Skip to main page content
Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2014 Aug 12;14(8):14765-85.
doi: 10.3390/s140814765.

Active In-Database Processing to Support Ambient Assisted Living Systems

Affiliations
Free PMC article

Active In-Database Processing to Support Ambient Assisted Living Systems

Wagner O de Morais et al. Sensors (Basel). .
Free PMC article

Abstract

As an alternative to the existing software architectures that underpin the development of smart homes and ambient assisted living (AAL) systems, this work presents a database-centric architecture that takes advantage of active databases and in-database processing. Current platforms supporting AAL systems use database management systems (DBMSs) exclusively for data storage. Active databases employ database triggers to detect and react to events taking place inside or outside of the database. DBMSs can be extended with stored procedures and functions that enable in-database processing. This means that the data processing is integrated and performed within the DBMS. The feasibility and flexibility of the proposed approach were demonstrated with the implementation of three distinct AAL services. The active database was used to detect bed-exits and to discover common room transitions and deviations during the night. In-database machine learning methods were used to model early night behaviors. Consequently, active in-database processing avoids transferring sensitive data outside the database, and this improves performance, security and privacy. Furthermore, centralizing the computation into the DBMS facilitates code reuse, adaptation and maintenance. These are important system properties that take into account the evolving heterogeneity of users, their needs and the devices that are characteristic of smart homes and AAL systems. Therefore, DBMSs can provide capabilities to address requirements for scalability, security, privacy, dependability and personalization in applications of smart environments in healthcare.

Figures

Figure 1.
Figure 1.
(a) Existing infrastructures supporting smart environments and AAL systems perform data processing at different layers; (b) in the proposed database-centric architecture, the reactive behavior and data processing are integrated and performed within the database management system (DBMS). Notation: ADB, active database; DB, database; In-DB, in-database processing, HW, hardware; UI, user interface.
Figure 2.
Figure 2.
Example of a sensor setup for a given home environment. PIR denotes passive infrared motion sensors; the magnet to capture door openings; the bed sensor to detect bed exits; the resident wears a social alarm. A load cell to measure weight is placed on the top-left leg support of the bed.
Figure 3.
Figure 3.
The proposed system architecture, including resource adapters and the active database. Notation: UI, user interface; UDFs, user-defined functions; IPC, inter-process communication.
Figure 4.
Figure 4.
A cut-off value can separate the standard deviation of the measured weight signal into in-bed signals and out-of-bed signals.
Figure 5.
Figure 5.
Bed entrances and exits are accurately detected by the active rule, while the bed-exit detection provided by the Emfit Bed Sensor misses bed exits or generates nonexistent bed exits. Because the sensors were active from 10 p.m. until 6 a.m., it was not possible to detect when the individual went to bed or when he left. TL LC denotes top-left load cell.
Figure 6.
Figure 6.
Transition probabilities (p) of events for a confidence threshold of 0.2. Mean (μt) and standard deviation (σt) of the transition time (normally distributed).
Figure 7.
Figure 7.
A decision tree distinguishes different time periods during the night. Notation: Ba, bathroom; K, kitchen; H, hallway; L, living room; I, inactivity; D, door openings; Bin, bed entrances; Bout, bed exit; N, lack of events. TPI, Time Period I; !TPI, not Time Period I.

Similar articles

See all similar articles

References

    1. De Morais W.O., Lundström J., Wickström N. Ambient Assisted Living and Active Aging. Springer; Berlin, Germany: 2013. A Database-Centric Architecture for Home-Based Health Monitoring; pp. 26–34.
    1. Tarricone R., Tsouros A.D. Home Care in Europe: The Solid Facts. WHO Regional Office; Copenhagen, Denmark: 2008.
    1. Malmberg B., Ernsth M., Larsson B., Zarit S.H. Angels of the night: Evening and night patrols for homebound elders in Sweden. Gerontologist. 2003;43:761–765. - PubMed
    1. Thörner R., Persson M., Eriksson H., Isaksson A., Lundström J. Technical Report, Centre for Health Technology in Halland. Halmstad University; Halmstad, Sweden: 2011. Trygg om natten. (In Swedish)
    1. United Nations, Department of Economic and Social Affairs, Population Division World Population Prospects: The 2012 Revision, Key Findings and Advance Tables (Working Paper No. ESA/P/WP.227) [(accessed on 16 December 2013)]. Available online: http://esa.un.org/wpp/index.htm.
Feedback