Best Practices and Modern Methods
Buch, Englisch, 219 Seiten, Format (B × H): 160 mm x 241 mm, Gewicht: 524 g
ISBN: 978-3-031-48962-4
Verlag: Springer
This book starts with the rationale for creating an FCM by contrast to other techniques for participatory modeling, as this rationale is a key element to justify the adoption of techniques in a research paper. Fuzzy cognitive mapping is an active research field with over 20,000 publications devoted to externalizing the qualitative perspectives or “mental models” of individuals and groups. Since the emergence of fuzzy cognitive maps (FCMs) back in the 80s, new algorithms have been developed to reduce bias, facilitate the externalization process, or efficiently utilize quantitative data via machine learning. It covers the development of an FCM with participants through a traditional in-person setting, drawing from the experience of practitioners and highlighting solutions to commonly encountered challenges. The book continues with introducing principles of simulations with FCMs as a tool to perform what-if scenario analysis, while extending those principles to more elaborated simulation scenarios where FCMs and agent-based modeling are combined. Once an FCM model is obtained, the book then details the analytical tools available for practitioners (e.g., to identify the most important factors) and provides examples to aid in the interpretation of results. The discussion concerning relevant extensions is equally pertinent, which are devoted to increasing the expressiveness of the FCM formalism in problems involving uncertainty. The last four chapters focus on building FCM models from historical data. These models are typically needed when facing multi-output prediction or pattern classification problems. In that regard, the book smoothly guides the reader from simple approaches to more elaborated algorithms, symbolizing the noticeable progress of this field in the last 35 years. Problems, recent references, and functional codes are included in each chapter to provide practice and support further learning from practitioners and researchers.
Zielgruppe
Graduate
Autoren/Hrsg.
Fachgebiete
Weitere Infos & Material
Fuzzy Cognitive Maps: Best Practices and Modern Methods
Philippe J. Giabbanelli and Gonzalo Nápoles
1 Defining and Using Fuzzy Cognitive Mapping
Philippe J. Giabbanelli, C.B. Knox, Kelsi Furman, Antonie Jetter and
Steven Gray
1.1 Introduction
1.2 Three equivalent definitions
1.2.1 FCMs as mental models
1.2.2 FCMs as mathematical objects
1.2.3 FCMs as simulation tools
1.3 A typology of uses
1.3.1 FCMs as Expert Systems
1.3.2 FCMs in Collective Intelligence
1.3.3 FCMs as boundary objects to support learning
1.3.4 FCMs as prediction models
Exercises
References
2 Creating an FCM with participants in an interview or workshop setting
C.B. Knox, Kelsi Furman, Antonie Jetter, Steven Gray and Philippe J.Giabbanelli
2.1 Decision Factors
2.1.1 Individual vs Group Modeling2.1.2 Facilitator vs. Participant Mapping
2.1.3 Hand-Drawn Models vs Modeling Software
2.1.4 Pre-Defined, Open-Ended Concepts or Hybrid Approach
2.2 Data Collection
2.2.1 Creating a Parsimonious Model and Weighting Connections
2.2.2 Participant Recruitment
2.2.3 Facilitation Considerations
2.3 Conclusions
Exercises
References
3 Principles of simulations with FCMs
Gonzalo Nápoles and Philippe J. Giabbanelli
3.1 Introduction: revisiting the reasoning mechanism
3.2 Activation functions
3.3 Convergence: a mathematical perspective
3.4 Convergence: a simulation approach
3.5 A detailed example in Python
3.6 Exercises
References
4 Hybrid Simulations
Philippe J. Giabbanelli
4.1 Introduction
4.2 Rationale for a hybrid ABM/FCM simulation
4.3 Main steps to design a hybrid ABM/FCM simulation
4.4 Example of study design and Python implementation
4.5 Scaling-up simulations using parallelism
4.6 Exercises
References
5 Analysis of Fuzzy Cognitive Maps
Ryan Schuerkamp and Philippe J. Giabbanelli
5.1 Why Analyze Fuzzy Cognitive Maps?
5.2 What Are the Important Concepts?
5.2.1 Transmitter, Receiver, and Ordinary Concepts5.2.2 Centrality Measures
5.3 Validating the Facilitation Process
5.3.1 Number of Concepts and Relationships
5.3.2 Receiver-Transmitter Ratio
5.3.3 Metrics based on shortest paths
5.3.4 Clustering Coefficient
5.3.5 Density
5.3.6 Feedback Loops
5.4 Conclusion
5.5 Exercises
References
6 Extensions of Fuzzy Cognitive Maps
Ryan Schuerkamp and Philippe J. Giabbanelli
6.1 Why Do We Extend Fuzzy Cognitive Maps?
6.2 Interval-Valued Fuzzy Cognitive Maps
6.2.1 Example Interval-Valued Fuzzy Cognitive Map Inference
6.3 Time-Interval Fuzzy Cognitive Maps
6.3.1 Example Time-Interval Fuzzy Cognitive Map Inference
6.4 Extended-Fuzzy Cognitive Maps
6.4.1 Example Extended-Fuzzy Cognitive Map Inference
6.5 Trends and Future of Extensions of Fuzzy Cognitive Maps
6.6 Exercises
References
7 Creating FCM models from quantitative data with evolutionary algorithms
David Bernard and Philippe J. Giabbanelli
7.1 Introduction
7.2 Representing the genome .
7.2.1 Transformations between vector and matrix
7.2.2 Constraints
7.3 Evaluation
7.4 Genetic Algorithms
7.5 Analysis
7.6 CMA-ES
ExercisesReferences
8 Advanced learning algorithm to create FCM models from quantitative data
Agnieszka Jastrzebska and Gonzalo Nápoles
8.1 Introduction
8.2 Hybrid Fuzzy Cognitive Map model
8.3 Training the hybrid FCM model
8.4 Optimizing the hybrid FCM model
8.4.1 Detecting superfluous relationships
8.4.2 Calibrating the sigmoid offset
8.4.3 Calibrating the weights
8.5 How to use these algorithms in practice?
8.6 Applying the FCM model to real-world data
8.6.1 Sensitivity to the sigmoid function parameters8.6.2 Comparison with other learning approaches
8.7 Further readings
8.8 Exercises
References
9 Introduction to Fuzzy Cognitive Map-based classification
Agnieszka Jastrzebska and Gonzalo Nápoles
9.1 Introduction
9.2 Preliminaries
9.2.1 Notions of classification and features
9.2.2 Preliminary processing
9.2.3 Performance metrics
9.3 The FCM-based classification model
9.3.1 Basic FCM architecture for data classification
9.3.2 Genetic Algorithm-based optimization
9.3.3 How does the model classify new instances?
9.4 Classification toy case study
9.4.1 Data description
9.4.2 Classifier implementation
9.4.3 Classification – overall quality
9.5 Further readings
9.6 Exercises
References
10 Addressing accuracy issues of Fuzzy Cognitive Map-based classifiers
Gonzalo Nápoles and Agnieszka Jastrzebska
10.1 Introduction
10.2 Long-term Cognitive Network-based classifier
10.2.1 Generalizing the traditional FCM formalism
10.2.2 Recurrence-aware decision model
10.2.3 Learning algorithm for LTCN-based classifiers
10.3 Model-dependent feature importance measure
10.4 How to use the LTCN-based classifier in practice?
10.5 Empirical evaluation of the LTCN classifier
10.5.1 Pattern classification datasets10.5.2 Does the LTCN classifier outperform the FCM classifier?
10.5.3 Hyperparameter sensitivity analysis
10.5.4 Comparison of LTCN with state-of-the-art classifiers
10.6 Illustrative case study: phishing dataset
10.7 Further readings
10.8 Exercises
References
Index
