Cristian O. Lombardo

A Multisensor Data-Fusion Approach for ADL and Fall classification

This paper deals with an advanced approach for the monitoring of elders and people with neurological pathologies (e.g., Alzheimer). The system that adopts a multisensor approach is able to recognize critical events, such as falls or prolonged inactivity, to monitor the user posture, and to notify the alerts to caregivers. In particular, this paper focuses on smart algorithms developed for the activities of daily living (ADL) classification, which use the information provided by inertial sensors embedded in the user device. In particular, a novel multisensor data-fusion approach, combining data from an accelerometer and a gyroscope, is presented. Apart from alert management, the information provided by this system is useful to track the evolution of the user pathology, also during rehabilitation tasks. Results obtained during tests with users demonstrate suitable performances of the adopted paradigm, in terms of sensitivity and specificity, in performing falls and ADL classification tasks. The average value of the sensitivity index for the classes of falls and ADL considered through this paper is 0.81, while the average value of the specificity index is 0.98.

An advanced tracking solution fully based on native sensing features of smartphone

This paper deals with an advanced multi-sensor approach for the implementation of a tracking system exploiting sensing and processing features embedded in smartphone devices. In particular, a methodology based on advanced data fusion paradigms assuring an efficient heading estimation has been developed. The main advantage of the solution proposed resides in the possibility to correctly perform heading estimation also in the presence of serious environmental influence due to magnetic field distortion. Among possible application contexts, the proposed system would be particularly suitable for the development of mobility assistive systems for a safe and efficient exploration of educational/job environments by weak people.

An Event Polarized Paradigm for ADL Detection in AAL Context

The possibility to detect activities of daily living (ADLs), with particular regards to fall detection, is mandatory to implement a rigorous remote monitoring of frail people. Actually, unintentional falls cause a lot of hospitalizations and may lead to serious consequence due to long-lie happenings. Moreover, the ability to properly classify different kinds of falls could represent a strategic diagnostic tool. The widespread use of smartphones equipped with many embedded sensors would represent a suitable solution for ADL monitoring, especially for the future generation of elderly. The activity presented through this paper focuses on the development of a fully smartphone-based ADL detector, which uses an advanced classification paradigm to discriminate between different kinds of falls. The sensitivity and specificity features of the system are in line with the real needs of the Ambient Assisted Living context.

RESIMA: An Assistive Paradigm to Support Weak People in Indoor Environments

This paper deals with the RESIMA architecture developed to assist people with sensory disability in indoor environments, with particular regard to the visually impaired. With respect to solutions presented in the state-of-the-art, RESIMA is a smart multisensor assistive system which, exploiting a high resolution monitoring of the user position in the spatial-temporal domain as well as a deep inertial monitoring of the user status, assures a reliable and continuous form of assistance. The system is based on a wireless sensor network and smart paradigms, which extract relevant information from data collected through the multisensor architecture to manage interactions between the user and the environment itself. This paper mainly focuses on the multisensor system architecture and smart paradigms for the user localization and the user-environment interaction (UEI). Real experiments, performed by good health users, demonstrate an accuracy of the positioning system of about 3.9 cm and a suitable rate of success probability associated to the UEI functionality embedded in the RESIMA architecture.

RESIMA: A new WSN based paradigm to assist weak people in indoor environment

This paper deals with the RESIMA architecture developed to assist people in performing daily activity in indoor environment. As respect to solutions presented in the SOTA, RESIMA is a smart multi-parametric assistive system which performs a high resolution monitoring of the user position in the spatial-temporal domain as well as a deep inertial monitoring of the user status, thus assuring a reliable and continuous form of assistance to weak users. The system is based on a Wireless Sensor Network and smart paradigms which extract relevant information from data collected through the multi-sensor architecture. The paper mainly focuses on the multi-sensor system architecture and smart paradigms used to implement user localization. Positioning system accuracy of about 3 cm has been obtained while the system shows good reproducibility and reliability.

A Low-Cost Accelerometer Developed by Inkjet Printing Technology

In this paper, an inkjet-printed sensor in the mesoscale is presented with the aim to investigate its behavior as an accelerometer in the low-frequency domain (up to 20 Hz), which properly fits with the need of typical applications in the field of human and seismic monitoring. The accelerometer consists of a Polyethylene terephthalate membrane clamped by four spring legs to a fixed support. The sensing readout strategy is implemented through four strain gauges directly printed onto the flexible substrate. The advantages of the approach proposed are mainly related to the adopted low-cost direct printing technology, which allows for the realization of cheap and customizable devices. The sensor behavior has been deeply investigated. The device responsivity and resolution are 9.4 mV/g and 0.126 g, respectively, at 10 Hz, and 41.0 mV/g and 0.003 g, respectively, at 35 Hz. The performances obtained encourage the development of the all-inkjet-printed sensor proposed, especially taking into account its low cost and disposable features.

An inkjet printed seismic sensor

In this paper an inkjet printed sensor in the mesoscale is presented with the aim to investigate its behavior as accelerometer in the low frequency domain typical of inertial stimuli coming from human caused and seismic phenomena. The accelerometer consists of a PET membrane clamped by four spring-legs to a fixed support. The sensing readout strategy is implemented through four inkjet printed strain gauges. Advantages of the approach proposed are mainly related to the low frequency operation due to the flexible membrane and the proof mass adopted. Moreover, the adopted low cost direct printing technology allows for the realization of the strain gauges directly into the PET membrane. The device has been characterized and shows good performances especially taking into account its low cost and disposable characteristics.

An Electronic Cane with a Haptic Interface for Mobility Tasks

There are numerous electronic solutions to help visually impaired in mobility tasks in everyday life. Although many of these systems correctly detect obstacles and locate services, thus improving the life of visually impaired people, generally the information provided by these systems is codified arbitrarily, thus requiring a learning phase and therefore discourages their use. This paper proposes an haptic approach to provide information about the presence of obstacles along the walking path that can be easily understood by the users. The aim of the proposed system is to reproduce the feeling provided by a traditional white cane, but using a short cane equipped with a smart system of sensors and actuators.

Smart homecare technologies for the visually impaired: recent advances

License. The full terms of the License are available at http://creativecommons.org/licenses/by-nc/3.0/. Non-commercial uses of the work are permitted without any further permission from Dove Medical Press Limited, provided the work is properly attributed. Permissions beyond the scope of the License are administered by Dove Medical Press Limited. Information on how to request permission may be found at: http://www.dovepress.com/permissions.php Smart Homecare Technology and TeleHealth 2015:3 9–16 Smart Homecare Technology and TeleHealth Dovepress

Telemetric Technique for Wireless Strain Measurement From an Inkjet-Printed Resistive Sensor

Strain monitoring allows obtaining critical information regarding the conditions of several systems. It would help, for example, to avoid possible structural damages. However, not all the existing devices are suitable to accomplish this task for a great number of applications, because of the characteristics of measurement environment, which prevent the use of batteries or wired connections. The use of telemetric devices may overcome these limitations, since they rely on the magnetic coupling between two inductors for wireless sensor supply and data transmission. The work treated in this paper presents a technique that permits us to calculate the output of a resistive strain gauge from a measurement of system impedance phase performed at a specific frequency, when distance between the inductors is fixed. We validated the method using a real device working with a low-cost sensor fabricated through inkjet-printing technology on a flexible substrate. We applied successive deformations, until 1% of sensor length at rest position. Calculated strain presents a percentage deviation from measured values going from 0.7% to 7%, whereas the highest uncertainty is 0.02% of sensor length at rest. Experimental results put in evidence, on one hand, the potential of inkjet printing to fabricate valid sensing elements and, on the other hand, that the proposed approach is successful in strain estimation.