1,720,995 research outputs found
ODINS: On-Demand Indoor Navigation System RFID Based
No full textThis paper presents an On-Demand Indoor Navigation System (ODINS) based on RFID technology. ODINS is a distributed infrastructure where a set of information points (Fixed Stations-FS) provides the direction to a user who has to reach the destination point he/she has previously selected. ODINS system is proposed for residencies hosting people with mild cognitive disabilities and elderly but it can be also applied to structures where people could be disoriented. The destination is configured at some reception points or it is a predefined (e.g. the bed room or a selected 'safe' point). The destination is associated with a RFID disposable bracelet assigned to her/him. The path is algorithmically computed and spread to all FSs. Every time the user is disoriented, she/he can search for the closest FS that displays the right directition. FSs should be located in strategic positions and provide a user-friendly interface such as bright arrows. The complexity is 'system-side' making ODINS usable for everyone
Classifying Alzheimer’s wandering and apathetic behaviours using indoor and outdoor localization data
Full text linkDementia, especially Alzheimer’s disease, is increasing due to population ageing and is projected to nearly triple by 2050. Understanding and identifying common behaviours such as apathy, depression, and wandering can enable caregivers and medical professionals to enhance the quality of care for patients and implement appropriate interventions to mitigate cognitive decline. This paper analyses localization data collected from patients with mild cognitive impairment and Alzheimer’s disease residing in a healthcare facility. In particular, metrics and behavioural indices are computed to classify the behaviour of individuals. The proposed method was initially applied to the localization data of seven residents, each exhibiting distinct behaviours. Subsequently, validation was conducted using data from 46 patients monitored over three months. Classification results were compared with the observations made by healthcare operators and physicians. The study demonstrated a high level of accuracy in classifying patients into different behavioural domains, such as wandering and depressed–apathetic, with 42 out of 46 cases correctly classified
Sleep Monitoring: Enriching the Traditional Approach by Sensor-collected Data
No full textThis paper describes a new approach to studying sleep quality. The approach combines subjective (obtained through paper questionnaires) and objective (obtained through sensors) measures to monitor sleep quality more accurately and easily.We consider some of the major measures traditionally used to monitor sleep quality, such as PSQI (Pittsburgh Sleep Quality Index); we then introduce a general architecture of the approach to collect, in a hybrid way, data from paper questionnaires (via a mobile application) and sensors. We validate the approach considering the PSQI questionnaire and identify different questions for which we analyze data obtained from a bed sensor (Murata SCA11H) located under the mattress.We collect over a two-month long period both subjective and objective measures and compare the measures considering different questions of the PSQI questionnaire (the questionnaire, referred to a one-month long period, is collected every two weeks). Results confirm the feasibility of the proposed approach. This hybrid approach is expected to lead to a richer dataset, helpful in identifying sleeping disorders and monitoring the overall quality of sleep. Moreover, the approach helps the patient to fill in already validated paper questionnaires, by estimating their answers analyzed through the patterns detected in the data from the sensors
NeeMAS: A Need-Based Multi-agent Simulator of Human Behavior for Long-Term Drifts in Smart Environments
No full textEarly identification of long-term changes in the behaviour of people monitored with smart environment solutions is essential to prevent health decline. However, data collection and analysis of human behaviour are challenging and time-consuming.
A potential solution consists in creating digital twins of the individuals to replicate the typical behaviours for advanced data analytics. The Assistive Technology Group (ATG) at Politecnico di Milano has developed NeeMAS (NEEd-based Multi-Agent Simulator), a novel simulator that effectively simulates human behaviour with physiological and social needs, cognitive decay, and behavioural drifts due to ageing or disease onset such as apathy or depression.
NeeMAS simulates a senior care facility with several individuals, spending part of their time in their rooms and in part sharing common indoor and outdoor spaces interacting with other people. Experimental results show the feasibility and flexibility of the proposed approach for the generation of typical human behaviours and their drifts
SMED: SMart Chair for Emotion Detection
No full textThe paper presents the concept of SMED, a smart chair designed for real-time monitoring of patients’ vital signs like heart rate and respiratory rate and a functional prototype developed to evaluate the effectiveness of the concept. The prototype leverages a strain gauge system integrated into a harmonic steel to detect changes in body pressure and vibrations. Physiological data of interest are obtained using the ballistocardiography methodology. The final goal of this work is to enhance the quality of care and support for individuals with Autism Spectrum Disorder (ASD) who face difficulties in communicating their emotions, stress and discomfort, during medical or dental visits
Monitoring Dressing Autonomy: A Remote Home Care RFID-Based Solution for People with Dementia
Full text linkThe number of elder people with dementia is steadily increasing, and so is the need for solutions to support remote home care and to facilitate “aging in place”. People affected by dementia often need assistance with daily self-care tasks such as dressing, eating, and bathing. Our focus is on the dressing activity: we analyze the requirements and propose a system that leverages RFID-based technology to support individuals in dressing appropriately, let the individuals reside at home or in assisted living facilities. The system exploits RFID tags, fixed or ironed onto the person’s clothes, and antennas to read and collect data from the tags. The system detects the user’s outfit, eventually providing the individual with immediate feedback and alerting the caregiver. We compare two different RFID technologies: one operating at 13.56 MHz (HF)—commonly adopted in the literature—and one at 868 MHz (UHF). An in-depth analysis of the RFID technology for detecting worn clothes is reported, considering the scenario where the antennas are positioned on one side of a door to achieve comprehensive detection coverage of the entire body
Preventing Muscle Imbalance: A Cost-Effective Solution for Home Exercise
No full textThis paper proposes a low-cost system to help users perform exercises at home, monitoring muscle imbalances. Muscle imbalance occurs when there is a strength disparity between muscles on one side of the body or one side of a joint.
The proposed device detects asymmetries in exercises involving the lower limbs, employing two slim insoles equipped with only three pressure sensors positioned along the foot, one on the heel and two in the front. The data collected by these sensors are wirelessly transmitted to a user-friendly interface, which serves as a guide, assisting users in achieving more balanced and symmetrical training, important for maintaining musculoskeletal health and enhancing overall physical well-being. The paper presents an analysis of relevant literature, introduces the device and its characteristics, and presents the physical prototype and its experimental results
Quantitative Indicators for Behaviour Drift Detection from Home Automation Data
No full textSmart Homes diffusion provides an opportunity to implement elderly monitoring, extending seniors' independence and avoiding unnecessary assistance costs. Information concerning the inhabitant behaviour is contained in home automation data, and can be extracted by means of quantitative indicators. The application of such approach proves it can evidence behaviour changes
BigEar: Ubiquitous Wireless Low-Budget Speech Capturing Interface
Full text linkThis article presents BigEar, a wireless low-cost speech capturing interface that aims to realize unobtrusive and transparent context-aware vocal interaction for home automation. The speech recognition process implemented in BigEar system considers noise sources including possible holes in the reconstructed audio stream and tries to overcome them by means of inexactness toleration mechanisms to improve intelligibility of the reconstructed signal. Key contribution of this work is the use of extremely low cost devices to realize a modular flexible and real-time wireless sensor network. On-field implementation and experiments show that the proposed solution can perform real-time speech reconstruction, while listening tests confirm the intelligibility of the reconstructed signal
A Multi-Resident Number Estimation Method for Smart Homes
Full text linkPopulation aging requires innovative solutions to increase the quality of life and preserve autonomous and independent living at home. A need of particular significance is the identification of behavioral drifts. A relevant behavioral drift concerns sociality: older people tend to isolate themselves. There is therefore the need to find methodologies to identify if, when, and how long the person is in the company of other people (possibly, also considering the number). The challenge is to address this task in poorly sensorized apartments, with non-intrusive sensors that are typically wireless and can only provide local and simple information. The proposed method addresses technological issues, such as PIR (Passive InfraRed) blind times, topological issues, such as sensor interference due to the inability to separate detection areas, and algorithmic issues. The house is modeled as a graph to constrain transitions between adjacent rooms. Each room is associated with a set of values, for each identified person. These values decay over time and represent the probability that each person is still in the room. Because the used sensors cannot determine the number of people, the approach is based on a multi-branch inference that, over time, differentiates the movements in the apartment and estimates the number of people. The proposed algorithm has been validated with real data obtaining an accuracy of 86.8%
- …
