ICMLT 2024 Keynote Speaker
Prof. Angrisani Leopoldo (IEEE Fellow), Università degli Studi di Napoli Federico II, Italy
Leopoldo Angrisani is Full Professor of Electrical and Electronic Measurements with the Department of Information Technology and Electrical Engineering of the University of Naples Federico II, Italy. He is also Chair of the Board of the Ph.D. Program ICTH - Information and Communication Technology for Health of the University of Naples Federico II.
His research activity has always been focused on topics related to electrical and electronic measurements. He currently pays attention to the role of measurement in the IoT field and, more generally, in the Industry 4.0 field, cyber-physical measurement systems, measurement of ICT systems sustainability and sustainability of measurements, sensors, sensor networks, and measurement methods in precision agriculture and livestock farming, operation and performance assessment of communication systems, equipment, and networks, measurement uncertainty, impact of quantum technologies on measurements.
He was and is currently involved in many industrial research projects, in cooperation with small, medium, and great enterprises, for which he played and is currently playing the role of scientific coordinator. He is currently the Coordinator of the Technical/Scientific Committee of MedITech – one of the eight Italian Competence Centers on I4.0 enabling technologies.
He is Fellow Member of the IEEE Instrumentation and Measurement and Communications Societies. He was Honorary Chairman of the first (M&N 2019) and second (M&N 2022) edition of the IEEE International Symposium on Measurements & Networking, General Chairman of the second edition (MetroInd4.0&IoT 2019) of the IEEE International Workshop on Metrology for Industry 4.0 and IoT, and General Chairman of the first edition (IEEE MeAVeAS 2023) of the IEEE International Workshop on Measurements and Applications in Veterinary and Animal Sciences. He is vice-chair of the Italian Association “GMEE-Electrical and Electronic Measurements Group”, and a corresponding member of the Accademia Pontaniana in Naples, the oldest Italian academy, with almost 600 years of history, which has always brought together renowned Neapolitan scholars.
In 2009, he was awarded the IET Communications Premium for the paper entitled “Performance measurement of IEEE 802.11b-based networks affected by narrowband interference through cross-layer measurements” (published in IET Communications, vol. 2, No. 1, January 2008).
The IEEE Instrumentation & Measurement Society Italy Chapter, which he has been chairing since 2015, was awarded in 2016 the prestigious recognition “I&M Society Best Chapter Award” by the IEEE Instrumentation & Measurement Society, in 2017 the prestigious recognition “Most Improved Membership Chapter for 2016” by the IEEE Italy Section, in 2018 the prestigious recognition “Most Innovative Chapter 2018” by the IEEE Italy Section, and in 2021 the prestigious recognition "Chapter of the Year 2021" by the IEEE Region 8 (Europe, Middle Est, Africa).
In 2021, he was awarded the prestigious recognition “2021 IEEE Instrumentation and Measurement Society Technical Award” with the following citation “For contributions in the advancement of innovative methods and techniques for communication systems test and measurement”.
Speech Title: AI-based measurements: a new sustainability-aware perspective
Abstract: Nowadays, the concept of Sustainability has gained significant relevance across various spheres of human activity, including the realm of Information and Communication Technologies (ICTs). However, ICTs are a double-edged sword for sustainability: they are fundamental tools for developing and implementing more sustainable processes and products; nevertheless, the very use of ICTs has its own environmental impact.
Measurement systems are relevant manifestations of ICTs. Hence, it is extremely important to address the sustainability of measurements and their impact on the environment. In turn, it is also necessary to develop new measurement models that can contribute to a robust assessment of sustainability.
Starting from these considerations, the talk will present an innovative methodological approach aimed at modeling and evaluating the sustainability of ICT manifestations, with special regard both to common electronic measurement systems and their evolution towards Cyber-Physical Measurement Systems (CPMSs), which holistically exploit 4.0 enabling technologies, and in particular Artificial Intelligence (AI), for achieving unsurpassed metrological performance.
Assessing the sustainability of CPMS makes it unavoidable to evaluate the environmental impact of AI-based solutions, due, for example, to the effort required to build large data sets, and software libraries, and to train AI models. However, in the literature, there is a lack of systematic studies estimating how much these “actions” can be considered green.
To start bridging this gap, the talk will also introduce a case study, related to the acquisition and processing of biosignals, particularly Electroencephalography (EEG). It will show a practical example of an optimal balance between the performance of AI-based measurement and the mitigation of the related environmental impact.
Prof. Xiao-Zhi Gao, University of Eastern Finland, Finland
Xiao-Zhi Gao received his B.Sc. and M.Sc. degrees from the Harbin Institute of Technology, China in 1993 and 1996, respectively. He obtained his D.Sc. (Tech.) degree from the Helsinki University of Technology (now Aalto University), Finland in 1999. He has been working as a professor at the University of Eastern Finland, Finland since 2018. Prof. Gao has published more than 500 technical papers in refereed journals and international conferences. His current Google Scholar H-index is 42. Prof. Gao’s research interests are nature-inspired computing methods with their applications in optimization, data mining, machine learning, control, signal processing, and industrial electronics.
Speech Title: An Introduction to Nature-inspired Computing Methods and Applications
Abstract: Nature-Inspired Computing (NIC) methods draw inspiration from the natural world. They encompass a large variety of approaches based on the principles and mechanisms found in physical, chemical, biological, and social systems. In this talk, the underlying working principles of a few NIC algorithms are introduced. Some typical applications of these techniques are also presented and discussed.
Prof. Jianhua Zhang, Oslo Metropolitan University, Norway
Jianhua Zhang is currently a Professor of Computer Science at Oslo Metropolitan University, Norway. His recent research interests are in the fields of computational intelligence, machine learning, intelligent systems and control, biomedical signal processing, and neurocomputing. In those fields he has published 4 books, 11 book chapters, and around 200 peer-reviewed journal and conference papers.
Dr Zhang served as Chair of IFAC (International Federation of Automatic Control) Technical Committee on Human-Machine Systems for two consecutive terms (2017-2023) and Vice Chair of IEEE Norway Section (2019-2023). He currently serves as Vice Chair of IFAC Technical Committee on Human-Machine Systems and Vice Chair for IEEE CIS (Computational Intelligence Society) Norway Chapter.
Dr Zhang is on editorial board of four international journals, including Frontiers in Neuroscience, Cognitive Neurodynamics (Springer), and Cognition, Technology & Work (Springer). He served as IPC Co-Chair for IFAC LSS 2013 (Shanghai) and HMS 2016 (Kyoto), and IPC Chair for IFAC HMS 2019 (Tallinn) and HMS 2022 (San Jose). He was also a keynote speaker or chair for a number of other international scientific conferences.
Speech Title: Forecasting Household Energy Consumption based on Deep Neuroevolution Models
Abstract: Accurate energy consumption prediction provides the basis for informed decisions on energy purchase and generation, as it prevents overloading and enables energy storage in a more efficient way. In this work, we construct a new deep learning model to predict the household energy consumption. We employ differential evolution (DE) algorithm to determine the optimal architecture of the deep neural network model. Finally, we present and analyze the real-life data analysis results to show the effectiveness of the deep neuroevolution models for energy use prediction problem under investigation.