Artificial Intelligence applied to Structural Health Monitoring (SHM) has provided considerable advantages in the accuracy and quality of the estimated structural integrity. Nevertheless, several challenges still need to be tackled in the SHM field, which extended the monitoring process beyond the mere data analytics and structural assessment task. Besides, one of the open problems in the field relates to the communication layer of the sensor networks since the continuous collection of long time series from multiple sensing units rapidly consumes the available memory resources, and requires complicated protocol to avoid network congestion. In this scenario, the present work presents a comprehensive framework for vibration-based diagnostics, in which data compression techniques are firstly introduced as a means to shrink the dimension of the data to be managed through the system. Then, neural network models solving binary classification problems were implemented for the sake of damage detection, also encompassing the influence of environmental factors in the evaluation of the structural status. Moreover, the potential degradation induced by the usage of low cost sensors on the adopted framework was evaluated: Additional analyses were performed in which experimental data were corrupted with the noise characterizing MEMS sensors. The proposed solutions were tested with experimental data from the Z24 bridge use case, proving that the amalgam of data compression, optimized (i.e., low complexity) machine learning architectures and environmental information allows to attain high classification scores, i.e., accuracy and precision greater than 96% and 95%, respectively.

The aim of this work is to present a preliminary study for the design of a digital auscultation system, i.e., a novel wearable device for patient chest auscultation and a digital stethoscope. The development and testing of the electronic stethoscope prototype is reported with an emphasis on the description and selection of sound transduction systems and analog electronic processing. The focus on various microphone technologies, such as micro-electro-mechanical systems (MEMSs), electret condensers, and piezoelectronic diaphragms, intends to emphasize the most suitable transducer for auscultation. In addition, we report on the design and development of a digital acquisition system for the human body for sound recording by using a modular device approach in order to fit the chosen analog and digital mics. Tests were performed on a designed phantom setup, and a qualitative comparison between the sounds recorded with the newly developed acquisition device and those recorded with two commercial digital stethoscopes is reported.

Condition Monitoring (CM) is an extremely critical application of the Internet of Things (IoT) within Industry 4.0 and Smart City scenarios, especially following the recent energy crisis. CM aims to monitor the status of a physical appliance over time and in real time in order to react promptly when anomalies are detected, as well as perform predictive maintenance tasks. Current deployments suffer from both interoperability and management issues within their engineering process at all phases – from their design to their deployment, to their management –, often requiring human intervention. Furthermore, the fragmentation of the IoT landscape and the heterogeneity of IoT solutions hinder a seamless onboarding process of legacy devices and systems. In this paper, we tackle these problems by first proposing an architecture for CM based on both abstraction layers and toolchains, i.e ., automated pipelines of engineering tools aimed at supporting the engineering process. In particular, we introduce four different toolchains, each of them dedicated to a well-defined task ( e.g ., energy monitoring). This orthogonal separation of concerns aims to simplify both the understanding of a complex ecosystem and the accomplishment of independent tasks. We then illustrate our implementation of a complete CM system that follows said architecture as a real Structural Health Monitoring (SHM) pilot of the Arrowhead Tools project, by describing in detail every single tool that we developed. We finally show how our pilot achieves the main objectives of the project: the reduction of engineering costs, the integration of legacy systems, and the interoperability with IoT frameworks.

This paper reports the architecture of a low-cost smart crutches system for mobile health applications. The prototype is based on a set of sensorized crutches connected to a custom Android application. Crutches were instrumented with a 6-axis inertial measurement unit, a uniaxial load cell, WiFi connectivity, and a microcontroller for data collection and processing. Crutch orientation and applied force were calibrated with a motion capture system and a force platform. Data are processed and visualized in real-time on the Android smartphone and are stored on the local memory for further offline analysis. The prototype’s architecture is reported along with the post-calibration accuracy for estimating crutch orientation (5° RMSE in dynamic conditions) and applied force (10 N RMSE). The system is a mobile-health platform enabling the design and development of real-time biofeedback applications and continuity of care scenarios, such as telemonitoring and telerehabilitation.

The development of an instrumented patellar prosthesis, able to measure the contact forces at the patellofemoral joint, can significantly aid in investigating the causes of total knee arthroplasty failures due to patellar complications. This study focuses on developing and validating an instrumented patellar prosthesis to measure contact forces in the patellofemoral joint. A piezoresistive force sensor was characterized and integrated into a conditioning circuit, with the aim of its implementation in the prosthesis. To measure medial and lateral forces independently, the sensors were trimmed in half. Compression tests (up to 2000 N) assessed sensor performance in terms of linearity (R² = 0.998 intact vs. 0.989 trimmed), repeatability (0.9% intact vs. 0.8% trimmed), and accuracy (1.7% intact vs. 2.3% trimmed) for forces up to 250 N. Higher force levels resulted in increased errors, but at a rate still comparable to that of existing sensors in the literature. Key considerations for the design of the instrumented prosthesis, such as minimizing point and shear loads, were identified. A prototype prosthesis capable of housing the sensor was proposed. The integrated system shows potential for improving the understanding of Total knee arthroplasty (TKA) failures through in vitro studies and could serve as an intraoperative tool for the evaluation of bone resections.