Embedded Files
PhD and MSc recent courses teached by Prof. Joberto Martins.
Future Internet and Smart City with OpenFlow and Machine Learning 2021
Internet and networks are evolving and expanding their utilization dramatically. New paradigms, new protocols, new intelligent solutions and large scale complex systems are emerging on various areas of our daily life. Researchers and engineers need to understand the current network evolution trends and to know what relevant new technologies are involved.
This course presents the network evolution scenario and presents the SDN/OpenFlow technology in the context of the actual and challenging Smart City scenario. Smart City characteristics, project issues and development challenges are addressed. SDN/ OpenFlow with some basic Machine Learning tools are applied to Smart City projects to allow a comprehension on how new technologies can improve system development and highlight their potential..
This course presents the network evolution scenario and presents the SDN/OpenFlow technology in the context of the actual and challenging Smart City scenario. Smart City characteristics, project issues and development challenges are addressed. SDN/ OpenFlow with some basic Machine Learning tools are applied to Smart City projects to allow a comprehension on how new technologies can improve system development and highlight their potential..
- Hochschule für Technik und Wirtschaft des Saarlandes - HTW - 2021; and- Salvador University - UNIFACS - 2021
Course Focus:
This course focuses on presenting the current network architecture and systems evolutionary trends and explores the Software-Defined Networking (SDN) new paradigm as a solution to develop new systems.In technical terms, the course elaborates on two main topics:-- Software-Defined Networks (SDN) with OpenFlow; and-- Smart City projects as an application scenario.
A typical Smart City project has most of the mentioned Future Internet requirements that engineers have to solve: heterogeneity, largely distributed, high volume of data, multiple networks involved and so on. This course will present firstly how to use SDN/ OpenFlow to develop a new, efficient and programmable communications solution (Communication Level) and, secondly, how new techniques like artificial intelligence can be used to allocate resources in a smart city context (Application Level).
It will explore incrementally the following aspects of system and application development:-- How networks can possibly evolve with SDN and without SDN;-- How SDN supports routing, virtualization and scalability capabilities necessary on current and future systems;-- What are the Smart City issues and requirements for system development;-- How can SDN with resource allocation, cognitive management and artificial intelligence foster new systems development for Smart City; and-- Presenting practical "use case" for Smart City project development.
Course Motivation:
The motivation to follow this course comes from the fact that engineers need to understand what are the main problems that actual IP-based solutions do have, what are the current trends on system development and what are the new technologies to use.
Why to follow this course?
The course is intended for PhD, master and graduate students, network engineers and developers involved with network research, design and implementation. Some basic knowledge of IP and networking technologies is required.
The motivation to follow this course comes from the fact that engineers need to understand what are the main problems that actual IP-based solutions do have, what are the current trends on system development and what are the new technologies to use.
Why to follow this course?
- To learn SDN/OpenFlow basics;
- To experiment SDN/OpenFlow network programming with MiniNet;
- To acquire expertise on Smart City project issues and requirements; and
- To perceive the use of Machine Learning techniques for cognitive management using SDN/OpenFlow as the basic network programming paradigm.
The course is intended for PhD, master and graduate students, network engineers and developers involved with network research, design and implementation. Some basic knowledge of IP and networking technologies is required.
Machine Learning: Case-based Reasoning, Reinforcement Learning and Applications 2020 and 2021
Artificial intelligence (AI), as technical topic, has been active for decades but it, currently, is indeed a brand new trend in Computer Science with diverse and interesting application areas. This course has as its main objective to present a theoretical/ practical introduction to Case-based Reasoning (CBR) and Reinforcement Learning (RL) that are complementary and extensively used techniques in the AI domain.
- Salvador University - UNIFACS - 2020
Course Focus:
This course focuses on presenting some current and frequently used Machine Learning (ML) techniques, ML systems evolutionary trends and explores the ML new paradigm as a solution to develop new applications and systems .In technical terms, the course elaborates on the following main topics:
- Artificial intelligence current status, main techniques and evolutionary trends;
- Case-based Reasoning (CBR) and Reinforcement Learning (RL) machine learning techniques; and
- Use case and ML application.
The course will explore incrementally the following CBR and RL aspects and application development:
- How systems and networks can possibly be implemented and optimized with Machine Learning techniques;
- How ML techniques supports current and future systems;
- How can ML with resource allocation and cognitive management foster new systems development for the network communication application scenario; and
- Presenting practical use case for ML project development.
Course Motivation:
The motivation to follow this course comes from the fact that computer scientists and engineers need to understand what are the suitable machine learning problems that are complex and difficult to model based on logic programming. In addition to that, it is necessary to know what are the current trends on machine learning based development, to identify solutions and to understand the new technologies to be used.
Why to follow this course?
The course is intended for PhD, master and graduate students, network engineers and developers involved with network research, design and implementation. Some basic knowledge of IP and networking technologies is required.
The motivation to follow this course comes from the fact that computer scientists and engineers need to understand what are the suitable machine learning problems that are complex and difficult to model based on logic programming. In addition to that, it is necessary to know what are the current trends on machine learning based development, to identify solutions and to understand the new technologies to be used.
Why to follow this course?
- To learn Machine Learning basics;
- To experiment Machine Learning programming with tools;
- To acquire expertise on Machine Learning project issues and requirements; and
- To perceive the use of Artificial Intelligence (AI) techniques for applications.
The course is intended for PhD, master and graduate students, network engineers and developers involved with network research, design and implementation. Some basic knowledge of IP and networking technologies is required.
Page updated
Google Sites
Report abuse