KSU, Marietta, GA, USA | December 19-21, 2022

invited speakers

Title: Anticipatory Radio Resource Management for 5G Networks and Beyond

Hossam Hassanein
- Prof.,
  University of Alberta
  Kingston, Ontario, Canada
5G wireless networks have brought about a technological transformation in modern societies by providing an ultra-reliable high-speed communications infrastructure that will serve billions of devices, machines and vehicles. These devices will contribute massive amounts of data that will need to be pipelined over future 5G networks under the umbrella of future smart cities, connected autonomous cars, and IoT applications. The complexity of 5G networks will hence be unprecedented, due to the very diverse applications, ultra-low latency requirements for critical vehicle communication, growing demand for high positioning accuracy for location-based services, and dense, heterogeneous architectures.

Hossam Hassanein, Ph.D.
In this talk, we address our efforts towards developing a smart management solution suite for future 5G networks based on innovative machine learning and big data analytics techniques. In particular, we discuss data-driven radio resource management functions that are mobility- and context-aware. In this domain we discuss the design of a predictive resource allocator that leverages individual user-level mobility information to opportunistically plan data transmissions in advance. We also discuss how to autoconfigure 5G mobility management network settings of cell selection and handover. The solutions will enable networks to be self-diagnosing and self-organizing and will enhance network capacity and user service while reducing capital and operating expenditures.
Speaker Biography:
Hossam Hassanein is a leading authority in the areas of broadband, wireless and mobile networks architecture, protocols, control and performance evaluation. His record spans more than 600 publications in journals, conferences and book chapters, in addition to numerous keynotes and plenary talks in flagship venues. Dr. Hassanein has received several recognition and best paper awards at top international conferences. He is the founder and director of the Telecommunications Research Lab (TRL) at Queen's University School of Computing, with extensive international academic and industrial collaborations. He is the recipient of the 2016 IEEE Communications Society Communications Software Technical Achievement Award for outstanding contributions to routing and deployment planning algorithms in wireless sensor networks, and the 2020 IEEE IoT, Ad Hoc and Sensor Networks Technical Achievement and Recognition Award for significant contributions to technological advancement of the Internet of Things, ad hoc networks and sensing systems. Dr. Hassanein is a fellow of the IEEE, and is a former chair of the IEEE Communication Society Technical Committee on Ad hoc and Sensor Networks (TC AHSN). He is an IEEE Communications Society Distinguished Speaker (Distinguished Lecturer 2008-2010).

Title: Machine Learning Driven Signal Demodulation

Satyam Agarwal
- EE, Indian Institute of Technology Ropar
  Ropar, Punjab, India
Conventional demodulation schemes suffer from low bit error rate caused due to signal impairment resulting from non-ideal components (oscillators, filters, product multipliers) used for signal transmission and reception as well as channel impairments. These signal distortions are time-varying which the conventional schemes are unable to detect and correct. In this talk, we will delve into the application of machine learning to understand how it can help alleviate some of the highlighted issues and provide a better bit detection performance. A transfer learning-based bit detection scheme will be discussed which learns the transmitter/receiver and channel state from the pilot symbols and quickly adapts its deep learning model to detect the bits with high accuracy. We present both the simulations and experimental results and highlight some of the trade-offs in the proposed scheme.

Satyam Agarwal, Ph.D.

Speaker Biography:
Dr. Satyam Agarwal received the Ph.D. degree in electrical engineering from IIT Delhi in 2016. He is currently an Assistant Professor with the Department of Electrical Engineering, IIT Ropar, India. Prior to this, he was an Assistant Professor with IIT Guwahati. In 2017, he was a Post-Doctoral Researcher with Politecnico di Torino, Turin, Italy. He is the recipient of the DST-INSPIRE faculty award. His research interests are in the wide areas of wireless communication networks, including next-generation networks, 5G networks and architecture, and air-borne networks. Research interest are in the broad areas of Wireless communications and networks.

Title: The solar cell architectures, cost and reliability for affordable and sustained photovoltaic electricity

Abasifreke (Aba) Ebong
- Prof.,
  Department of Electrical & Computer Engineering
  The University of North Carolina at Charlotte
The efficiency, cost and reliability of a solar cell can impact the affordability and sustained photovoltaic electricity. The efficiency or the power output from a solar cell is a function of the architecture, which can output different open circuit voltage (VOC), the short circuit current (ISC) and the fill factor (FF) that are pertinent for high efficiency. The prevailing architectures include: PERC, PERT, PERL, TopCon, and SHJ, for crystalline silicon solar cells, because of the effectiveness in surface passivation that results in high electrical output parameters. Each architecture in today’s commercial solar cell uses the Ag metal paste for its metallization, thus the cost of manufacturing varies as the cost of Ag metal powder. The reliability of each architecture is important to guarantee maximum and continuous power output at the module level in the field. For a sustained photovoltaic electricity, reliable maximum-power output must be guaranteed for a long term at a competitive cost. This work reviews the different technologies (architectures) of crystalline silicon solar cells, cost and reliability to ascertain the longevity of the photovoltaic electricity.

Abasifreke (Aba) Ebong, Ph.D.

Speaker Biography:
Aba Ebong received his Ph.D. in Electrical and Computer Engineering from the University of New South Wales, Australia in 1995. His Ph.D. dissertation was on cost-effective double-sided buried contact silicon solar cells. After completing the Ph.D. program in 1995, he joined Samsung Electronics in South Korea as a Postdoctoral Fellow. His focus was on training and implementation of the buried contact technology transferred from the University of New South Wales. In September 1997, he joined the University Center of Excellence for Photovoltaic Research and Education (UCEP), Georgia Tech., Atlanta, as a Research Faculty. At UCEP, he worked on the development, design, modeling, fabrication, and characterization of low-cost, high-efficiency belt line multicrystalline, Cz, and Fz silicon solar cells. In 2001 he joined GE Global Research as Electrical Engineer, working on Solid State Lighting (LED-light emitting diodes) based on III-V semiconductors. While at GE, he developed current spreading model for light emitting diodes, which enhanced the evaluations of several conceptual designs without actually fabricating them. In 2004, he returned to the UCEP at Georgia Tech as the Assistant Director of the center, responsible for sponsored research in crystalline and amorphous silicon solar cells. Dr Ebong joined the Faculty of the University of North Carolina at Charlotte as a Professor in February 2011. Having worked in close collaboration with several companies including; equipment, front silver screen-printed pastes, dielectric and silicon wafers to develop belt machine for contact co-firing, inline diffusion, and high quality front silver pastes, Dr Ebong brings more than 22 years’ experience to his current position. He has published over 160 papers in the field of Photovoltaics. His current research interest include: high throughput, low-cost and high efficiency silicon solar cells based on comprehension of screen-printed contacts formation to homogeneous emitters with high sheet resistances; Development of low-cost manufacturable high efficiency solar cells with alternative to screen-printed contacts; Electrochemistry and Device Physics. He is also interested in solid state lighting “sunlight to light”, an area where solar cell and LED can be merged.

Title: Pervasive Glucose Monitoring: A Non-Invasive Approach based on Near-Infrared Spectroscopy

Maria Valero de Clemente
- Dir.,
  Internet of Things as Service Research Group
  College of Computing and Software Engineering / Information Technology
  Kennesaw State University
With more than 12% of Americans living with diabetes and more than 30% suffering from metabolic syndrome, the United States is facing the need for more technology for easy and non-invasive blood glucose monitoring. The current pervasive technologies can be leveraged as the foundation for new sensor devices and intelligent models to monitor and manage glucose. This paper presents an approach for monitoring glucose concentration with a pervasive device. Using a powerful machine-learning model, the device captures and processes spectroscopy images of a body’s extremities.

Maria Valero de Clemente, Ph.D.
The spectroscopy or spectral image is based on the theory of light intensity data from the spectrum. Using light absorption, the proposed sensor executes a model that permits glucose estimation. The procedure is noninvasive, as no blood or needles are required. The device also pairs the information to a mobile application for real-time monitoring. Preliminary studies show an accuracy of 90.78% compared with traditional blood glucose estimation.
Speaker Biography:
Dr. Valero is an assistant professor in the College of Computing and Software Engineering, Department of Information Technology at Kennesaw State University (KSU). She received her Ph.D. in Electrical and Computer Engineering at the University of Georgia. She was an associate professor at the University of Tachira (Venezuela) from 2004 to 2015. Dr. Valero is the Director of the IoT as Service Research Group at the College of Computing and Software Engineering. Her research group investigates the use of IoT and sensor devices as a service for healthcare and cybersecurity. In the healthcare path, Dr. Valero's group is focused on implementing signal processing and advanced machine learning techniques to understand sensorial data for remote and non-invasively monitoring of the human body and certain diseases like diabetes, heart rate complications, and brain issues. She has been the lead PI of NSF and NIH awards related to device technologies for healthcare.