In the Direction of an Artificial Intelligence-Enabled Monitoring Platform for Concrete Structures.

In a seismic context, it is fundamental to deploy distributed sensor networks for Structural Health Monitoring (SHM). Indeed, regularly gathering data from a structure/infrastructure gives insight on the structural health status, and Artificial Intelligence (AI) technologies can help in exploiting this information to generate early warnings useful for decision-making purposes. With a perspective of developing a remote monitoring platform for the built environment in a seismic context, the authors tested self-sensing concrete beams in loading tests, focusing on the measured electrical impedance. The formed cracks were objectively assessed through a vision-based system. Also, a comparative analysis of AI-based and statistical prediction methods, including Prophet, ARIMA, and SARIMAX, was conducted for predicting electrical impedance. Results show that the real part of electrical impedance is highly correlated with the applied load (Pearson's correlation coefficient > 0.9); hence, the piezoresistive ability of the manufactured specimens has been confirmed. Concerning prediction methods, the superiority of the Prophet model over statistical techniques was demonstrated (Mean Absolute Percentage Error, MAPE < 1.00%). Thus, the exploitation of electrical impedance sensors, vision-based systems, and AI technologies can be significant to enhance SHM and maintenance needs prediction in the built environment.

Damage Identification in Cement-Based Structures: A Method Based on Modal Curvatures and Continuous Wavelet Transform.

Modal analysis is an effective tool in the context of Structural Health Monitoring (SHM) since the dynamic characteristics of cement-based structures reflect the structural health status of the material itself. The authors consider increasing level load tests on concrete beams and propose a methodology for damage identification relying on the computation of modal curvatures combined with continuous wavelet transform (CWT) to highlight damage-related changes. Unlike most literature studies, in the present work, no numerical models of the undamaged structure were exploited. Moreover, the authors defined synthetic damage indices depicting the status of a structure. The results show that the I mode shape is the most sensitive to damages; indeed, considering this mode, damages cause a decrease of natural vibration frequency (up to approximately -67%), an increase of loss factor (up to approximately fivefold), and changes in the mode shapes morphology (a cuspid appears). The proposed damage indices are promising, even if the level of damage is not clearly distinguishable, probably because tests were performed after the load removal. Further investigations are needed to scale the methodology to in-field applications.

Wearable Electrocardiography for Physical Activity Monitoring: Definition of Validation Protocol and Automatic Classification.

Wearable devices are rapidly spreading thanks to multiple advantages. Their use is expanding in several fields, from medicine to personal assessment and sport applications. At present, more and more wearable devices acquire an electrocardiographic (ECG) signal (in correspondence to the wrist), providing potentially useful information from a diagnostic point of view, particularly in sport medicine and in rehabilitation fields. They are remarkably relevant, being perceived as a common watch and, hence, considered neither intrusive nor a cause of the so-called "white coat effect". Their validation and metrological characterization are fundamental; hence, this work aims at defining a validation protocol tested on a commercial smartwatch (Samsung Galaxy Watch3, Samsung Electronics Italia S.p.A., Milan, Italy) with respect to a gold standard device (Zephyr BioHarness 3.0, Zephyr Technology Corporation, Annapolis, MD, USA, accuracy of ±1 bpm), reporting results on 30 subjects. The metrological performance is provided, supporting final users to properly interpret the results. Moreover, machine learning and deep learning models are used to discriminate between resting and activity-related ECG signals. The results confirm the possibility of using heart rate data from wearable sensors for activity identification (best results obtained by Random Forest, with accuracy of 0.81, recall of 0.80, and precision of 0.81, even using ECG signals of limited duration, i.e., 30 s). Moreover, the effectiveness of the proposed validation protocol to evaluate measurement accuracy and precision in a wide measurement range is verified. A bias of -1 bpm and an experimental standard deviation of 11 bpm (corresponding to an experimental standard deviation of the mean of ≈0 bpm) were found for the Samsung Galaxy Watch3, indicating a good performance from a metrological point of view.

Accuracy and Precision of Wearable Devices for Real-Time Monitoring of Swimming Athletes.

Nowadays, the use of wearable devices is spreading in different fields of application, such as healthcare, digital health, and sports monitoring. In sport applications, the present trend is to continuously monitor the athletes' physiological parameters during training or competitions to maximize performance and support coaches. This paper aims to evaluate the performances in heart rate assessment, in terms of accuracy and precision, of both wrist-worn and chest-strap commercial devices used during swimming activity, considering a test population of 10 expert swimmers. Three devices were employed: Polar H10 cardiac belt, Polar Vantage V2, and Garmin Venu Sq smartwatches. The former was used as a reference device to validate the data measured by the two smartwatches. Tests were performed both in dry and wet conditions, considering walking/running on a treadmill and different swimming styles in water, respectively. The measurement accuracy and precision were evaluated through standard methods, i.e., Bland-Altman plot, analysis of deviations, and Pearson's correlation coefficient. Results show that both precision and accuracy worsen during swimming activity (with an absolute increase of the measurement deviation in the range of 13-56 bpm for mean value and 49-52 bpm for standard deviation), proving how water and arms movement act as relevant interference inputs. Moreover, it was found that wearable performance decreases when activity intensity increases, highlighting the need for specific research for wearable applications in water, with a particular focus on swimming-related sports activities.

Wearable devices as a valid support for diagnostic excellence: lessons from a pandemic going forward.

Today, the use of wearable devices is continuously increasing with many different application fields. Their low-cost and wide availability make these devices proper instruments for long-term monitoring, potentially useful to detect physiological changes related to influenza or other viruses. The relevance of this aspect and the impact of such technology have become evident particularly in the last year, during COVID-19 emergency; (big) data from wearable devices (already worn by many citizens) together with artificial intelligence techniques gave birth to specific studies dedicated to quickly identify patterns discriminating between healthy and infected people. These evaluations are made on the basis of parameters measured by these devices, among which heart rate, physical activity, and sleep seem to play a dominant role. This could be extremely significant in terms of early detection and limit of contagion risk. However, there is still a lot of research to be conducted in terms of measurement accuracy, data management (privacy and security issues), and results exploitation, in order to reach an accurate and reliable solution helping the whole healthcare system particularly in epidemic events, such as the SARS-CoV-2 pandemic.

Development of a Novel Medical Device for Mucositis and Peri-Implantitis Treatment.

In spite of all the developments in dental implantology techniques, peri-implant diseases are frequent (prevalence up to 80% and 56% of subjects for mucositis and peri-implantitis, respectively) and there is an urgency for an effective treatment strategy. This paper presents an innovative electromedical device for the electromagnetic treatment of mucositis and peri-implantitis diseases. This device is also equipped with a measurement part for bioimpedance, which reflects the health conditions of a tissue, thus allowing clinicians to objectively detect impaired areas and to monitor the severity of the disease, evaluate the treatment efficacy, and adjust it accordingly. The design of the device was realized considering literature data, clinical evidence, numerical simulation results, and electromagnetic compatibility (EMC) pre-compliance tests, involving both clinicians and engineers, to better understand all the needs and translate them into design requirements. The reported system is being tested in more than 50 dental offices since 2019, providing efficient treatments for mucositis and peri-implantitis, with success rates of approximately 98% and 80%, respectively.

Measurement of the 100 MHz EMF radiation in vivo effects on zebrafish D. rerio embryonic development: A multidisciplinary study.

The augmented exposure of both environment and human being to electromagnetic waves and the concomitant lack of an unequivocal knowledge about biological consequences of these radiations, raised public interest on electromagnetic pollution. In this context, the present study aims to evaluate the biological effects on zebrafish (ZF) embryos of 100 MHz radiofrequency electromagnetic field (RF-EMF) exposure through a multidisciplinary protocol. Because of the shared synteny between human and ZF genomes that validated its use in biomedical research, toxicology and developmental biology studies, ZF was here selected as experimental model and a measurement protocol and biological analyses have been set up to clearly discriminate between RF-EMF biological and thermal effects. The results showed that a 100 MHz EMF was able to affect ZF embryonic development, from 24 to 72 h post fertilization (hpf) in all the analyzed pathways. Particularly, at the 48 hpf stage, a reduced growth, an increased transcription of oxidative stress genes, the onset of apoptotic/autophagic processes and a modification in cholesterol metabolism were detected. ZF embryos faced stress induced by EMF radiation by triggering detoxification mechanisms and at 72 hpf they partially recovered from stress reaching the hatching time in a comparable way respect to the control group. Data here obtained showed unequivocally the in vivo effects of RF-EMF on an animal model, excluding thermal outcomes and thus represents the starting point for more comprehensive studies on dose response effects of electromagnetic fields radiations consequences.

Bioimpedancemetry for the assessment of periodontal tissue inflammation: a numerical feasibility study.

In dentistry possible inflammatory episodes of oral cavity can be very frequent (periodontitis, mucositis, peri-implantitis) and they can have serious consequences. Indeed, peri-implantitis is still the principal cause of implant failure. Impedance values of biological tissues are related to the physiological/pathological state of the tissue itself. In fact, an inflamed site exhibits an impedance value lower than that of the corresponding healthy tissue. Based on these observations, the aim of this work is to determine if impedancemetric measurements are able to provide information about the inflammatory state of tissues. A numerical 3D model has been realized to simulate the measurement conditions present in the event of inflammation around a dental implant. The aim is to understand if it is possible to determine the presence of an inflamed tissue and to locate its site, so that the treatment could be specifically focused in that specific area. A simplified geometry reproducing the implant has been realized in order to validate the numerical model by means of experimental measurements. The obtained results are satisfactorily accurate, so the model can be considered reliable. Therefore, multiple simulations have been run on the original model to carry out a parametric study in terms of different conductivity values, different volumes of inflamed tissues and different measurement frequencies. The advantages and limits of such a method have been shown to properly define the main constraints for the system design.