ORACLES: netwOrks, Robotics, mAChine Learning, and fuzzy systEms labS
1. Computer Networks (ΜΚ19-Η)
6th Semester (3rd Year)
5 ECTS, 4 hours per week
Goals:
The course is an introduction to the technology of data networks. Aims to familiarize students with the issues of packet routing within networks with an emphasis on Internet routing. The course also provides a first introduction to new network technologies, security, and network management issues. Finally, it brings students in touch with current cutting-edge issues in network technology, as well as network management and security issues in networks. After attending the course students should:
- Know and be able to apply the principles of structured cabling.
- Be familiar with the operation of network technologies such as Ethernet type networks.
- Be familiar with the basic principles of the Internet.
- Have a good understanding of the subject matter and understand the usefulness and operation of routing protocols.
- Understand the basic concepts of network management and security.
- Have a good understanding of the subject matter and understand the usefulness and implementation of network management systems.
- Be familiar with basic security issues arising from the connection of computers to networks and the basic principles of how to deal with them.
- Understand technological developments in a rapidly developing field.
- Be able to apply this knowledge in a real network environment.
Theory (3 hours per week) :
Introduction to Computer Networks and World Wide Web. Protocols, packets transferring, Internet history, applications. Http, FTP, DNS, sockets. TCP, UDP, IP. Network security, wireless security, firewalls, VPNs, DDOS.
Lab (1 hour per week) :
Wireshark, analysing protocols, packet addressing, Ethernet and ARP. Encapsulation and TCP/IP protocol stack, Ping, traceroute, RTT time, hop count, TTL, DNS, Fragmentation. ICMP, TCP Dump, TCP Sender Window, TELNET, FTP and TFTP, SMTP, DHCP. OSI, Switching, Multiplexing Synchronization, baseband/passband transmission, ADSL, ATM. Socket Programming, HyperText Transfer Protocol.
2. Robotics (Ε4)
7th Semester (4th Year)
5 ECTS, 4 hours per week
Goals:
The familiarization of the student with the basic concepts of
robotics with particular emphasis on solving the basic concepts of robotics
kinematic problems (position and velocity)
of robotic arms. After the end of the course, the student
the student will have the ability to understand basic
concepts of robotics, to perform kinematics, to understand robotics concepts, and to
position, velocity, and acceleration analysis of robotic arms
arms, design controllers in the form of introductory
control techniques for robotic arms and to design controllers with an introduction to robotic arm control
robotic arm trajectories.
Theory (3 hours per week) :
Introduction to Robotics (History, Modern and Future Technology). Structure and classification of robots. The components of robots, manipulation, sensors, control, control architectures, representation, behavior, locomotion and navigation, ensemble robotics, learning, and the future and ethical implications of robotics. Kinematic (Forward and Inverse) Robot Arm Analysis. Robotic Arm Wheel Design. Static Robot Analysis (Jacobian Matrices and Force and Torque Transformations). Dynamic Analysis of Robots (Newton-Euler and Lagrange Models). Basic Robot Control Techniques (PID, Decentralized Control).
Lab (1 hour per week) :
Simulation in Matlab & Simulink.
In the practical part, we will apply robot interaction schemes in different environments (education and home use) using simulations and real robots - Robotic arms.
Teaching with lecture demonstrations and examples on PC.
3. Machine Learning (ΕΥΗ6)
8th Semester (4th Year)
5 ECTS, 4 hours per week
Goals:
The aim of the course is for the student to acquire a comprehensive and as complete as possible view on the field of Machine Learning and Pattern Recognition, which is currently considered one of the most important for the field of Electrical/Computer Engineering.
Key elements and problems of learning theory such as Neural Networks, pattern recognition, value prediction and clustering are given. The necessary mathematical background as well as the basic programming tools for the implementation and application of the relevant algorithms are given. Upon successful completion of the course the student will be able to:
- Know the most basic machine learning methods and their fields of application.
- Understand the basic types of problems to which machine learning can be applied.
- Analyse simple learning problems and apply appropriate methods to solve them.
- Implement basic learning models with appropriate programming tools.
- Evaluate the performance of learning models.
Theory (3 hours per week) :
Present a complete view of the
field of Pattern Recognition - Machine Learning.
In addition to the most popular models and
Machine Learning methods (supervised and unsupervised), the basic elements of the theory are also presented
so that the student is aware of how they work
how these models work, what are the real possibilities
and what their limitations are. It also gives an overview of the
extensive reference to the applications of Recognition
Pattern-Machine Learning, e.g.
Big Data problems/applications,
computer vision, image analysis, recognition
face recognition, character recognition, voice analysis,
natural language processing, sentiment analysis;
opinion extraction, robotics, bioinformatics, etc.
Lab (1 hour per week) :
Τhe course will be accompanied by
practical exercises of a laboratory nature so that the
The student will have a better understanding of the concepts
developed in the theoretical part. These exercises will
involve the use of appropriate software tools
(Matlab and Python), with emphasis on open-source tools.
software that implements Recognition models
Pattern-Machine Learning in different scenarios;
use cases.
4. Fuzzy Systems (ΕΥΗ4)
9th Semester (5th Year)
5 ECTS, 4 hours per week
Goals:
The basic aim of the course is for students to
acquire a good level of knowledge about the fundamental
principles and models of fuzzy logic and to
understand the operation of fuzzy logic systems
logic. The theory of fuzzy logic offers a
a different way of dealing with real-world
systems without mathematical standardization and the
students have the opportunity to study complex
systems that are difficult to mathematically
their mathematical standardization. In the laboratory part the
the first contact of the student with the development of intelligent
techniques in MATLAB environment. The familiarization with the
techniques of intelligent control give the student
the ability to develop and design systems
control systems.
Theory (3 hours per week) :
Teaching with lectures-presentations and
examples on the computer.
Features of Computational Intelligence: Empirical, Fuzzy, and Neural Systems.
Fuzzy Knowledge. Elements of Fuzzy Logic. Fuzzy Inference. Fuzzy logic-based control techniques. Fuzzy controllers and rule controllers, development of fuzzy control models. Fuzzy Cognitive Networks.
Training algorithms of fuzzy systems, neural networks, adaptive neuro-fuzzy systems, and applications of intelligent techniques in automatic control.
Fuzzy and neural control architectures, data-based control, model building, and parameter tuning. Robust and intelligent control (neural and fuzzy).
Applications in the following scientific areas: robotics, automatic control systems, energy, environment, medicine, economics, transport, energy, environment, medicine, economics. Fault detection in industrial systems.
Simulation in Matlab & Simulink.
Lab (1 hour per week) :
Teaching with lectures-presentations and
examples on the computer.
Use of Matlab & Simulink, Python programming language.