Gabriele Rescio | Consiglio Nazionale delle Ricerche (CNR) (original) (raw)

Uploads

Papers by Gabriele Rescio

Lecture notes in electrical engineering, 2019

Journal of Manufacturing Systems, 2022

Sensors, Apr 1, 2022

This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY

Sensors, May 28, 2023

Lecture notes in electrical engineering, 2017

Falls are very dangerous events among elderly people. Several automatic fall detectors have been ... more Falls are very dangerous events among elderly people. Several automatic fall detectors have been developed to reduce the time of the medical intervention, but they cannot avoid the injures due to the fall. The purpose of this study has been to identify a computational framework for the real-time and automatic detection of the fall risk, allowing the fast adoption of properly intervention strategies, to reduce injuries and traumas due to falls. A wearable, wireless and minimally invasive surface Electromyography (EMG)-based system has been used to measure four lower-limb muscles activities. Eleven young healthy subjects have simulated several fall events (through a movable platform) and normal Activities of Daily Living (ADLs) and their patterns have been analyzed. Highly discriminative features extracted within the EMG signals for the pre impact fall evaluation have been explored and a threshold-based approach has been adopted, assuring the real-time functioning. The threshold level for each feature has been set to distinguish an instability condition from normal activities. The proposed system seems able to recognize all falls with an average lead-time of 840 ms before the impact, in simulated and controlled fall conditions.

ABSTRACT Falling down events can cause trauma, disability and death among older people. Accelerom... more ABSTRACT Falling down events can cause trauma, disability and death among older people. Accelerometer-based devices are able to detect falls in controlled environments. This kind of solution often presents poor performance in real conditions. The aim of this work is the development of a computationally low-cost algorithm for feature extraction and the implementation of a Machine Learning scheme for people fall detection, by using a tri-axial MEMS wearable wireless accelerometer. The proposed approach allows to generalize the detection of fall events in several practical conditions. It appears invariant to the age, weight, height of people and to the relative positioning area (even in the upper part of the waist), overcoming the drawbacks of well-known threshold-based approaches in which several parameters need to be manually estimated according to the specific features of the end-user. In order to limit the workload, the specific study on posture analysis has been avoided and a polynomial kernel function is used while maintaining high performance in terms of specificity and sensitivity. The supervised clustering step is achieved by implementing an One-Class Support Vector Machine classifier in a stand-alone PC.

This paper presents a low-dropout voltage regulator capable of delivering ±5 mA to the load with ... more This paper presents a low-dropout voltage regulator capable of delivering ±5 mA to the load with a quiescent current as low as 8 μA and a temperature coefficient equal to 7-ppm/°C, over a temperature range from -40 °C to +125 °C. The output voltage can be either 1.25 V or 1.8 V, while the input voltage can range from 1.8 V to 5.5 V. The bipolar output current is achieved by using a class-AB error amplifier with a quiescent current control circuit based on a translinear loop. The low temperature coefficient is guaranteed by a current mode bandgap circuit with curvature compensation.

The vital signs monitoring is very useful to detect medical diseases. The paper presents an open,... more The vital signs monitoring is very useful to detect medical diseases. The paper presents an open, flexible, wireless and portable platform for monitoring vital signs in the healthcare scenarios, both indoor and outdoor. The platform has been designed in order to overcome the limitations of well-known technologies for mobile architectures, such as the battery lifetime and the lack of the open source codes. To reduce these issues the platform integrates the fast, easy-to-use, safe and low-power Near Field Communication protocol for data transmission in proximity, addressing the Internet of Things paradigm. The platform uses the Arduino NANO board and the related open source software libraries, so it could be possible to add new functionalities in a fast way. The first prototype of the platform has been customized for human body temperature measurement by using the digital TMP100 temperature sensor. However, a real “ecosystem” of portable devices could be prototyped with low-effort for the acquisition/transmission of other kind of clinical signs such as heart-rate, breath-rate, ECG.

Sarcopenia is a disorder characterized by a loss of muscle mass and muscle strength. It is associ... more Sarcopenia is a disorder characterized by a loss of muscle mass and muscle strength. It is associated with the natural ageing process, as well as geriatric medical conditions and bed rest. Consequently, it is very beneficial from a medical point of view to periodically monitor patients at risk of developing sarcopenia to early detect its onset or progression through objective and specific indicators. In the last years, surface electromyography (sEMG) increasingly plays an important role for prevention, diagnosis, and rehabilitation in this research area. Moreover, the recent progresses in EMG technologies have allowed for the development of low invasive and reliable smart EMG-based wearable device. The paper presents the design and implementation of an integrated platform that includes a sEMG based wearable device and interfacing with a processing software for clinical monitoring and management of the pathology. The system has been designed to both preventive (early diagnosis) and monitoring purposes of the patient's condition over time. Here, we present a preliminary study on the feasibility of the developed platform for management of sarcopenia. Specifically, this work deals with the identification of the best trade-off between sampling frequency of the EMG signals and variance of the highly discriminative features extracted within the EMG signals for the automatic measurement of sarcopenia.

AbstractIn this paper we present a wearable wireless accelerometer device for people fall detect... more AbstractIn this paper we present a wearable wireless accelerometer device for people fall detection in ambient assisted living (AAL) applications, communicating with care holders and relatives of the assisted person through an ADSL based gateway. The wearable system is ...

Springer eBooks, Oct 25, 2013

Fall events can cause trauma, disability and death among older people. Accelerometer-based device... more Fall events can cause trauma, disability and death among older people. Accelerometer-based devices are able to detect falls in controlled environments. The paper presents a computationally low-power approach for feature extraction and supervised clustering for people fall detection by using a 3-axial MEMS wearable accelerometer, managed by an stand-alone PC through ZigBee connection. The paper extends a previous work in which fall events were detected according to a threshold-based scheme. The proposed approach allows to generalize the detection of falls in several practical conditions, after a short period of calibration. The clustering scheme appears invariant to age, weight, height of people and relative positioning area (even in the upper part of the waist), overcoming the drawbacks of well-known threshold-based approaches in which several parameters need to be manually estimated, according to the specific features of the end-user. In order to limit the workload, the specific study on posture analysis has been avoided and a polynomial kernel function is used while maintaining high performance in terms of specificity and sensitivity. The supervised clustering step is achieved by implementing an One-Class Support Vector Machine classifier.

Lecture notes in electrical engineering, Sep 9, 2017

The chapter presents a study on an electromyography-based wearable system for fall risk assessmen... more The chapter presents a study on an electromyography-based wearable system for fall risk assessment. It has been focused especially on the electrical activity analysis of the user’s lower limb muscles in relation to his body movement. For that purpose four wireless electromyography probes (sEMG) have been placed on the Gastrocnemius/Tibialis muscles and an accelerometer-equipped t-shirt has been worn during the Activities of Daily Living (ADLs) and fall events simulations. The results obtained have shown that the simultaneous contraction of the muscles considered appear relevant immediately after the starting of the imbalance condition, when the vertical velocity of the user’s body is too low for the commonly used inertial-based pre-fall detection systems. So an sEMG-based platform should be suitable to realize a more efficient platform to prevent the injures due to the fall. The mean lead-time measured, in controlled condition, is more than 750 ms with performance in terms of sensitivity and specificity more than 75%.

In factories of the future, advanced automation systems (e.g., cobots, exoskeletons, cyber physic... more In factories of the future, advanced automation systems (e.g., cobots, exoskeletons, cyber physical systems) will reduce the physical effort of workers and compensate their limitations as well as ensure more flexibility, agility, and competitiveness. However, the activities of the operator 4.0 will entail an increased share of complex cognitive tasks. Therefore, monitoring the mental load will be increasingly important to ensure work environments that promote healthy life and wellbeing for all at all ages. For this aim, this paper proposes a framework to analyze heart rate, galvanic skin response and electrooculogram signals in order to extract features able to detect an excessive stress or cognitive load. Two wearable devices are used: Empatica E4 wristband and J!NS MEME electrooculography glasses. The proposed framework has been experimented through a laboratory test focused on LEGO brick-based simulations of manufacturing activities.

Computers in Industry, Jun 1, 2023

Sensors, Jan 16, 2023