Semester: 7
Elective
ECTS: 6
Hours per week: 4
Professor: T.B.D.
Teaching style: Lectures and exercises, Face to face
Grading: Theory (exams, short test) (70%), Laboratory (30%)
Activity | Workload |
---|---|
Lectures | 26 |
Tutorial Exercises | 0 |
Laboratory Exercises | 26 |
Computational Exercises | 0 |
Personal study | 98 |
Course total | 150 |
The specific course is an introduction to basic concepts of Fuzzy Logic (FL) Systems and Artificial Neuro-Fuzzy Inference Systems. This course is also a technological analysis on issues, problems and applications related to modeling techniques based on artificial intelligence.
The aim of the course is the understanding of the basic elements of FL Systems and ANNs in issues related to applications of modeling and forecasting for Engineers.
Upon completion of the course, students will be able to:
To understand the basic characteristics of the theory and methodologies of the intelligent systems.
Distinguish when and why we apply intelligent techniques to a real system.
Utilize tools and techniques for the development of intelligent systems.
Model complex systems when it is difficult to develop a mathematical model.
To be able to work with their fellow students to create and present, both individually and in groups, a case study from its initial stages to its final evaluation and proposal for solutions.
Be able to work with their fellow students, to create and present both at individual and group level a case study from its initial stages up to the final evaluation and finally to be able to propose new ideas and solutions.
More specifically, students will be able to:
Ability to search, analyze and synthesize data and information, using the necessary internet technologies and bibliographic research and networking.
Ability to make decisions, through the consideration of solutions and options for elaboration of the assigned laboratory tasks and exercises.
Ability to work independently, through the preparation of individually performed tasks and exercises.
Ability for group work, through the elaboration of group work and exercises.
Ability to plan, manage and evaluate projects, through undertaking and elaborating completed work (project).
Ability to produce new research ideas and inductive thinking while designing systems operating in dynamic environments.
Decision making
Individual project
Teamwork
Introduction – Crisp Sets, Fuzzy Sets, Basic Features, Boolean Algebra
Fuzzy Set Algebra – Properties of α-Sections, Fuzzy Relationships, Projection of Fuzzy Relations, Extension Principle
Fuzzy Arithmetics – Fuzzy numbers, Interval arithmetic, Fuzzy arithmetic operations,
LR-Fuzzy Numbers, Triangular and Trapezoidal Fuzzy Numbers
Introduction to Fuzzy Systems – Characteristics and Function, Fuzzy Inference Machines, Fuzzification methods, Defuzzification methods
Fuzzy logic controllers – Fuzzy control methodology
Fuzzy methods in decision making
Applications using MATLAB for fuzzy arithmetic operations and fuzzy control systems.
Artificial Neural Networks: Basic Artificial Neuron Representation Models, Types of Activation Functions, Basic Architectural Structures of Neural Networks. Basic algorithms of the learning process.
Basic model of Artificial Neuro-Fuzzy Inference System (structure, layers, optimization methods for training)
Federated learning and its applications in industry 4.0
Machine learning in the shipping industry
Space design using AI algorithms
Pre-earthquake survey of structures using AI
Earthquake mitigation using neural networks
Calculation of dynamic characteristic of structures
Calculation of mechanical properties of structural elements using Neural Networks
Laboratory
The workshop includes the following laboratory exercises:
Use of Matlab Fuzzy Inference System (Fuzzy Logic Toolbox) for modeling fuzzy systems.
Use of Matlab Adaptive Neuro-Fuzzy Inference System (ANFIS) for the development and training data for modeling/predicting results.
Application and use of Fuzzy Logic Toolbox for the navigation safety of fishing boats in the marine sector.
Application and use of Fuzzy Logic Toolbox for motion prediction and risk assessment of intelligent vehicles in robotics sector.
Application and use of Fuzzy Logic Toolbox for the ship weather routing in the marine sector.
Application and use of Fuzzy Logic Toolbox for autonomous car-driving in the automotive sector.
Application and use of ANFIS for real-time vessel behavior prediction in the marine sector.
Application and use of the vehicle routing problem based on fuzzy concepts in the transportation sector.
Application and use of the assembly line balancing problem based on fuzzy concepts in the manufacturing sector.
Applications of AI in Architecture: Space design using algorithms
Applications of AI in pre-earthquake survey of structures
Applications of control systems with neural network for earthquake mitigation
Applications of of AI in calculation of dynamic characteristic of structures based on AI approach
Applications of Neural networks in calculation of mechanical properties of structural elements
Α Course in Fuzzy Systems and Control», L.X. Wang, , Prentice Hall, 1997.
Neuro-Fuzzy and Soft Computing, J. Jang, C. Sun, E. Mizutani, , Prentice Hall, 1997.
Fuzzy Logic with Engineering Applications, T. Ross, , MacGraw-Hill, NY, 1995.
Fuzzy Engineering», B. Kosko, Prentice Hall, 1997.
«Fuzzy and Neural Approaches in Engineering, L. Tsoukalas, R. Uhrig, , MATLAB Supplement, John Wiley & Sons, 1997.
«Soft Computing and Intelligent Systems Design, F. Karray and C. De Silva, , Addison Wesley, 2004.
«An introduction to fuzzy control, D. Driankov, H Hellendoorn, M. Reinfrank Springer 1995.
The specific course is an introduction to basic concepts of Fuzzy Logic (FL) Systems and Artificial Neuro-Fuzzy Inference Systems. This course is also a technological analysis on issues, problems and applications related to modeling techniques based on artificial intelligence.
The aim of the course is the understanding of the basic elements of FL Systems and ANNs in issues related to applications of modeling and forecasting for Engineers.
Upon completion of the course, students will be able to:
To understand the basic characteristics of the theory and methodologies of the intelligent systems.
Distinguish when and why we apply intelligent techniques to a real system.
Utilize tools and techniques for the development of intelligent systems.
Model complex systems when it is difficult to develop a mathematical model.
To be able to work with their fellow students to create and present, both individually and in groups, a case study from its initial stages to its final evaluation and proposal for solutions.
Be able to work with their fellow students, to create and present both at individual and group level a case study from its initial stages up to the final evaluation and finally to be able to propose new ideas and solutions.
More specifically, students will be able to:
Ability to search, analyze and synthesize data and information, using the necessary internet technologies and bibliographic research and networking.
Ability to make decisions, through the consideration of solutions and options for elaboration of the assigned laboratory tasks and exercises.
Ability to work independently, through the preparation of individually performed tasks and exercises.
Ability for group work, through the elaboration of group work and exercises.
Ability to plan, manage and evaluate projects, through undertaking and elaborating completed work (project).
Ability to produce new research ideas and inductive thinking while designing systems operating in dynamic environments.
Decision making
Individual project
Teamwork
Introduction – Crisp Sets, Fuzzy Sets, Basic Features, Boolean Algebra
Fuzzy Set Algebra – Properties of α-Sections, Fuzzy Relationships, Projection of Fuzzy Relations, Extension Principle
Fuzzy Arithmetics – Fuzzy numbers, Interval arithmetic, Fuzzy arithmetic operations,
LR-Fuzzy Numbers, Triangular and Trapezoidal Fuzzy Numbers
Introduction to Fuzzy Systems – Characteristics and Function, Fuzzy Inference Machines, Fuzzification methods, Defuzzification methods
Fuzzy logic controllers – Fuzzy control methodology
Fuzzy methods in decision making
Applications using MATLAB for fuzzy arithmetic operations and fuzzy control systems.
Artificial Neural Networks: Basic Artificial Neuron Representation Models, Types of Activation Functions, Basic Architectural Structures of Neural Networks. Basic algorithms of the learning process.
Basic model of Artificial Neuro-Fuzzy Inference System (structure, layers, optimization methods for training)
Federated learning and its applications in industry 4.0
Machine learning in the shipping industry
Space design using AI algorithms
Pre-earthquake survey of structures using AI
Earthquake mitigation using neural networks
Calculation of dynamic characteristic of structures
Calculation of mechanical properties of structural elements using Neural Networks
Laboratory
The workshop includes the following laboratory exercises:
Use of Matlab Fuzzy Inference System (Fuzzy Logic Toolbox) for modeling fuzzy systems.
Use of Matlab Adaptive Neuro-Fuzzy Inference System (ANFIS) for the development and training data for modeling/predicting results.
Application and use of Fuzzy Logic Toolbox for the navigation safety of fishing boats in the marine sector.
Application and use of Fuzzy Logic Toolbox for motion prediction and risk assessment of intelligent vehicles in robotics sector.
Application and use of Fuzzy Logic Toolbox for the ship weather routing in the marine sector.
Application and use of Fuzzy Logic Toolbox for autonomous car-driving in the automotive sector.
Application and use of ANFIS for real-time vessel behavior prediction in the marine sector.
Application and use of the vehicle routing problem based on fuzzy concepts in the transportation sector.
Application and use of the assembly line balancing problem based on fuzzy concepts in the manufacturing sector.
Applications of AI in Architecture: Space design using algorithms
Applications of AI in pre-earthquake survey of structures
Applications of control systems with neural network for earthquake mitigation
Applications of of AI in calculation of dynamic characteristic of structures based on AI approach
Applications of Neural networks in calculation of mechanical properties of structural elements
Α Course in Fuzzy Systems and Control», L.X. Wang, , Prentice Hall, 1997.
Neuro-Fuzzy and Soft Computing, J. Jang, C. Sun, E. Mizutani, , Prentice Hall, 1997.
Fuzzy Logic with Engineering Applications, T. Ross, , MacGraw-Hill, NY, 1995.
Fuzzy Engineering», B. Kosko, Prentice Hall, 1997.
«Fuzzy and Neural Approaches in Engineering, L. Tsoukalas, R. Uhrig, , MATLAB Supplement, John Wiley & Sons, 1997.
«Soft Computing and Intelligent Systems Design, F. Karray and C. De Silva, , Addison Wesley, 2004.
«An introduction to fuzzy control, D. Driankov, H Hellendoorn, M. Reinfrank Springer 1995.