Tutorial Presentations

Soft sensors are models that allow estimating the values of a variable based on other process information, without having to measure this variable directly. The main benefits of soft sensors are (1) they represent a low-cost alternative when compared to physical sensors, (2) they can work together with physical sensors, including identifying when they fail, (3) they allow implementation on existing devices, and (4) they provide real-time estimates, being an option for measurements where physical sensors depend on time-consuming analysis. In this tutorial, we are going to learn how to develop a data-driven soft sensor using Python taking into account data-driven techniques such as neural networks, decision trees, and other regression techniques. Besides the soft sensor development, we will discuss 10 good practices to develop safer, more reliable and more efficient models. The good practices involves the understanding of the risk of not taking care of models extrapolation, the effect of data quality and data quantity while building the models, and the importance of error distribution besides general metrics. After building the models, we will discuss good practices to improve efficiency, how to monitor performance and how to perform models calibration.

We present a novel non-contact microwave cavity method and instrumentation to evaluate the environmental effects on the dielectric permittivity of electronic materials. This approach addresses the challenge of field perturbation caused by non-uniform depolarization field distribution when a partially inserted dielectric sample interacts with the cavity, which can otherwise skew resonant frequency measurements. Our method enables precise analysis of strongly perturbing, partially inserted specimens, which are inaccessible to conventional techniques. By demonstrating a linear relationship between the natural resonant frequency shift and the damping ratio with the volume fraction of the specimen, we improve measurement uncertainty. Incremental sample insertion enhances data resolution, increasing data points from 1 to 20 for a single specimen and significantly improving accuracy for complex permittivity evaluations under environmental exposure. Example applications include the measurement of water vapor transmission rates for thin-film protective coatings on epitaxial monolayer graphene, the impact of environmental moisture and UV radiation on insulating dielectrics in solar installations, and the CO₂ capture efficiency of polyethylenimine thin films. 

There has been an astronomical increase in the number of technical paper
submissions in the past decade. Some of the reasons include:

• pressure to publish, as the success indicator, for promotion and professional
  advancement,
• universities moving away from the traditional Theses and Dissertations compilations and
  instead use peer-reviewed journal papers,
• creation of new journals, and
• the open-access publishing “economy”.

Effective journal paper writing requires many implicit and explicit issues to consider. This involves deciding on the proper, most effective and relevant publications venue; having the knowledge of (and experience) how to compile the content that goes into the paper; having a clear knowledge of the publications’ guidelines and rules for the chosen venue; etc.

The review process is the most crucial aspect of a proper publishing process. It involves the authors, the editors, and the reviewers, and how each performs detrimentally impacts the outcome and the “Quality”.

Inclusion of AI-assisted and AI-generated content has become an important issue. To this end, IEEE has specific guidelines with to authors and reviewers must adhere and ignoring them could have significant implications for authors and reviewers.

This tutorial will specifically discuss issues and guidelines relevant to: Technical Paper Writing; Publication Process; Review Requirements; and Use and Implications of AI Content for authors and reviewers.

Join us in this comprehensive tutorial to explore the Electrical Resistance Tomography (ERT) — a valuable technique for non-invasive conductivity mapping of 2D and thin-film materials. This tutorial will give you an overview of both experimental practices and advanced mathematical methods, providing a foundation for professionals and researchers interested in exploiting ERT in material science. The first part of the tutorial will focus on practical challenges and solutions in experimental ERT setups. Learn how to implement in-contact electrical measurements on thin films, using suitable custom fixtures; unravel the pros and cons of different measurement protocols; understand how to optimize instrumentation for speed and accuracy. In the second part, the focus will move on the mathematical framework behind ERT. From deriving forward models with partial differential equations to solving non-linear inverse problems with advanced numerical methods, this section will provide hands-on insights into the computational tools needed for an effective conductivity mapping with real-world examples. The tutorial will also introduce Open Science practices, including the development of FAIR-compliant datasets, promoting collaboration between experimental and computational research communities. This tutorial will be an opportunity for professionals and researchers seeking to deepen their understanding of ERT and its applications in material science. 

The increasing energy consumption demand urges to level up the power grid's reliability in every aspect. The high-voltage circuit breaker (HVCB) is one of the most important elements of the power grid responsible for the protection and control of the power system. The life expectancy of a newly installed CB is approximately 40 years. Through its lifetime, under normal conditions. CB will operate (make or break) for less than ten minutes while during abnormal conditions it will operate for less than one minute. To prevent potential issues that might arise during operating and specifically during its long idling time, the HVCBs are inspected and maintained regularly. The presentation will cover the invasive as well as noninvasive measurement methods, signal processing and result interpretation used for assessing the condition of the HVCB. It covers approaches to assessing conditions of the main and arcing contact, operating mechanism as well as the actuating coil focusing on the measurement and acquired signals interpretation.

The first portion of the presentation is devoted to the anatomy of the measurement approaches for performing well-established tests in industrial applications such as timing test, static resistance measurement, and dynamic resistance measurement as well as assessing the condition of the actuating coil and operating mechanism in the form of minimum trip voltage test and motor test. Additionally, the mechanical integrity will be discussed based on vibration fingerprint-based assessment.

The second portion of the presentation is oriented toward signal processing, analysis and algorithms utilized to quantify the measurement described in the first portion of the presentation. Thus, the denoising, processing and feature extraction for each stated test will be covered. Furthermore, the extracted features and indices interpretation will be supported by real-life measurements of different HVCB types.

Impedance spectroscopy has become an indispensable tool in modern measurement science, offering unique insights into material and system properties through frequency-dependent electrical measurements. This method is particularly valuable because it is non-invasive and can reveal information about physical and chemical processes that remain hidden to conventional measurement techniques. This tutorial aims to bridge the gap between theoretical understanding and practical implementation of impedance spectroscopy for different classes of application requirements.

We will begin with the fundamentals of impedance measurements and progressively explore real-world applications across various domains. Through practical examples, we will examine how impedance spectroscopy is implemented in laboratory environments with big devices and in-field implemented in embedded systems. The tutorial will address key applications, including material testing, battery characterization, biomedical measurements, and sensor development. Special attention will be given to common challenges encountered in practice, such as dealing with measurement uncertainties, choosing appropriate measurement parameters, and optimizing system performance.

Beyond the basics, we will explore recent developments in advances in measurement hardware and new approaches for data analysis. We will discuss practical strategies for interpreting measurement results, from traditional equivalent circuit modeling to modern analysis methods. The tutorial concludes with a look at current trends and future possibilities in the field.

The Internet of Things (IoT) paradigm enables smart objects to communicate, this allows us to interact with our environment in a smart way. It is predicted that low power and ultra-low power sensors will make up the majority of IoT devices by 2030. To leverage the full potential of IoT applications, machine learning (ML) techniques are required to analyze sensor measurements on the edge for real-time analytics, lower latency, and less privacy concern. In this tutorial, we will first give a comprehensive overview of low power sensors and compare various IoT communication protocols. We will cover the end-to-end data integration steps from sensors to the loud data platform using real life award-winning smart cities examples. This tutorial will review various methods for applying ML and deep learning to resource-limited low power sensors. Different hardware and software options will be discussed including bio-inspired chipsets, traditional centralized learning, federated ML, pruning and TinyML for edge computing. We will demonstrate the latest design of our acoustic sensor with edge ML capability for real time sound classification. Development trend and future research opportunities for edge AI and IoT will also be presented. 

Electrical impedance spectroscopy (EIS) is a powerful technique, but performing accurate measurements can be challenging. Selecting the right equipment, sensors and configurations requires a deep understanding of specifications, parameters, and options—decisions that even experienced engineers and scientists may find complex. The interdependencies of components, practical constraints, and the prevalence of imprecise or overly simplified assumptions further complicate the process.

This tutorial addresses the critical technical aspects of EIS measurement setups, providing participants with both foundational knowledge and actionable insights. Topics covered include:

• A concise review of EIS fundamentals
• Exploration of common and unconventional EIS applications
• Overview of available instrument classes and their specific strengths
• In-depth analysis of key specifications and their practical implications
• Multichannel systems and their advantages
• Addressing parasitic influences
• Selection and use of electrodes and sensors

The tutorial combines lectures with hands-on sessions to solidify understanding through practical examples. Real-life case studies from academic research and industrial applications will illustrate the discussed concepts, highlighting their relevance and significance. By the end, participants will be equipped to navigate the complexities of EIS measurements, make informed decisions about setups, and avoid common pitfalls caused by oversimplifications or misconceptions.

Autonomous systems are nowadays having an undisputed pervasiveness in the modern society. Autonomous driving cars as well as applications of service robots (e.g. cleaning robots, companion robots, intelligent healthcare solutions, tour guided systems) are becoming more and more popular and a general acceptance is now developing around such systems in the modern societies. Nonetheless, one of the major problems in building such applications relies on the capability of autonomous systems to understand their surroundings and then plan proper counteractions. The most popular solutions, which are gaining more and more attention, rely on artificial intelligence and deep learning as a means to perceive the structured and complex natural environment. Nonetheless, besides the importance of such complex tools, classical concept of metrology, such as standard uncertainty, accuracy and precision, are still unavoidable for a clear and effective understanding of modern autonomous systems applications. 

At the end of this tutorial the attendee will be able to answer such questions as: what are the tools and the methods of major relevance for autonomous systems applications? How do concepts as uncertainty map in the autonomous systems realm?

Compound-Oriented Measurement Technology is a specialized area within measurement technology that requires a more comprehensive approach than standard measurement techniques. These methods can be complex and involve several stages, including sampling, sample preparation, transportation, reformatting, measurement, and data processing. The intricate nature of these procedures requires a validation, which consideres all subprocesses within the overall workflow for accurate measurement results. In contrast to most physical measurements, compound-oriented measurements qualify (identify) and quantify the measurand of interest. Often, the measurand must be selected from multi-component mixtures of different compounds embedded in biological, chemical, medical, industrial, or environmental matrices. Compound-oriented measurements can be improved using robotic systems to increase sample throughput, ensure the safety of personnel, and enhance measurement accuracy. This tutorial will provide an in-depth exploration of the theoretical and practical aspects of compound-oriented measurements, the validation strategies required for both manual and automated methods, and the key parameters for evaluating measurement systems. Real-world examples, such as detecting heavy metals and pharmaceutical residues in environmental and biological samples, will demonstrate the validation results for both manual and automated measurement processes. The tutorial will also highlight how robotic systems can streamline workflows and reduce the influence of variables, leading to more accurate and reliable results. By the end of this tutorial, you will gain a comprehensive understanding of the complexities of compound-oriented measurements and the potential of automation solutions through robotic systems.

The acquisition of information about physical quantities by means of sensors historically fostered the interpretation of measurement as a merely experimental activity. Conversely, measurement is a complex activity, far more complex than suitably connecting and reading an instrument. Indeed, prior of the execution of empirical activities, measurement always requires descriptive activities to be performed to ensure both the correct implementation of the experiments and the interpretation of the obtained information. 

In this tutorial, the basic concepts involved in any measurement are presented and discussed. The tutorial contents support a methodologically correct development required by any measurement, regardless the kind of involved quantities (either physical or non-physical) or the field of application. 

At the end of this tutorial the attendee will be able to answer such questions as: Which characteristics need to be fulfilled to ensure that an informative empirical process is a measurement? How an adequate model for a given measurement can be identified? How the quantity of information obtained through measurement can be evaluated and expressed? 

Antennas are seen everywhere connectivity is required. Along with cellular phones and IoT devices, vehicles in the land or the sea need channels of communication via relays in the sky or the peak of a hill to send and receive information in a mobile network indebted to functions of the antennas. The quality of the communication is determined by that of an antenna whether it goes with the analogue or digital mobile framework, for it allows an RF signal from the transmitter to reach the receiver. Before the antenna is deployed for the ultimate configuration of wireless communication, its characteristics of electromagnetic radiation are assessed with the far-field test equipment at an anechoic chamber. It is normal of the Zigbee, Bluetooth, WiFi, 5G mobile, metasurface lens, RIS reflectors, SAR antennas, etc. to undergo the conventional test method. Meanwhile, it runs across technical limits and shortcomings when the radiation aperture or structure holding the antenna is very large such as access point antennas mounted on a building or high directivity ones having large apertures adopted for hyper connectivity and target detection. In case the space for a wireless link such as the localizer in the instrument landing system as well as the mountain-top television relay station should be too large to be put into the anechoic chamber, an alternative method had to be come up with. The drone is adopted to the in-flight observation of the electromagnetic properties of the antenna huge or positioned very high. Step 1 is to equip the drone with the probe antenna, GPS antenna, spectrum analyzer, data storage and controller. Step 2 is to define the shape and size of the field scanning surface comprising observation positions with the distance and angular range from the antenna under test (AUT). Step 3 is to calibrate the AUT with the reference antenna like the log-periodic or horn antenna. Step 4 is to conduct the field scanning with the drone and record the observed field at every observation position on the scanning surface. Step 5 is to make the field plot and analyze it. In this talk, the general idea is mentioned and followed by elaborating on a real example of a UHF broadcasting antenna.  

Rolling element bearings are commonly used in rotating machines such as vehicles, aircraft, and motors. As a matter of fact, most machinery imperfections, especially for small- and medium-size machines, are related to bearing defects. However, reliable fault detection in rolling element bearings remains a challenging task in this research and development field, due to reasons such as system dynamics complexity and feature modulations. This tutorial will address recent development and the related challenges in bearing fault detection and real-time health condition monitoring. The covered research aspects include smart sensor-based data acquisition, signal denoising to improve signal-to-noise ratio, signal processing for bearing representative feature extraction, and AI-based real-time machine condition monitoring and fault diagnostics. This tutorial will discuss recent research progress in related fields, the challenges encountered, and possible solutions. It will also provide examples and strategies on how to implement the related technologies for machine health condition monitoring and fault diagnostics in real-world industrial applications.

The precision agriculture (PA) combines technologies and practices that assure the optimization of the operations associated agricultural production through specific farm management. 

Regarding the used technologies distributed smart sensing systems characterized by fixed and mobile nodes (based on remote sensing  and Unnamed Aerial Vehicle (UAV))) are used to turn the farming operations into data, and to optimize the future operation based on data driven models that can be part of digital twins applied in precision agriculture. Edge and cloud computing platforms that are capable to run AI/ML algorithms may contribute to help on human decisions. 

The tutorial focusses on digital transformation of the agriculture in the context of heavily uncertainty associated with climate change. The IoT ecosystem technologies for precision agriculture will be discussed including multimodal sensing and artificial intelligence. In-situ and remote sensing are considered special attention being granted to the soil characteristics monitoring (moisture and macronutrients concentration). 

The agriculture UAV imagery and satellite  imagery solutions as so as the relation between the data coming from the in-situ distributed smart sensors and acquired images using multispectral and thermographic camera and imagery techniques will be part of the presentation as so as elements of virtualization in the case of digital twins implementation. AI multiple sources data driven models for an increased crops quality through the optimization of farming operations as so as examples of data driven models for smart irrigation and nutrients will be discussed.