Aboul Ella Hassanien (Abo)

n/a

This paper introduces a hybrid scheme that combines the advantages of fuzzy sets and rough sets in conjunction with statistical feature extraction techniques. An application of breast cancer imaging has been chosen and hybridization scheme have been applied to see their ability and accuracy to classify the breast cancer images into two outcomes: cancer or non-cancer. The introduced scheme starts with fuzzy image processing as pre-processing techniques to enhance the contrast of the whole image; to extracts the region of interest and then to enhance the edges surrounding the region of interest. A subsequently extract features from the segmented regions of the interested regions using the gray-level co-occurrence matrix is presented. Rough sets approach for generation of all reducts that contains minimal number of attributes and rules is introduced. Finally, these rules can then be passed to a classifier for discrimination for different regions of interest to test whether they are cancer or non-cancer. To measure the similarity, a new rough set distance function is presented. The experimental results show that the hybrid scheme applied in this study perform well reaching over 98% in overall accuracy with minimal number of generated rules. (This paper was not presented at any IFAC meeting).

Learning methods and approximation algorithms are fundamental tools that deal with computationally hard problems and problems in which the input is gradually disclosed over time. Both kinds of problems have a large number of applications arising from a variety of fields, such as algorithmic game theory, approximation classes, coloring and partitioning, competitive analysis, computational finance, cuts and connectivity, geometric problems, inapproximability results, mechanism design, network design, packing and covering, paradigms for design and analysis of approximation and online algorithms, randomization techniques, real-world applications, scheduling problems and so on. The past years have witnessed a large number of interesting applications using various techniques of Computational Intelligence such as rough sets, connectionist learning; fuzzy logic; evolutionary computing; artificial immune systems; swarm intelligence; reinforcement learning, intelligent multimedia processing etc.. In spite of numerous successful applications of Computational Intelligence in business and industry, it is sometimes difficult to explain the performance of these techniques and algorithms from a theoretical perspective. Therefore, we encouraged authors to present original ideas dealing with the incorporation of different mechanisms of Computational Intelligent dealing with Learning and Approximation algorithms and underlying processes.

Human reasoning usually is very approximate and involves various types of uncertainties. Approximate reasoning is the computational modelling of any part of the process used by humans to reason about natural phenomena or to solve real world problems. The scope of this book includes fuzzy sets, Dempster-Shafer theory, multi-valued logic, probability, random sets, and rough set, near set and hybrid intelligent systems. Besides research articles and expository papers on theory and algorithms of approximation reasoning, papers on numerical experiments and real world applications were also encouraged. This Volume comprises of 12 chapters including an overview chapter providing an up-to-date and state-of-the research on the applications of Computational Intelligence techniques for approximation reasoning. The Volume is divided into 2 parts: Part-I: Approximate Reasoning – Theoretical Foundations and Part-II: Approximate Reasoning – Success Stories and Real World Applications

Global optimization is a branch of applied mathematics and numerical analysis that deals with the task of finding the absolutely best set of admissible conditions to satisfy certain criteria / objective function(s), formulated in mathematical terms. Global optimization includes nonlinear, stochastic and combinatorial programming, multiobjective programming, control, games, geometry, approximation, algorithms for parallel architectures and so on. Due to its wide usage and applications, it has gained the attention of researchers and practitioners from a plethora of scientific domains. Typical practical examples of global optimization applications include: Traveling salesman problem and electrical circuit design (minimize the path length); safety engineering (building and mechanical structures); mathematical problems (Kepler conjecture); Protein structure prediction (minimize the energy function) etc.

Computational tools or solutions based on intelligent systems are being used with great success in Data Mining applications. Nature has been very successful in providing clever and efficient solutions to different sorts of challenges and problems posed to organisms by ever-changing and unpredictable environments. It is easy to observe that strong scientific advances have been made when issues from different research areas are integrated. A particularly fertile integration combines biology and computing. Computational tools inspired on biological process can be found in a large number of applications. One of these applications is Data Mining, where computing techniques inspired on nervous systems; swarms, genetics, natural selection, immune systems and molecular biology have provided new efficient alternatives to obtain new, valid, meaningful and useful patterns in large datasets.