*COMPUTATIONAL INTELLIGENCE FOR SUPPLY CHAIN MANAGEMENT AND DESIGN:   
   ADVANCED METHODS*   
      
    EDITED BOOK   
      
   IGI Global (former IDEA publishing)   
      
   *Book Editors:   
   *   
      
   */I. Minis, V. Zeimpekis, G. Dounias, N. Ampazis/*   
      
   Department of Financial & Management Engineering   
      
   University of the Aegean   
      
   {i.minis, vzeimp}@fme.aegean.gr; g.dounias@aegean.gr;   
   n.ampazis@fme.aegean.gr   
      
      
   *1. Synopsis*   
      
      
      
   This edited volume will focus on the contribution of Computational   
   Intelligence to Supply Chain Management. Computational Intelligence   
   (CI) is a term corresponding to a new generation of algorithmic   
   methodologies in artificial intelligence, which combines elements of   
   learning, adaptation, evolution and approximate (fuzzy) reasoning to   
   create programs that -in a way- can be considered intelligent. The   
   proposed edited volume will present CI methods addressing topics in   
   the entire spectrum of the supply chain i.e. from forecasting,   
   planning for production and distribution to actual implementation,   
   including production and inventory control, warehouse management,   
   management of distribution channels, and transportation. Emphasis will   
   be given to those CI methods and techniques that provide effective   
   solutions to complex supply chain problems, exhibiting superior   
   performance with respect to other methods of operations research.  The   
   edited volume will also include integrated case studies that describe   
   the solution to actual problems of high complexity.   
      
   * *   
      
   * *   
      
   *2. Supply Chain and Computational Intelligence*   
      
   * *   
      
   The supply chain of both manufacturing and commercial enterprises   
   comprises a highly distributed environment, in which complex processes   
   evolve in a network of companies.  Such processes include materials   
   procurement and storage, production of intermediate and final   
   products, warehousing, sales, and distribution (see Fig. 1).  The role   
   of the supply chain in a company's competitiveness is critical, since   
   the supply chain affects directly customer service, inventory and   
   distribution costs, and responsiveness to the ever changing markets.   
   Furthermore, this role becomes more critical in today's distributed   
   manufacturing environment, in which companies focus on core   
   competencies and outsource supportive tasks, thus creating large   
   supply networks. Within this environment there are strong interactions   
   of multiple entities, processes, and data.  For each process in   
   isolation, it is usually feasible to identify those decisions that are   
   locally optimal, especially in a deterministic setting.  However,   
   decision making in supply chain systems should consider intrinsic   
   uncertainties, while coordinating the interests and goals of the   
   multitude of processes involved.   
      
      
      
   **   
      
   *Figure 1.* The flow of decisions and information in the supply chain   
      
      
      
   Most advances in the use of computational methods to support supply   
   chain operations have focused in low level operational decisions,   
   while little attention has been applied to more important areas of   
   supply chain management like product forecasting and strategic support   
   systems. In addition, many existing models focus on individual   
   components of the overall system, and thus ignore the integrated   
   approach. An integrated approach, however, is essential due to the   
   inherent trade-offs involved in all stages of the supply chain   
   operations.   
      
      
      
   Computational Intelligence has emerged as a rapid growing field in the   
   past few years. Its variety of intelligent techniques emulate human   
   intelligence and processes found in natural systems such as adaptation   
   and learning, planning under large uncertainty, coping with large   
   amounts of data, etc. Successful industrial applications of   
   intelligent systems usually deal with several of these aspects and it   
   is therefore natural to combine various technologies with different   
   capabilities within an integrated decision support system. Most of the   
   tasks required for effective management of logistics activities can be   
   achieved using methodologies from several areas of computational   
   intelligence.   
      
      
      
   For the purposes of this book computational intelligence methodologies   
   are generally classified into three major areas, according to the   
   nature of the methodology used to approach supply chain management   
   problems:   
     1. _Standard_ widely acknowledged and applied _intelligent   
        techniques_, such as neural networks (NN), fuzzy systems (FS),   
        genetic algorithms and genetic programming (GA/GP, and other   
        machine learning algorithms (ML). These methods manage to   
        successfully perform association, generalization, function   
        approximation, rule induction, etc. in difficult multivariate   
        domains of application. Methods belonging to this category could   
        be further divided into automated-learning computational   
        intelligence techniques, (NNs, GA/GP, other ML algorithms) and in   
        intelligent modeling approaches (where fuzzy systems and rough   
        sets could be included, as well as approaches related to fuzzy   
        decision analysis, intelligent multi-criteria decision making,   
   etc).   
     2. _Hybrid and Adaptive Intelligence_ by which is meant any   
   efficient   
        combination of the above mentioned intelligent techniques, with   
        other intelligent or conventional methodologies for handling   
        complex problems. Usually one of the methods combined within a   
        hybrid or adaptive scheme, is used either to filter or to fine   
        tune special operations of another methodology, in an intelligent   
        manner and in a way that the total scheme performs superior to   
        simple standard or conventional approaches. Most popular hybrid   
        methodologies are neuro-fuzzy systems, evolving-fuzzy systems,   
        neuro-genetic approaches and genetic-fuzzy ones. There are also   
        applications in literature combining wavelets with intelligent   
        techniques, as well as standard intelligent techniques with   
        nature-inspired ones.   
     3. _Nature Inspired Intelligence_ (NII) in which are included   
        methodologies such as swarm intelligence, ant colony   
   optimization,   
        bee-algorithms, artificial immune systems etc., applied in   
        logistics and supply chain optimization problems. Usually these   
        methodologies represent simultaneous exploration and exploitation   
        of the search space in a smart manner (i.e. local and global   
        search), analogously to the way natural systems or societies   
        perform similar tasks (e.g. swarm flying or swimming, food search   
        and identification, etc.)   
      
      
      
      
   This edited volume will present CI methods addressing topics in the   
   entire spectrum of the supply chain i.e. from forecasting, planning   
   for production and distribution to actual implementation, including   
      
   [continued in next message]   
      
   --- SoupGate-Win32 v1.05   
    * Origin: you cannot sedate... all the things you hate (1:229/2)