Rule Based Systems for Big Data | springerprofessional.de

Springer Professional

nach oben

2016 | Buch

Kapitel lesen Erstes Kapitel lesen

Rule Based Systems for Big Data

A Machine Learning Approach

verfasst von: Han Liu, Alexander Gegov, Mihaela Cocea

Verlag: Springer International Publishing

Buchreihe : Studies in Big Data

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten

Über dieses Buch

The ideas introduced in this book explore the relationships among rule based systems, machine learning and big data. Rule based systems are seen as a special type of expert systems, which can be built by using expert knowledge or learning from real data.

The book focuses on the development and evaluation of rule based systems in terms of accuracy, efficiency and interpretability. In particular, a unified framework for building rule based systems, which consists of the operations of rule generation, rule simplification and rule representation, is presented. Each of these operations is detailed using specific methods or techniques. In addition, this book also presents some ensemble learning frameworks for building ensemble rule based systems.

Anzeige

Inhaltsverzeichnis

Frontmatter

Chapter 1. Introduction

Abstract

Expert systems have been increasingly popular for commercial applications. A rule based system is a special type of expert system. The development of rule based systems began in the 1960s but became popular in the 1970s and 1980s (Partridge and Hussain in Knowledge Based Information Systems. Mc-Graw Hill, London, 1994). A rule based system typically consists of a set of if-then rules, which can serve many purposes such as decision support or predictive decision making in real applications.

Han Liu, Alexander Gegov, Mihaela Cocea

Chapter 2. Theoretical Preliminaries

Abstract

As mentioned in Chap. 1, some fundamental concepts strongly relate to rule based systems and machine learning, including discrete mathematics, statistics, if-then rules, algorithms, logic and statistical measures of rule quality.

Han Liu, Alexander Gegov, Mihaela Cocea

Chapter 3. Generation of Classification Rules

Abstract

As mentioned in Chap. 1, rule generation can be done through the use of the two approaches: divide and conquer and separate and conquer. This chapter describes the two approaches of rule generation. In particular, the existing rule learning algorithms, namely ID3, Prism and Information Entropy Based Rule Generation (IEBRG), are illustrated in detail. These algorithms are also discussed comparatively with respects to their advantages and disadvantages.

Han Liu, Alexander Gegov, Mihaela Cocea

Chapter 4. Simplification of Classification Rules

Abstract

As mentioned in Chap. 1, pruning methods are increasingly required for rule simplification due to the overfitting problem. This chapter introduces two approaches of rule simplification namely, pre-pruning and post-pruning. In particular, some existing rule pruning algorithms are described in detail. These algorithms are also discussed comparatively with respects to their advantages and disadvantages.

Han Liu, Alexander Gegov, Mihaela Cocea

Chapter 5. Representation of Classification Rules

Abstract

As mentioned in Chap. 1, appropriate rule representation is necessary in order to improve model efficiency and interpretability. This chapter introduces three techniques for representation of classification rules namely, decision trees, linear lists and rule based networks. In particular, these representations are illustrated using examples in terms of searching for firing rules. These techniques are also discussed comparatively in terms of computational complexity and interpretability.

Han Liu, Alexander Gegov, Mihaela Cocea

Chapter 6. Ensemble Learning Approaches

Abstract

As mentioned in Chap. 1, ensemble learning is helpful to improve overall accuracy of classification. This chapter introduces three approaches of ensemble learning namely, parallel learning, sequential learning and hybrid learning. In particular, some popular methods for ensemble learning, such as Bagging and Boosting, are illustrated in detail. These methods are also discussed comparatively with respects to their advantages and disadvantages.

Han Liu, Alexander Gegov, Mihaela Cocea

Chapter 7. Interpretability Analysis

Abstract

Chapter 1 stressed the significance of interpretability for the purpose of knowledge discovery. This chapter introduces theoretical aspects of interpretability on rule based systems. In particular, some impact factors are identified and how these factors have an impact on interpretability is also analyzed. In addition, some criteria for evaluation on interpretability are also listed.

Han Liu, Alexander Gegov, Mihaela Cocea

Chapter 8. Case Studies

Abstract

This chapter introduces three case studies of big data. In particular, the methods and techniques introduced in Chaps. 3, 4, 5 and 6 are evaluated through theoretical analysis and empirical validation using large data sets in terms of accuracy, efficiency and interpretability.

Han Liu, Alexander Gegov, Mihaela Cocea

Chapter 9. Conclusion

Abstract

This chapter summaries the contributions of this book in terms of theoretical significance, practical importance, methodological impact and philosophical aspects. This chapter also identifies and highlights further directions of this research area towards improvement of the research methodologies presented in this book.

Han Liu, Alexander Gegov, Mihaela Cocea

Backmatter

Titel: Rule Based Systems for Big Data
verfasst von: Han Liu
Alexander Gegov
Mihaela Cocea
Copyright-Jahr: 2016
Verlag: Springer International Publishing
Electronic ISBN: 978-3-319-23696-4
Print ISBN: 978-3-319-23695-7
DOI: https://doi.org/10.1007/978-3-319-23696-4

Weitere Formate
Fachgebiete
Bücher
Zeitschriften
Themenseiten
Jetzt Einzelzugang starten
Zugang für Unternehmen
Referenzkunden
SLX-Digitalkonferenz: Zukunftswerkstatt 2024