IEEE Green Energy and Smart Systems Conference
Long Beach, CA


Deep Learning with MATLAB

Speaker: Aycan Hacioglu

Deep learning can achieve state-of-the-art accuracy for image segmentation and classification, speech recognition and enhancement, predictive maintenance, and many other domains. This machine learning technique has been adopted across many different industries, including automated driving, aerospace design, medical diagnostics, industrial automation, energy forecasting, and robotics. This session will feature industry examples, a deep learning workflow overview, and an update on the latest Artificial Intelligence capabilities available in MATLAB that help overcome common implementation challenges.

Highlights include:

·       Managing, automated labeling, and augmenting large data sets (images, signals, text, etc.)

·       Utilizing intuitive interfaces to easily create, visualize, analyze, and train networks or manage multiple experiments

·       Leveraging pre-trained models (e.g. GoogLeNet and ResNet) and imported models from Keras-TensorFlow, Caffe, and the ONNX Model format for transfer learning

Speaker Bio:

Aycan Hacioglu is a Customer Success Engineer at MathWorks. She has a BS in Chemical Engineering from Bogazici University, Turkey and a jointly awarded Ph.D. in Chemical Engineering from the University of Florida and Universite Lille1-Sciences and Technologies, France. Before joining MathWorks, she was an Assistant Teaching Professor at the Chemical Engineering Department of the University of Missouri for 3.5 years. She extensively used MATLAB for fluid dynamics and mass transfer simulations. She is experienced in mathematical modeling, process simulations, numerical methods and perturbation theory. She also integrated MATLAB to separation processes and transport phenomena courses she taught. She is excited to share her experience and passion to use MathWorks products in academia.

Learning Dynamics by Smart Systems

Speaker: Hsiao-Chun Wu, Ph. D., Professor of Electrical and Computer Engineering, Louisiana State University, USA

How to construct a dynamic system has been appealing to researchers in physics, applied mathematics, computer science, and engineering since it can facilitate system identification, trajectory tracking, and time series forecast. In recent years, advanced smart systems capable of identifying dynamics inherent in the observed data are in high demand as they can enable the machine intelligence for predicting and detecting human behaviors and environmental evolution. According to our recent studies, the time series can be transformed into critical homological structures and/or features such that robust machine learning can be established using the homological analysis, especially for classifying, detecting, and predicting object motions, human behaviors, and fundamental characteristics in time varying (dynamic) signals. The conventional statistical signal processing and machine learning approaches are often under the unrealistic assumption of i.i.d. (statistically independently and identically distributed) data and thus the dynamics across data samples are not allowed. Based on the aforementioned new machine learning paradigm, it is possible to convert any non i.i.d. time series resulting from a Markov process to a neat geometric structure so the detection. prediction, and classification can be accurately fulfilled. In this talk, the mathematical framework and algorithms of the advanced homological analysis to learn dynamics by smart systems will be introduced and then the corresponding effectiveness on several practical applications will be demonstrated.

Speaker Bio

Hsiao-Chun Wu graduated from University of Florida in 1999 with a Ph. D. degree in Electrical and Computer Engineering, where he started to dedicate research on Signal Processing under the guidance of Dr. Jose C. Principe. Since March of 1999, he had joined Motorola Personal Communications Sector research labs and gotten involved with the ongoing research for Motorola VR Lite speech recognition software. His research in Motorola included novel robust speech detection and enhancement algorithms in a wide variety of background noise. In January of 2001, he joined the faculty at the Department of Electrical and Computer Engineering, Louisiana State University as a tenure-track assistant professor; he became a tenured associate professor in 2007. In July to August 2007, Dr. Wu was a visiting assistant professor at Television and Networks Transmission Group, Communications Research Centre, Ottawa, Canada. From August to December 2008, he was a visiting associate professor at Department of Electrical Engineering, Stanford University, California, USA. His current interests are in graph-based algorithms, topological analysis, finite-field transforms, audio/speech signal processing, image processing, neural-networks/artificial-intelligence, pattern recognition and machine learning, wireless systems, wireless communications, intelligent systems, robotic technologies, indoor and outdoor localization/ranging/navigation mechanisms, non-destructive evaluation for material, civil, and mechanical structures, and biometric instrumentation. Dr. Wu has published more than 270 refereed journal and conference papers in signal processing, broadcasting, wireless communications, computer, electronics, sensor networks and ultrasonics areas (more than 230 of them are published by IEEE or ACM). He has ever served on twenty journal editorial boards in the area of electrical and computer engineering including IEEE Transactions on Signal Processing, IEEE Transactions on Mobile Computing, IEEE Transactions on Wireless Communications, IEEE Transactions on Broadcasting, IEEE Transactions on Vehicular Technology, IEEE Communications Magazine, IEEE Communications Letters, IEEE Signal Processing Letters, etc. From 2009 to 2011, he has been serving on IEEE Multimedia Technical Committee. Dr. Wu is currently an IEEE Distinguished Lecturer and an IEEE Fellow of Class 2015.

A security-by-design approach to IoT deployment in power sector

Speaker: Dr Jolly Wong  CEng FIET CITP FBCS

Internet of Things (IoT) has huge potential to significantly transform the industrial sectors, including power sector.  The McKinsey Global Institute predicts that potential economic impact of IoT will reach up to USD 11 trillion per year by 2025.

The power sector has been the beneficiary of some recognizable early consumer-oriented applications of IoT, such as smart meters.  In Hong Kong, with our continuous drive for cost-effectiveness and efficiency through versatile engineering technologies and digital innovation, we envisage that the pace and scale of IoT deployment, through the installation of an advanced metering infrastructure (AMI) within Hongkong Electric to support our operations, will increase rapidly and aggressively over the next several years.

The smart meters and associated applications will provide 580,000 customers with more consumption details, facilitating them to optimize energy use so that appropriate measures can be taken to save energy.  The move will help transform Hong Kong into a smarter city.

Pushing intelligence to the edge with IoT has no doubt drastically enhanced the cost-efficiency in automatic and self-sustaining business operations. However, it has also significantly increased the attack surface from a cybersecurity perspective as every point of connection that exists carries the risk of being hacked.  IoT is indeed a double-edged sword. 

While IoT helps many organizations improve operational efficiency in a way that was unimaginable even a decade ago; it also makes these organizations more susceptible to cyber-attacks. In order to maximize the benefits of leveraging IoT to achieve tangible operational efficiency gain while minimizing the risks particularly those related to cybersecurity vulnerabilities, there is a pressing need to establish a framework with practicable guidelines on cyber security for IoT.

The purpose of this workshop is to set out a practical framework with principles and specific guidelines to ensure that the security posture of various IoT devices deployed by Hongkong Electric is robust, resilient, and responsive to emerging threats.

Speaker Bio

Dr. Wong is a technology consultant with over 30 years of experience working in public goods projects.  As Chief Technology Officer at the Hong Kong Police Force (HKPF), he oversaw the formulation of policies and strategies of ICT imperatives and rollout of command and control communications systems which won him the Outstanding Contribution to TETRA (Critical Communications) Award in 2008.

He created the Finance-Operate-Own-Share (FOOS) business model, which successfully applied public and private partnerships to resolve major technological challenges in the HKPF. The model and its application have won awards like the Ken Goulding Prize for Professional Excellence 2015 and parts of the model has been replicated by organizations all over the world.

Between 2015 and 2017 Dr Wong was a member of the Advisory Committee on Innovation and Technology, the body that wrote the ‘Smart City’ blueprint for innovation and technology development for the HKSAR Government. In January 2021 he became the Senior Adviser for Hongkong Electric Company Limited (HEC) on technology policy and strategy related to innovation and cybersecurity.  HEC is a utility providing a safe and highly reliable (at rating over 99.9999%) electricity supply to over 580,000 households on Hong Kong and Lamma Islands.

Dr Wong is deeply involved with the Institution of Engineering and Technology (IET) and has served as its Vice President, Trustee, Council Chairman and Hong Kong Branch Chairman. He was the former Hong Kong Chapter Chair of the IEEE Engineering Management Society.  He mentors STEM students as a Visiting Professor for Shanghai University and Beijing University of Posts and Telecommunications, and is also a Policy Fellow for the Centre for Science and Policy (CSaP) at University of Cambridge.

Clean Transportation Planning, Research, and Development at the California Energy Commission

Speakers: Kiel Pratt & Ben Wender

California is a leader in policies and programs to mitigate the impacts of climate change, reduce harmful emissions, and protect the health of all Californians through rapid transitions to zero-emission transportation and electricity systems. In September 2020, Executive Order N-79-20 established statewide targets for 100 percent of new passenger vehicle sales, all drayage truck operations, and all off-road equipment operations where feasible to be zero-emission by 2035, followed all medium- and heavy-duty vehicle operations by 2045 where feasible. At the same time, Senate Bill 100 calls for 100 percent of retail electricity sales to come from renewable and zero-carbon resources by 2045. The California Energy Commission (CEC) runs numerous programs to help plan for and develop the technologies to enable the simultaneous evolution of the transportation and electricity systems. This presentation will provide an overview of relevant state policies, share recent analyses quantifying the number of chargers and associated electric infrastructure required to reach policy targets, and review CEC-funded technology research, development, and demonstration projects focused on vehicle-grid integration and the use of distributed energy resources to support electric vehicle charging.

Speakers Bio:

Kiel Pratt supervises a unit within the CEC’s Fuels and Transportation Division supporting California’s transition to zero-emission transportation. The team, the Vehicle-Grid Integration Unit, coordinates analytical work to leverage clean energy investments and cutting-edge modeling to help bring about a future where electrified transportation moves people and goods more conveniently than ever, and where electrified transportation is part of a carbon-neutral, reliable, and resilient energy system. Kiel holds a Bachelor of Science degree in mathematics and a minor in music from Cal Poly at San Luis Obispo. 

Ben Wender is an Electric Generation System Program Specialist in the Research and Development Division at the CEC, where he manages the transportation electrification portfolio for the Electric Program Investment Charge (EPIC) program. EPIC funds more than $130M per year in competitive research awards across numerous clean energy technologies. Prior to working at the CEC, Ben worked for five years at the National Academies of Sciences, Engineering, and Medicine’s Board on Energy and Environmental Systems where he managed studies related to electric system resilience, grid modernization, and vehicle fuel economy technologies. He received a MS and PhD from Arizona State University in Civil, Environmental, and Sustainable Engineering.

Fog/Edge Computing, 5G overview and 6G Initiatives  

Speaker: Zhensheng Zhang

Recent deployment in the internet to support Internet of Things (IoT) includes cloud computing and fog computing.   Fog/Edge computing is a disseminated computing infrastructure in which application and its services are handled either at the network edge or in a remote data center- cloud. Fog computing improves efficiency and trim the amount of data that requires to be transmitted for processing, analysis and storage by placing the data close to the end user. In this talk, we will have a high level overview of the basic infrastructure and platform Fog/edge Computing,  review its architecture and key interfaces, highlight key differences between cloud computing and fog computing, discuss under which condition one is preferred than the other. Fifth generation (5G) communication networks are being deployed in many areas. We will review, at high level,  the timelines and technologies used in 2/3/4/5G networks. If time permits, we will discuss/predict some of the 6G features/initiative.

Speaker Bio:

Dr. Zhensheng Zhang received his Ph. D. in Electrical Engineering from UCLA. He has over twenty five years’ experience in design and analysis of network architecture, protocols and control algorithms, of the communication networks. He has worked at Cubic Corporation, Boeing, Bell Laboratories, Lucent Technologies, and Columbia University, respectively, focusing on research and development in wireless networks. He has published over 100 technical papers in IEEE Journals and key IEEE conferences (one paper was listed as the top 10 most reading articles from IEEE Communications Society website in 2007).  He was IEEE Comsoc distinguished lecturer (2010-2013), the IEEE LATINCOM Keynote Speaker (2013); received the IEEE Regional/Area Outstanding Engineer award in 2011. He is an IEEE Fellow.

He has been very active in IEEE Comsoc in the past decade, some of his roles include: 

Member-at-Large (MAL), IEEE comsoc Board of Governors (B0G), 2021-2023

Director, Membership Service (Comsoc BoG) 2016-2017,

IEEE 5G summit San Diego 2019 General co-Chair,

IEEE San Diego Section chair 2021,

Globecom 2012 TPC Chair;   Globecom 2015 Executive Vice Chair;

Board Member, North America Region (NAR), 2008-2015; 2018-2021; 

IEEE ICC 2015 TPC vice Chair;  

Editor, IEEE Transactions on Wireless Communications (2000-2004).