An Introduction to Artificial Psychology

Application Fuzzy Set Theory and Deep Machine Learning in Psychological Research using R
1. Auflage 2023
ISBN: 978-3-031-31171-0
Verlag: Springer International Publishing

Buch, Englisch, 252 Seiten, Format (B × H): 160 mm x 241 mm, Gewicht: 576 g

Artificial Psychology (AP) is a highly multidisciplinary field of study in psychology. AP tries to solve problems which occur when psychologists do research and need a robust analysis method. Conventional statistical approaches have deep rooted limitations. These approaches are excellent on paper but often fail to model the real world. Mind researchers have been trying to overcome this by simplifying the models being studied. This stance has not received much practical attention recently. Promoting and improving artificial intelligence helps mind researchers to find a holistic model of mental models. This development achieves this goal by using multiple perspectives and multiple data sets together with interactive, and realistic models. In this book, the methodology of approximate inference in psychological research from a theoretical and practical perspective has been considered. Quantitative variable-oriented methodology and qualitative case-oriented methods are both used to explainthe set-oriented methodology and this book combines the precision of quantitative methods with information from qualitative methods. This is a book that many researchers can use to expand and deepen their psychological research and is a book which can be useful to postgraduate students. The reader does not need an in-depth knowledge of mathematics or statistics because statistical and mathematical intuitions are key here and they will be learned through practice. What is important is to understand and use the new application of the methods for finding new, dynamic and realistic interpretations. This book incorporates theoretical fuzzy inference and deep machine learning algorithms in practice. This is the kind of book that we wished we had had when we were students. This book covers at least some of the most important issues in mind research including uncertainty, fuzziness, continuity, complexity and high dimensionality which are inherent to mind data. These are elements of artificialpsychology. This book implements models using R software.

Zielgruppe

Graduate

Autoren/Hrsg.

Farahani, Hojjatollah

Blagojevi¿, Marija

Blagojevic, Marija

Saljoughi, Sara

Azadfallah, Parviz

Watson, Peter

Esrafilian, Forough

Fachgebiete

• Geisteswissenschaften Philosophie Moderne Philosophische Disziplinen Philosophie des Geistes, Neurophilosophie
• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Maschinelles Lernen
• Sozialwissenschaften Psychologie Allgemeine Psychologie Kognitionspsychologie
• Sozialwissenschaften Psychologie Psychologie / Allgemeines & Theorie Psychologie: Allgemeines

Inhaltsverzeichnis

Introduction

1              After Method

1.1         Pathology of methodology in psychology

1.2         The devil is in the details

1.3         Farewell to certainty in psychology

1.4         Certainty or a repeated cumulative uncertainty

1.4.1            Psychological constructs in disguise

1.4.2           Objectivity in psychology is a real or dram?

1.4.3           What is uncertainty?

1.4.4           Uncertainty typology

1.4.4.1      Typology of Morgen and Henrion

1.4.4.2      Smithson typology

1.4.4.3      Klir Typology

1.4.5           Why fuzzy set theory (FST)?

1.4.6           Gray Swan: Towards to Fuzzy Psychology

1.4.7           A sensitive birth

1.4.8           Gray world of mind

1.4.9           The Fuzzy logic under psychological view

1.4.10        Why fuzzy logic theory?

1.4.11        Is fuzzy psychology a reasonable field of psychology?

1.4.12        What is Machine Learning

1.4.13        Supervised versus unsupervised algorithms

1.4.14        Difference between artificial intellenge and machine learning

1.4.15        Difference between machine learning and deep learning

1.4.16        Why must psychologists change their view and methods?

1.4.17        Towards to artificial psychology

1.4.18         combine fuzzy and deep machine learning methodology1.4.19        What an artificial psychologist needs

1.4.20        Overview on R software

2              Overview on Mathematical Basis of Fuzzy Set Theory

2.1         History of fuzzy set theory

2.2         Fuzzy set theory versus Classical set theory

2.3         Linguistic variables

2.4         Fuzzy membership functions

2.4.1           Triangular membership function

2.4.2           trapezoidal membership function

2.4.3           Gaussian Membership Functions

2.4.4           Z-shaped membership function

2.5         Fuzzy Set operations

2.5.1           Subset

2.5.2           Intersection

2.5.3           Union

2.5.4           Complement

2.5.5           Set difference

2.6         Membership grade operations

2.6.1           Scalar cardinality

2.6.2           Alpha-cut(a-cut)

2.7         Overview on fuzzy arithmetic

2.8         Fuzzy relationship

2.9         Fuzzy-rules

2.10      Fuzzification and defuzzification Process

2.11      Practical examples using R

3              Fuzzy Inference Systems (FIS)

3.1         Classical statistical inference

3.1.1           Statistical inference

3.1.2           The Holy Grail of P-value

3.1.3           What P-value tells us

3.1.4           What P-value does not tell us

3.2         Fuzzy inference systems

3.2.1           Fuzzy inference

3.2.2           Mamdani-type fuzzy inference system

3.2.3           Single-input single-output Mamdani fuzzy inference system

3.2.4           Two-input single-output Mamdani fuzzy inference system

3.2.5           Weight of input variables

3.2.6           Takagi-Sugeno -type fuzzy inference system

3.2.7           Adaptive neuro-fuzzy inference system(ANFIS)

3.2.8           Intuitionistic fuzzy inference system

3.2.9           Practical examples using R

4              Fuzzy Cognitive Maps(FCM)

4.1         Basic concepts of fuzzy cognitive maps

4.2         Building the fuzzy cognitive maps in psychology

4.3         Combined fuzzy cognitive maps

4.4         Inference using fuzzy cognitive maps

4.5         Practical examples using R

5              Network analysis

5.1         What is a network view in psychology?

5.2         Network psychology

5.3         Fitting the network'

5.4         Network accuracy

5.5         Practical examples using R

6              Association Rules Mining and Associative Classification

6.1         Overview on association rules mining

6.2         Associative Classification

6.3         Association Rules Mining or Associative Classification: It is a question

6.4         Steps for doing the mining association rules

6.5         Practical examples using R

6.6         Which package of R is better?

7              Artificial Neural Network

7.1         When computer imitates neuron function

7.2         Artificial neural network

7.3         Basis of neural network analysis

7.4         Type of artificial neural network

7.5         Bolts of artificial neural network

7.6         Type of artificial neural networks

7.7         Multilayer Perceptron analysis

7.8         Deep Multilayer Perceptron analysis

7.9         Radial basis function network

7.10      Practical examples using R

8              Feature Selection

8.1         Feature selection and its importance in psychology

8.2         Types of feature selection methods

8.2.1           Embedded Methods

8.2.2           Wrapper Methods

8.2.3           Filter Methods

8.3         Feature selection based on genetic algorithm

8.4         Feature selection based on random forest

8.5         Recursive feature selection

8.6         Practical examples using R

9              cluster analysis

9.1         Introduction

9.2         Model-based cluster analysis

9.3         Data-driven cluster analysis

9.4         Determining number of cluster

9.4.1           A hard decision

9.4.2           A practical example for determining number of cluster using 3 algorithms using R

9.5         K-means algorithm

9.6         Fuzzy k-means algorithm

9.7         Practical examples for k-means

9.8         Practical examples for fuzzy k-means

Über Autor(innen)

Hojjatollah Farahani is Assistant Professor at the Tarbiat Modares University (TMU), Iran. He received his Ph.D. from Isfahan University in 2009, and he was a postdoctoral researcher in Fuzzy inference at the Victoria University in Australia (2014-2015), where he started working on Fuzzy Cognitive Maps (FCMs) under supervision of professor Yuan Miao. He is the author or co-author of more than 150 research papers and a reviewer in numerous scientific journals. He has supervised and advised many theses and dissertations in psychological sciences. His research interests and directions include psychometrics, advanced behavioral statistics, fuzzy psychology, artificial intelligence and machine learning algorithms in psychology.                                                                                                                                                      

Marija Blagojevic is Associate Professor at the Faculty of Technical Sciences Cacak, University of Kragujevac, Serbia, at the Department of Information technology. Born in 1984, she obtained her MSc degree in 2007 and PhD degree in technical sciences in 2014. Her current research interests include data mining, artificial neural networks, e-learning, programming, etc.  With fifteen years of experience in teaching and research activities, she is the author or co-author of more than 80 research papers, patents, technical solutions and a reviewer in numerous scientific journals. She is also a reviewer of projects and study programs and a member of partner universities for Tempus and Erasmus projects. She was a member of the organizational and scientific committees of several conferences and a member of the Commission for self-evaluation at the faculty. She was project coordinator for one innovative project in the domain of technology transfer.

Parviz Azadfallah has a PhD in Health Psychology and became qualified in several international academic courses in Neuropsychology and Psychodynamic Psychotherapies. He started his scientific activity at the Psychology Department of Tarbiat Modares University (TMU), Iran in 1999. He conducted many research projects and supervised 45 PhD theses and more than 50 Master dissertations from 1999 to 2023. He is the author or co-author of more than 250 research papers. He is also the author of some books, and his last book, Embodied Ego, uses a developmental approach to explain mind-body integration. He founded the Neuropsychology Laboratory of TMU in 2017. He is also a member of the Cognitive Neuroscience Department at TMU since 2019. Most of his research projects are based on experimental designs. On the other hand, he conducted many projects with the aim of knowledge construction through fundamental qualitative and culture-bound studies.

Peter Watson holds three degrees in Mathematical Statistics including a PhD (Manchester). He has been providing statistical support in various ways to the research at CBSU, the Cognition and Brain Sciences Unit in Cambridge, England (and its predecessor, the Applied Psychology Unit) since 1994 (and prior to that fulfilling a similar role at the MRC Age and Cognitive Performance Research Centre in Manchester, England). He is the co-author of over 100 papers and lectures at the University of Cambridge. He is a statistical referee for several journals including BMJ Open and the Journal of Affective Disorders. He has also been a major contributor of articles to the on-line CBSU statswiki web pages which receive upwards of 100,000 visits annually. He has also been secretary, since 1996, of the Cambridge Statistics Discussion Group and chair and meetings organiser for the SPSS users group (ASSESS) since 2001 and has also been a member of the Clinical Trials Advisory Panel for Alzheimer’s Research UK.                                                                                           

Forogh Esrafilian is Assistant Professor at the Tarbiat Modares University (TMU), Iran. Her interests include psychopathology, cultural and cross-cultural psychology and developmental cognitive psychology.

Sara Saljoughi was born on March 1, 1995. She received her Bachelor's in Electrical engineering from the Iran University of Science and Technology. Afterward, she discovered her intense passion for Cognitive science; as a result, she changed her academic direction and followed her passion. Right now, she is in the final stage of her master's in cognitive psychology and looks forward to continuing her studies in a Ph.D. program. Her research interests include computational neuroscience, connectivity, biomarkers, and brain networks. She is keen to discover brain networks and biomarkers for psychiatric and mental disorders by ML approaches.