CS/EE Networking Seminar
Date: Fri. July 8, 2:30-3:30pm
Location: EE Conference Room, Mudd 1300
Unlicensed Spectrum Forecasting: An Interference Umbrella based on Channel Analysis and Machine Learning
Dr. Kostas Chounos, Department of Electrical and Computer Engineering (ECE), University of Thessaly, Greece
Abstract: Nowadays, wireless dense networks (Wi-Fi) are widely used in order to serve the ever-increasing users' data demands. However, the enormous number of wireless devices emitting at the unlicensed parts of the spectrum simultaneously, seriously reduce the opportunities for efficient transmissions. In this presentation, a novel framework for predicting future interference levels for IEEE 802.11 networks is presented. At the heart of the framework lies a modelling mechanism which is able to estimate and determine in real-time, the over-the-air performance that each network user will receive over an IEEE 802.11 link, when considering and combining multiple wireless metrics and without requiring a network association (Wi-Fi AP-STA) to be performed. On top of the solution, a Machine Learning approach is integrated, in order to project the real-time predictions to long-term predictions in the future (2-hour interval). Additionally, the framework applies a self-correcting mechanism for the predictions, by extracting short-term predictions and accurate throughput calculations, when the current channel conditions largely differ from the long-term predictions. The proposed framework covers comprehensively the cases of interference created by either 802.11 or non 802.11 devices, which may occur at the target or at any overlapping wireless channel. Finally, extensive testbed experimentation proves the framework's proper functionality and accuracy, under the cases of both Indoor (controlled interference) and Outdoor (uncontrolled massive interference) environments.
Bio: Kostas Chounos is a Postdoctoral Researcher with the Department of Electrical and Computer Engineering (ECE), University of Thessaly, Greece. He received his bachelor degree in applied informatics engineering from the Technological Educational Institute of Crete, Heraklion, Greece, in 2010. Furthermore, he holds a master's degree (2014) and a Ph.D. (2021), in science and technology of computers and telecommunications engineering both from the University of Thessaly (ECE). Since 2013, he has been participating in several national and EU-funded research projects with the University of Thessaly. His research interests lie primarily in the areas of Wireless Networks, Cognitive Radio Networks, Interference Mitigation and Wireless Resource Allocation.
Design and implementation of Unmanned Ground Vehicles with autonomous and mixed reality features
Dimitrios Dallas and Emmanouil Maroulis, Department of Electrical and Computer Engineering (ECE), University of Thessaly, Greece
Abstract: Unmanned Ground Vehicles (UGVs), for both autonomous and teleoperated systems are well researched nowadays, as they can deliver challenging tasks. Algorithms for autonomous navigation like SLAM (Simultaneous Localization And Mapping), help a robot to understand its environment and recognize itself in it. There, robust sensors like cameras are mostly prefered while Visual SLAM is a common technique that most autonomous robots use nowadays. Additionally, new teleoperation approaches focus on the Human Robot Interface (HRI) and user experience. Technologies like spherical videos and Virtual Reality (VR) can provide immersive and interactive control of a UGV. In this context, a custom four-wheeled rover was developed consisting of two cameras, a 360 degrees camera and an RGB-D camera. The developed system is able to do SLAM and autonomously navigate in dynamic and feature-less environments without getting lost. Meanwhile, a teleoperation mechanism was also implemented, which includes spherical video navigation of the 360 degrees live-stream through a VR headset, giving the user real-time experience of the environment. Finally, a scenario in which the rover can autonomously find its destination based on the RSSI metric, is also showcased.
Dimitrios Dallas is a postgraduate researcher and M.Eng. candidate with the Department of Electrical and Computer Engineering (ECE), University of Thessaly. He holds an integrated M.Sc. degree, in Electrical and Computer Engineering from the University of Thessaly, which he obtained in November 2021. Since 2020, he has been participating as a research engineer in nationally and EU-funded projects with the Telecommunications and Networks laboratory of University of Thessaly. His primary interests in research lie in the technologies of Wireless Networks, Virtual/Mixed Reality and video streaming.
Emmanouil Maroulis is an M.Eng. candidate and researcher with the Department of Electrical and Computer Engineering (ECE), University of Thessaly. He received his 5-year diploma (integrated M.Sc.) in Electrical and Computer Engineering from the University of Thessaly, Volos, Greece, in 2021. Currently, he is a member of the Telecommunications and Networks laboratory of the University of Thessaly, where he works on embedded systems, Robotics and Wireless Networks. Most of his research is focused on autonomous navigation and drone operations.
Host: Prof. Gil Zussman