Autonomous Learning Systems is the result of over a
decade of focused research and studies in this emerging area which
spans a number of well-known and well-established disciplines that
include machine learning, system identification, data mining, fuzzy
logic, neural networks, neuro-fuzzy systems, control theory and
pattern recognition. The evolution of these systems has been both
industry-driven with an increasing demand from sectors such as
defence and security, aerospace and advanced process industries,
bio-medicine and intelligent transportation, as well as
research-driven - there is a strong trend of innovation of
all of the above well-established research disciplines that is
linked to their on-line and real-time application; their
adaptability and flexibility.

Providing an introduction to the key technologies, detailed
technical explanations of the methodology, and an illustration of
the practical relevance of the approach with a wide range of
applications, this book addresses the challenges of autonomous
learning systems with a systematic approach that lays the
foundations for a fast growing area of research that will underpin
a range of technological applications vital to both industry and
society.

Key features:

* Presents the subject systematically from explaining the
fundamentals to illustrating the proposed approach with numerous
applications.

* Covers a wide range of applications in fields including
unmanned vehicles/robotics, oil refineries, chemical industry,
evolving user behaviour and activity recognition.

* Reviews traditional fields including clustering,
classification, control, fault detection and anomaly
detection, filtering and estimation through the prism of evolving
and autonomously learning mechanisms.

* Accompanied by a website hosting additional material, including
the software toolbox and lecture notes.

Autonomous Learning Systems provides a 'one-stop
shop' on the subject for academics, students, researchers and
practicing engineers. It is also a valuable reference for
Government agencies and software developers.

Plamen Parvanov Angelov, Lancaster University, UK
Plamen Parvanov is a senior lecturer in the School of Computing and Communications at Lancaster University. He is an Associate Editor of three international journals and the founding co-Editor-in-Chief of the Springer journal Evolving Systems. He is also the Vice Chair of the Technical Committee on Standards, Computational Intelligence Society, IEEE and co-Chair of several IEEE conferences. His research in UAV/UAS is often publicised in external publications, e.g. the prestigious Computational Intelligence Magazine; Aviation Week, Flight Global, Airframer, Flight International, etc. His research focuses on computational intelligence and evolving systems, and his research in to autonomous systems has received worldwide recognition. As the Principle Investigator at Lancaster University for a team working on UAV Sense and Avoid fortwo projects of ASTRAEA his work was recognised by 'The Engineer Innovation and Technology 2008 Award in two categories: i) Aerospace and Defence and ii) The Special Award which is an outstanding achievement.

Klappentext

Autonomous Learning Systems is the result of over a decade of focused research and studies in this emerging area which spans a number of well-known and well-established disciplines that include machine learning, system identification, data mining, fuzzy logic, neural networks, neuro-fuzzy systems, control theory and pattern recognition. The evolution of these systems has been both industry-driven with an increasing demand from sectors such as defence and security, aerospace and advanced process industries, bio-medicine and intelligent transportation, as well as research-driven there is a strong trend of innovation of all of the above well-established research disciplines that is linked to their on-line and real-time application; their adaptability and flexibility.

Providing an introduction to the key technologies, detailed technical explanations of the methodology, and an illustration of the practical relevance of the approach with a wide range of applications, this book addresses the challenges of autonomous learning systems with a systematic approach that lays the foundations for a fast growing area of research that will underpin a range of technological applications vital to both industry and society.

Key features:

• Presents the subject systematically from explaining the fundamentals to illustrating the proposed approach with numerous applications.
• Covers a wide range of applications in fields including unmanned vehicles/robotics, oil refineries, chemical industry, evolving user behaviour and activity recognition.
• Reviews traditional fields including clustering, classification, control, fault detection and anomaly detection, filtering and estimation through the prism of evolving and autonomously learning mechanisms.
• Accompanied by a website hosting additional material, including the software toolbox and lecture notes.

Autonomous Learning Systems provides a 'one-stop shop' on the subject for academics, students, researchers and practicing engineers. It is also a valuable reference for Government agencies and software developers.

Forewords xi

Preface xix

About the Author xxiii

1 Introduction 1

1.1 Autonomous Systems 3

1.2 The Role of Machine Learning in Autonomous Systems 4

1.3 System Identification an Abstract Model of the Real World 6

1.4 Online versus Offline Identification 9

1.5 Adaptive and Evolving Systems 10

1.6 Evolving or Evolutionary Systems 11

1.7 Supervised versus Unsupervised Learning 13

1.8 Structure of the Book 14

PART I FUNDAMENTALS

2 Fundamentals of Probability Theory 19

2.1 Randomness and Determinism 20

2.2 Frequentistic versus Belief-Based Approach 22

2.3 Probability Densities and Moments 23

2.4 Density Estimation Kernel-Based Approach 26

2.5 Recursive Density Estimation (RDE) 28

2.6 Detecting Novelties/Anomalies/Outliers using RDE 32

2.7 Conclusions 36

3 Fundamentals of Machine Learning and Pattern Recognition 37

3.1 Preprocessing 37

3.2 Clustering 42

3.3 Classification 56

3.4 Conclusions 58

4 Fundamentals of Fuzzy Systems Theory 61

4.1 Fuzzy Sets 61

4.2 Fuzzy Systems, Fuzzy Rules 64

4.3 Fuzzy Systems with Nonparametric Antecedents (AnYa) 69

4.4 FRB (Offline) Classifiers 73

4.5 Neurofuzzy Systems 75

4.6 State Space Perspective 79

4.7 Conclusions 81

PART II METHODOLOGY OF AUTONOMOUS LEARNING SYSTEMS

5 Evolving System Structure from Streaming Data 85

5.1 Defining System Structure Based on Prior Knowledge 85

5.2 Data Space Partitioning 86

5.3 Normalisation and Standardisation of Streaming Data in an Evolving Environment 96

5.4 Autonomous Monitoring of the Structure Quality 98

5.5 Short- and Long-Term Focal Points and Submodels 104

5.6 Simplification and Interpretability Issues 105

5.7 Conclusions 107

6 Autonomous Learning Parameters of the Local Submodels 109

6.1 Learning Parameters of Local Submodels 110

6.2 Global versus Local Learning 111

6.3 Evolving Systems Structure Recursively 113

6.4 Learning Modes 116

6.5 Robustness to Outliers in Autonomous Learning 118

6.6 Conclusions 118

7 Autonomous Predictors, Estimators, Fi…