Showing papers by "Gian Marco Revel published in 2023"

Measuring material temperature in high-temperature microwave-based heating process: a virtual sensor approach

Abstract: Virtual sensors are pivotal to provide measures that would be extremely hard to make through the use of traditional hard sensors. This paper discusses an artificial intelligence-based approach for measuring temperature of the material being processed in a high-temperature microwave kiln. Preliminary results are reported for calcined clays, with temperature values up to approximately 500 °C. The results show that material temperature can be effectively predicted by the virtual sensor (average mean absolute error: 2.4 °C). The very same approach is currently being developed for other types of materials being processed through microwave-heating, such as ceramic pigments and iron bearing residues.

Automated Measurement of Geometric Features in Curvilinear Structures Exploiting Steger’s Algorithm

Abstract: Accurately assessing the geometric features of curvilinear structures on images is of paramount importance in many vision-based measurement systems targeting technological fields such as quality control, defect analysis, biomedical, aerial, and satellite imaging. This paper aims at laying the basis for the development of fully automated vision-based measurement systems targeting the measurement of elements that can be treated as curvilinear structures in the resulting image, such as cracks in concrete elements. In particular, the goal is to overcome the limitation of exploiting the well-known Steger’s ridge detection algorithm in these applications because of the manual identification of the input parameters characterizing the algorithm, which are preventing its extensive use in the measurement field. This paper proposes an approach to make the selection phase of these input parameters fully automated. The metrological performance of the proposed approach is discussed. The method is demonstrated on both synthesized and experimental data.

Propagation of the Measurement Uncertainty of Wearable Sensors for Thermal Comfort Assessment

Abstract: The development of personal comfort models (PCMs) is pivotal for the optimization of both the occupants’ comfort and the building energy consumption; wearable sensors assessing physiological parameters can be exploited for this aim. This paper considers commercial and laboratory prototypes of wearable sensors and aims at evaluating the propagation of the input measurement uncertainties on the features computed for the development of PCMs. Different types of wearables, suitable for physiological monitoring in a living environment, are considered: smartwatch, smartband, smart garment, smart ring, patch, and headband. The Monte Carlo simulation method is exploited for the uncertainty analysis. The results show that some features are more robust than others and this is relevant when selecting a feature subset for a model creation. The findings are useful for the design of PCMs aiming at improving the quality of life in indoor living environments, developed with a human-centric view.

A monitoring platform for the built environment: towards the development of an early warning system in a seismic context

Abstract: The aim of this paper is to present a monitoring system for the built environment based on electrical impedance sensors, together with the development of an early warning system to support decision-making processes in a seismic context. In particular, preliminary data were collected on mortar specimens embedding stainless-steel electrodes for the periodic measurement of electrical impedance. Hence, these data were exploited to train a Neural Prophet-based deep learning model for the prediction of the electrical impedance module. Indeed, this quantity can provide a lot of information about the health status of the monitored structures. The results can be exploited for the development of an early warning system supporting decision-making strategies for the building management. The model can predict the trend of electrical impedance with acceptable accuracy (MAPE <2%); hence, the monitoring platform can provide information suitable for the development of an early warning system.

Localization of Older People in an Indoor Scenario: A Measurement System Based on PIR Sensors Installed in a Social Robot

Abstract: People detection is widely used in remote health monitoring and smart homes. Passive infrared (PIR) sensors are the most used devices-free detection system for their affordability, non-invasiveness, low power consumption and high accuracy. However, there are still many challenges related to analyzing digital output data to extract useful information with multi-PIR systems. Thus, in this paper we propose a measurement system composed of multi-PIR sensors mounted on the head of a mobile social robot in which the granularity of the overlapped field of view (FoV) of sensors are considered to increase the localization accuracy. In addition, a Decision Tree (DT) classifier algorithm is trained on the system data to improve the localization accuracy. The results show that the accuracy of the system is 96% for tests performed in controlled environments when subjects have gait movement constraints. The accuracy of the system decreases (83.3%) when no constraints are applied.

Robot-based measurement of comfort through thermal infrared imaging and wearable sensors

Abstract: This paper presents an innovative integrated measurement system composed of a social robot, an infrared (IR) sensor and a wearable device (smartwatch) for the assessment of human thermal comfort. The goal of this work is to provide a human-centered methodology that exploits a robotic structure to provide a comfort coaching solution for the end-users in the built environment. For this purpose, physiological parameters such as Heart Rate Variability (HRV) and skin temperature (ts) are measured, in response to different environmental conditions in the office environment. Data were acquired during the summer season, with a dedicated measurement campaign that involved 8 participants. They were exposed to comfort and warm discomfort conditions while the smartwatch and the IR sensor acquired the parameters for 30 minutes. Data analysis was conducted to create suitable input datasets for testing 7 different supervised machine learning (ML) algorithms. The Thermal Sensation Vote (TSV) of the participants was used as the ground truth to evaluate thermal comfort. Results show that in the intrasubject dataset Random Forest (RF) and Naïve Bayes (NB) classifiers can distinguish whether the occupant was in thermal comfort with an accuracy of 93% and 94%, respectively. For the inter-subject comfort evaluation, the average accuracy is 63% for the comfort trial and 49% for the warm discomfort trial. The current research provides a further step in the measurement of thermal comfort, including a robot-based methodology and the use of physiological parameters and ML techniques to interpret human thermal comfort perception in the built environment.

Development and metrological characterization of cement-based elements with self-sensing capabilities for structural health monitoring purposes

Abstract: Mortar specimens containing conductive additions (i.e., biochar and recycled carbon fibres – both alone and together, and graphene nanoplatelets) were characterized from a metrological point of view. Their piezoresistive capability was evaluated, exploiting the 4-electrode Wenner’s method to measure electrical impedance in alternating current (AC); in this way, both material and electrode-material polarization issues were avoided. The selected mix-design was used to manufacture scaled concrete beams serving as demonstrators. Additionally, FEM-based models were realized for a preliminary analysis of the modal parameters that will be investigated through impact tests conducted after different loading tests, simulating potential seismic effects. The results show that the combined use of recycled carbon fibers and biochar provide the best performance in terms of piezoresistivity (with a sensitivity of 0.109 (µm/m)-1 vs 0.003 (µm/m)-1 of reference mortar). Conductive additions improve the Signal-to-Noise Ratio (SNR) and increase the material electrical conductivity, providing suitable tools to develop a distributed sensor network for Structural Health Monitoring (SHM). Such a monitoring system could be exploited to enhance the resilience of strategic structures and infrastructures towards natural hazards. A homogeneous distribution of conductive additions during casting is fundamental to enhance the measurement repeatability. In fact, both concrete intrinsic properties and curing effect (hydration phenomena, increasing electrical impedance) cause a high variability.