Limits...
A distributed multiagent system architecture for body area networks applied to healthcare monitoring.

Felisberto F, Laza R, Fdez-Riverola F, Pereira A - Biomed Res Int (2015)

Bottom Line: In the last years the area of health monitoring has grown significantly, attracting the attention of both academia and commercial sectors.In this context, we present an open and distributed architecture based on a multiagent system for recognizing human movements, identifying human postures, and detecting harmful activities.Moreover, we also characterize its performance, enabling future analyses and comparisons with similar approaches.

View Article: PubMed Central - PubMed

Affiliation: Fundação Para a Ciência e a Tecnologia (FCT), Foundation for Science and Technology, 1249-074 Lisbon, Portugal ; Higher Technical School of Computer Engineering, University of Vigo, Polytechnic Building, Campus Universitario As Lagoas s/n, 32004 Ourense, Spain.

ABSTRACT
In the last years the area of health monitoring has grown significantly, attracting the attention of both academia and commercial sectors. At the same time, the availability of new biomedical sensors and suitable network protocols has led to the appearance of a new generation of wireless sensor networks, the so-called wireless body area networks. Nowadays, these networks are routinely used for continuous monitoring of vital parameters, movement, and the surrounding environment of people, but the large volume of data generated in different locations represents a major obstacle for the appropriate design, development, and deployment of more elaborated intelligent systems. In this context, we present an open and distributed architecture based on a multiagent system for recognizing human movements, identifying human postures, and detecting harmful activities. The proposed system evolved from a single node for fall detection to a multisensor hardware solution capable of identifying unhampered falls and analyzing the users' movement. The experiments carried out contemplate two different scenarios and demonstrate the accuracy of our proposal as a real distributed movement monitoring and accident detection system. Moreover, we also characterize its performance, enabling future analyses and comparisons with similar approaches.

Show MeSH

Related in: MedlinePlus

Examples of how the body stays after a hampered fall. In (a) the body fully slid of the wall ending in a laying position; in (b) the user ended in a sitting position but his posture is incorrect; in (c) the user slid to a sitting position fully supported by the wall.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4385603&req=5

fig13: Examples of how the body stays after a hampered fall. In (a) the body fully slid of the wall ending in a laying position; in (b) the user ended in a sitting position but his posture is incorrect; in (c) the user slid to a sitting position fully supported by the wall.

Mentions: The second cause for misclassifications is related to the similarities between a hampered fall and the sit-down action. This type of falls stays undetected when the sudden decelerations of the multiple impacts are similar to the decelerations of a rougher sit-down action. In a first testing stage, part of this limitation was corrected by taking into account the user's final orientation state. In this line, if the user was lying down or sitting, but in an incorrect sit-down position, the alert is sent. In the event the acceleration is very similar to a rougher sit-down action, and the user final orientation is consistent with a normal sitting position, the fall stays undetected (although the information is still sent to the remote server). Figure 13 shows some examples of the aforementioned after fall positions.


A distributed multiagent system architecture for body area networks applied to healthcare monitoring.

Felisberto F, Laza R, Fdez-Riverola F, Pereira A - Biomed Res Int (2015)

Examples of how the body stays after a hampered fall. In (a) the body fully slid of the wall ending in a laying position; in (b) the user ended in a sitting position but his posture is incorrect; in (c) the user slid to a sitting position fully supported by the wall.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4385603&req=5

fig13: Examples of how the body stays after a hampered fall. In (a) the body fully slid of the wall ending in a laying position; in (b) the user ended in a sitting position but his posture is incorrect; in (c) the user slid to a sitting position fully supported by the wall.
Mentions: The second cause for misclassifications is related to the similarities between a hampered fall and the sit-down action. This type of falls stays undetected when the sudden decelerations of the multiple impacts are similar to the decelerations of a rougher sit-down action. In a first testing stage, part of this limitation was corrected by taking into account the user's final orientation state. In this line, if the user was lying down or sitting, but in an incorrect sit-down position, the alert is sent. In the event the acceleration is very similar to a rougher sit-down action, and the user final orientation is consistent with a normal sitting position, the fall stays undetected (although the information is still sent to the remote server). Figure 13 shows some examples of the aforementioned after fall positions.

Bottom Line: In the last years the area of health monitoring has grown significantly, attracting the attention of both academia and commercial sectors.In this context, we present an open and distributed architecture based on a multiagent system for recognizing human movements, identifying human postures, and detecting harmful activities.Moreover, we also characterize its performance, enabling future analyses and comparisons with similar approaches.

View Article: PubMed Central - PubMed

Affiliation: Fundação Para a Ciência e a Tecnologia (FCT), Foundation for Science and Technology, 1249-074 Lisbon, Portugal ; Higher Technical School of Computer Engineering, University of Vigo, Polytechnic Building, Campus Universitario As Lagoas s/n, 32004 Ourense, Spain.

ABSTRACT
In the last years the area of health monitoring has grown significantly, attracting the attention of both academia and commercial sectors. At the same time, the availability of new biomedical sensors and suitable network protocols has led to the appearance of a new generation of wireless sensor networks, the so-called wireless body area networks. Nowadays, these networks are routinely used for continuous monitoring of vital parameters, movement, and the surrounding environment of people, but the large volume of data generated in different locations represents a major obstacle for the appropriate design, development, and deployment of more elaborated intelligent systems. In this context, we present an open and distributed architecture based on a multiagent system for recognizing human movements, identifying human postures, and detecting harmful activities. The proposed system evolved from a single node for fall detection to a multisensor hardware solution capable of identifying unhampered falls and analyzing the users' movement. The experiments carried out contemplate two different scenarios and demonstrate the accuracy of our proposal as a real distributed movement monitoring and accident detection system. Moreover, we also characterize its performance, enabling future analyses and comparisons with similar approaches.

Show MeSH
Related in: MedlinePlus