Decision Tree And Ensemble Learning Based On Ant Colony Optimization

This book not only discusses the important topics in the area of machine learning and combinatorial optimization, it also combines them into one. This was decisive for choosing the material to be included in the book and determining its order of presentation. Decision trees are a popular method of classification as well as of knowledge representation. At the same time, they are easy to implement as the building blocks of an ensemble of classifiers. Admittedly, however, the task of constructing a near-optimal decision tree is a very complex process. The good results typically achieved by the ant colony optimization algorithms when dealing with combinatorial optimization problems suggest the possibility of also using that approach for effectively constructing decision trees. The underlying rationale is that both problem classes can be presented as graphs. This fact leads to option of considering a larger spectrum of solutions than those based on the heuristic. Moreover, ant colony optimization algorithms can be used to advantage when building ensembles of classifiers. This book is a combination of a research monograph and a textbook. It can be used in graduate courses, but is also of interest to researchers, both specialists in machine learning and those applying machine learning methods to cope with problems from any field of R&D.

This book not only discusses the important topics in the area of machine learning and combinatorial optimization, it also combines them into one. This was decisive for choosing the material to be included in the book and determining its order of presentation. Decision trees are a popular method of classification as well as of knowledge representation. At the same time, they are easy to implement as the building blocks of an ensemble of classifiers. Admittedly, however, the task of constructing a near-optimal decision tree is a very complex process. The good results typically achieved by the ant colony optimization algorithms when dealing with combinatorial optimization problems suggest the possibility of also using that approach for effectively constructing decision trees. The underlying rationale is that both problem classes can be presented as graphs. This fact leads to option of considering a larger spectrum of solutions than those based on the heuristic. Moreover, ant colony optimization algorithms can be used to advantage when building ensembles of classifiers. This book is a combination of a research monograph and a textbook. It can be used in graduate courses, but is also of interest to researchers, both specialists in machine learning and those applying machine learning methods to cope with problems from any field of R & D.

This book addresses many-criteria decision-making (MCDM), a process used to find a solution in an environment with several criteria. In many real-world problems, there are several different objectives that need to be taken into account. Solving these problems is a challenging task and requires careful consideration. In real applications, often simple and easy to understand methods are used; as a result, the solutions accepted by decision makers are not always optimal solutions. On the other hand, algorithms that would provide better outcomes are very time consuming. The greatest challenge facing researchers is how to create effective algorithms that will yield optimal solutions with low time complexity. Accordingly, many current research efforts are focused on the implementation of biologically inspired algorithms (BIAs), which are well suited to solving uni-objective problems. This book introduces readers to state-of-the-art developments in biologically inspired techniques and their applications, with a major emphasis on the MCDM process. To do so, it presents a wide range of contributions on e.g. BIAs, MCDM, nature-inspired algorithms, multi-criteria optimization, machine learning and soft computing.

This book presents a unified framework, based on specialized evolutionary algorithms, for the global induction of various types of classification and regression trees from data. The resulting univariate or oblique trees are significantly smaller than those produced by standard top-down methods, an aspect that is critical for the interpretation of mined patterns by domain analysts. The approach presented here is extremely flexible and can easily be adapted to specific data mining applications, e.g. cost-sensitive model trees for financial data or multi-test trees for gene expression data. The global induction can be efficiently applied to large-scale data without the need for extraordinary resources. With a simple GPU-based acceleration, datasets composed of millions of instances can be mined in minutes. In the event that the size of the datasets makes the fastest memory computing impossible, the Spark-based implementation on computer clusters, which offers impressive fault tolerance and scalability potential, can be applied.

This is the first comprehensive book dedicated entirely to the field of decision trees in data mining and covers all aspects of this important technique.Decision trees have become one of the most powerful and popular approaches in knowledge discovery and data mining, the science and technology of exploring large and complex bodies of data in order to discover useful patterns. The area is of great importance because it enables modeling and knowledge extraction from the abundance of data available. Both theoreticians and practitioners are continually seeking techniques to make the process more efficient, cost-effective and accurate. Decision trees, originally implemented in decision theory and statistics, are highly effective tools in other areas such as data mining, text mining, information extraction, machine learning, and pattern recognition. This book invites readers to explore the many benefits in data mining that decision trees offer: Self-explanatory and easy to follow when compacted Able to handle a variety of input data: nominal, numeric and textual Able to process datasets that may have errors or missing values High predictive performance for a relatively small computational effort Available in many data mining packages over a variety of platforms Useful for various tasks, such as classification, regression, clustering and feature selection

While thin film technology has benefited greatly from artificial intelligence (AI) and machine learning (ML) techniques, there is still much to be learned from a full-scale exploration of these technologies in atomic layer deposition (ALD). This book provides in-depth information regarding the application of ML-based modeling techniques in thin film technology as a standalone approach and integrated with the classical simulation and modeling methods. It is the first of its kind to present detailed information regarding approaches in ML-based modeling, optimization, and prediction of the behaviors and characteristics of ALD for improved process quality control and discovery of new materials. As such, this book fills significant knowledge gaps in the existing resources as it provides extensive information on ML and its applications in film thin technology. Offers an in-depth overview of the fundamentals of thin film technology, state-of-the-art computational simulation approaches in ALD, ML techniques, algorithms, applications, and challenges. Establishes the need for and significance of ML applications in ALD while introducing integration approaches for ML techniques with computation simulation approaches. Explores the application of key techniques in ML, such as predictive analysis, classification techniques, feature engineering, image processing capability, and microstructural analysis of deep learning algorithms and generative model benefits in ALD. Helps readers gain a holistic understanding of the exciting applications of ML-based solutions to ALD problems and apply them to real-world issues. Aimed at materials scientists and engineers, this book fills significant knowledge gaps in existing resources as it provides extensive information on ML and its applications in film thin technology. It also opens space for future intensive research and intriguing opportunities for ML-enhanced ALD processes, which scale from academic to industrial applications. . .

This book constitutes the refereed proceedings of the 13th International Conference on Computational Collective Intelligence, ICCCI 2021, held in September/October 2021. The conference was held virtually due to the COVID-19 pandemic. The 58 full papers were carefully reviewed and selected from 230 submissions. The papers are grouped in topical issues on knowledge engineering and semantic web; social networks and recommender systems; collective decision-making; cooperative strategies for decision making and optimization; data mining and machine learning; computer vision techniques; natural language processing; Internet of Things: technologies and applications; Internet of Things and computational technologies for collective intelligence; computational intelligence for multimedia understanding.