Behavior Drift Detection Based on Anomalies Identification in Home Living Quantitative Indicators

Abstract

Home Automation and Smart Homes diffusion are providing an interesting opportunity to implement elderly monitoring. This is a new valid technological support to allow in-place aging of seniors by means of a detection system to notify potential anomalies. Monitoring has been implemented by means of Complex Event Processing on live streams of home automation data: this allows the analysis of the behavior of the house inhabitant through quantitative indicators. Different kinds of quantitative indicators for monitoring and behavior drift detection have been identified and implemented using the Esper complex event processing engine. The chosen solution permits us not only to exploit the queries when run "online", but enables also "offline" (re-)execution for testing and a posteriori analysis. Indicators were developed on both real world data and on realistic simulations. Tests were made on a dataset of 180 days: the obtained results prove that it is possible to evidence behavior changes for an evaluation of a person's condition.

Literary Revision of Ambient Inteligence for the Care of the Elderly at Smart Homes

“…These are the data that the software most considers in the course of the day to day to provide an exemplary assisted life. The main idea is to provide independence to the elder, so in the end, all that these devices can provide is an alarm signal to stakeholders, as well as some entities such as police or health system facilities [21], [22], [23]. the subject's behaviors can help to identify emergencies depending on where and when they are performed [24], [25], [26] because it is known that not all people carry out their activities at the same time or in the same way.…”

Supporting Alzheimer’s Residential Care - A Novel Indoor Localization System

“…Moreover, a constant monitoring may be useful to obtain a complete analysis comprising medical data resulting from clinical exams (e.g., electrical activity of the heart, blood pressure, oxygen saturation), medical history and also an extremely accurate description of the activities performed as a daily routine. This type of monitoring is at the basis of behavioral drifts' analysis (Veronese et al, 2018); changes in human behavior, such as changes in the attendance of environments or in the order of execution of daily activities could be automatically recognized by the system and reported to caregivers. A crucial aspect of this analysis is the collection of data that must be carried out in a non-invasive but constant way: a progression of the disease may lie behind a change in the patient's daily routine.…”

Mathematical Criteria for a Priori Performance Estimation of Activities of Daily Living Recognition

“…Moreover, some works focus on metrics to evaluate the deviation of behavior [ 29 , 30 , 31 ]. Therefore, these works mainly focus on temporal criteria, and only focus on these for the deviation.…”