of the Centre International des Sciences Mecaniques (CISM), Udine, see picture below. CISM location " Palazzo del Torso " The workshop was jointly organised by Prof. G. Delia Riccia (University of Udine), Dr. D. Dubois ( CNRS and University of Toulouse III), Prof. R. Kruse (University of Magdeburg), and Prof. H .- J. Lenz (Free University Berlin). As the workshop was an invitational one, there was no need for a call for contributed papers. Contrarily, the four organisers recruited research workers from Europe who have had an impact in the last decade on "Intelligent Agents: Decision-Support and Planning".

This volume treats the four main categories of Statistical Quality Control: General SQC Methodology, On-line Control including Sampling Inspection and Statistical Process Control, Off-line Control with Data Analysis and Experimental Design, and, fields related to Reliability. Experts with international reputation present their newest contributions.

This book constitutes the refereed proceedings of the 5th International Conference on Intelligent Data Analysis, IDA 2003, held in Berlin, Germany in August 2003. The 56 revised papers presented were carefully reviewed and selected from 180 submissions. The papers are organized in topical sections on machine learning, probability and topology, classification and pattern recognition, clustering, applications, modeling, and data processing.

This work is a collection of front-end research papers on data fusion and perceptions. Authors are leading European experts of Artificial Intelligence, Mathematical Statistics and/or Machine Learning. Area overlaps with Intelligent Data Analysis, which aims to unscramble latent structures in collected data: Statistical Learning, Model Selection, Information Fusion, Soccer Robots, Fuzzy Quantifiers, Emotions and Artifacts.

In the 1920's, Walter Shewhart visualized that the marriage of statistical methods and manufacturing processes would produce reliable and consistent quality products. Shewhart (1931) conceived the idea of statistical process control (SPC) and developed the well-known and appropriately named Shewhart control chart. However, from the 1930s to the 1990s, literature on SPC schemes have been "captured" by the Shewhart paradigm of normality, independence and homogeneous variance. When in fact, the problems facing today's industries are more inconsistent than those faced by Shewhart in the 1930s. As a result of the advances in machine and sensor technology, process data can often be collected on-line. In this situation, the process observations that result from data collection activities will frequently not be serially independent, but autocorrelated. Autocorrelation has a significant impact on a control chart: the process may not exhibit a state of statistical control when in fact, it is in control. As the prevalence of this type of data is expected to increase in industry (Hahn 1989), so does the need to control and monitor it. Equivalently, literature has reflected this trend, and research in the area of SPC with autocorrelated data continues so that effective methods of handling correlated data are available. This type of data regularly occurs in the chemical and process industries, and is pervasive in computer-integrated manufacturing environments, clinical laboratory settings and in the majority of SPC applications across various manufacturing and service industries (Alwan 1991).

The contents of these proceedings reflect the intention of the organizers of the workshop to bring together scientists and engineers having a strong interest in interdisciplinary work in the fields of computer science, mathematics and applied statistics. Results of this collaboration are illustrated in problems dealing with neural nets, statistics and networks, classification and data mining, and (machine) learning.

Like the preceding volumes, and met with a lively response, the present volume is collecting contributions stressed on methodology or successful industrial applications. The papers are classified under four main headings: sampling inspection, process quality control, data analysis and process capability studies and finally experimental design.

Like the first three volumes, published in 1981, 1984 and 1987 and met with a lively response, the present volume is collecting contributions stressed on methodology or successful industrial applications. The papers are classified under three main headings; sampling inspection, process quality control and experimental design. In the first group there are nine papers on acceptance sampling. The second large group of papers deal with control charts and process control and the third group of papers includes contributions on experimental design.

The 10th International Workshop on Intelligent Statistical Quality Control took place in Seattle, USA, Aug 18-20, 2010. It was hosted by Professor C. M. Mastrangelo, Department of Industrial and Systems Engineering, University of Washington, Seattle. The workshop was jointly organized by Professors H. J. Lenz, C. M. Mastrangelo, W. Schmid and P.T. Wilrich. The twenty-seven papers in this volume were carefully selected by the scientific program committee, reviewed by its members, revised by the authors and, finally, adapted for this volume by the editors.

The book is divided into two parts: Part I "On-line Control" covers fields like control charting, monitoring and surveillance as well as acceptance sampling. Part II "Off-line Control" is devoted to experimental design, process capability analysis and data quality.

The purpose of the book is on the one hand to provide insights into important new developments in the area of statistical quality control especially surveillance and monitoring and on the other handto critically discuss methods used in on-line and off-line statistical quality control.

"

In Canada, acceptance sampling has been used in legal metrology applications for nearly four decades. One of its principal uses has been in the quality control of utility meters that measure electricity or natural gas supplied to consumers. By law, such meters must be inspected for conformance to specification requirements prior to use and be periodically inspected while huse. With few exceptions, due to the numerous utility companies in the country and their varied practices, the meters exist in the form of isolated lots for inspection purposes. The proportion of nonconforming meters in a lot has traditionally defined lot quality for utility meter sampling inspection purposes. Another principal application of acceptance sampling has been in the quality control of the net contents of packaged products sold in the marketplace. Such products include those sold on the basis of such measures as weight, volume, length, and area. In this particular application, products are also usually inspected on an isolated-lot basis for regulatory purposes. However, lot quality is usually measured on the basis of two criteria for such products: the proportion of nonc- forming packages in the lot and the lot mean quantity. This section reviews Canadian quality control practices in these two areas of application, highlighting some of the deficiencies and issues. Three-class s- pling plans are proposed as a possible solution to some of these deficiencies and issues.

Spatestens seit der grossen Aufdeckungswelle von Missbrauchsfallen in (kirchlichen und reformpadagogischen) Einrichtungen im Jahre 2010 ist fur eine grossere Offentlichkeit deutlich geworden, dass auch mannliche Kinder und Jugendliche in grosser Zahl von sexualisierter Gewalt betroffen sind. Besonders beunruhigend war in diesem Zusammenhang die Einsicht, dass die meisten Betroffenen uber viele Jahrzehnte Stillschweigen behielten uber das, was ihnen angetan worden war. Und auch die psycho-soziale Arbeit und politisch Verantwortliche haben lange Zeit uber die mannlichen Betroffenen hinweggeschaut. Nicht zuletzt im Rahmen des Runden Tisches, den die Bundesregierung zur Aufarbeitung der Missbrauchsfalle einberufen hat, ist der Ruf nach geeigneten - d. h. auch geschlechtssensiblen - Hilfen fur die Opfer sexualisierter Gewalt laut geworden. Mit diesem Buch wird erstmals ein Uberblick uber das Spektrum an Hilfen fur mannliche Betroffene gegeben. Dazu werden geschlechtssensible Konzepte fur praventives Handeln vorgestellt und Einblicke in die Arbeit im deutschsprachigen Ausland gegeben. Das Buch fuhrt zu der uberraschenden Einsicht, dass - fast im Verborgenen - eine sehr professionelle, differenzierte und entwicklungsfahige Praventions- und Hilfekultur entstanden ist, die auf eine vielfaltige Methodik und eine grosse Menge praktischer Handlungsideen verweisen kann."

Das Buch befasst sich mit der Bereitstellung von Daten und Verfahren fur analytische Zwecke (Planung, Entscheidung, Controlling sowie Fehlerruckverfolgung) in Unternehmen sowie der notwendigen Rechenleistungen. Die Autoren erlautern die Datenbereitstellung mittels Data Warehouses, Auswertung mittels OLAP-Operationalitat und geeignete Verfahren der explorativen Datenanalyse. Bei den Verfahren des Operations Research werden Simulation und Lineare Optimierung dargestellt. Neben erfolgreichen Anwendungen und Fallstudien steht das Verstandnis der zugrundeliegenden Algorithmen und Datenstrukturen, die fur das Erlernen der BI-Verfahren zwingend notwendig sind, im Vordergrund."

In der Praxis tritt haufig der Fall auf, dass eine ganze Folge von Warenlosen des gleichen Artikels vom gleichen Anlieferer zu kontrollieren ist bzw. zur Zwischenkontrolle oder Endkontrolle vorgelegt wird. In dieser Situation existieren meistens ziemlich genaue Kenntnisse uber Pruf-, Ersatz- und Garantiekosten eines Einzelstucks sowie Fixkosten fur die Prufung eines Loses. Auch uber die Verteilung der Losschlechtanteile, die Prozesskurve, sind in diesem Fall Kenntnisse vorhanden. In dieser Arbeit wird untersucht, wie durch die Analyse der Stichprobenergebnisse auf moegliche AEnderungen der Prozesskurve zu schliessen ist. Signalisieren die Stichprobenergebnisse eine AEnderung der Prozesskurve, so soll anhand der verfugbaren Informationen die neue Prozesskurve geschatzt werden, und ein neuer Prufplan soll entsprechend dieser Prozesskurve bayesoptimal gewahlt werden. Die in dieser Arbeit entwickelten adaptiven Stichprobensysteme schneiden hinsichtlich der erwarteten Verluste bei Fehlentscheidungen uber Prufaufwand und Losannahme z.T. erheblich besser ab, sind einfacher zu handhaben und kommen mit einer geringeren Zahl von Prufplanwechseln aus als herkoemmliche Verfahren.

The twenty-three papers in this volume are carefully selected, reviewed and revised for this volume, and are divided into two parts: Part 1: "On-line Control" with subchapters 1.1 "Control Charts" and 1.2 "Surveillance Sampling and Sampling Plans" and Part 2: "Off-line Control."