Attention-Based Health Monitoring

Attention-Based Health Monitoring

Zenonas Theodosiou (Department of Communication and Internet Studies, Cyprus University of Technology, Limassol, Cyprus) and Nicolas Tsapatsoulis (Department of Communication and Internet Studies, Cyprus University of Technology, Limassol, Cyprus)
DOI: 10.4018/ijmstr.2013070105
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

The application of mobile technologies for health monitoring has garnered great attention during the last years. The sensors together with a mobile device form a personal area network that monitors the patient’s health status. It gives advice to the patient, adjusts the environmental conditions according to the patient’s needs, and in the case of an emergency, notifies the patient’s doctor or the corresponding medical center. In the current work the authors present a new attention-based architecture for health monitoring emphasizing on the identification of attention seeking and dangerous health states. The experimental results indicate that the proposed architecture responses very fast to the changes of the patient’s biosignals and accurately in decisions concerning the patient’s health status.
Article Preview

Introduction

In recent years, mobile technologies are increasingly permeating in every aspect of our personals lives. The key advantage of mobile applications over the desktop ones is the combination of the mobility with 24/7 multi connectivity in order to deliver contextualized functionalities (Emmanouilides, 2013). There is a wide range of m-applications and m-market is expected to be worth $25 billion by the end of 2015 (ABI research, 2010). The use of mobile devices to provide health information, known as “m-health”, has gained great attention for supporting public health and clinical care (Krishna, 2009; Kaplan 2006). Such applications to existing health care delivery and monitoring systems offer great promise for improving the quality of life (Kahn, 2010). They allow healthcare professionals to monitor the health condition of a patient and to act upon indications of an abnormal state at any time and at any place (Broens, 2007).

These applications offer context-aware responses (Unhelkar & Murugesan, 2010) for their patients by automatically adapting to their changing contexts (Hong, 2009). Context aware systems are able to adapt their operations to the current context without explicit patient intervention and thus aim at increasing usability and effectiveness by taking environmental context into account (Baldauf, 2007). Context is any information that can be used to characterize the situation of an entity, while an entity can be a person, place or object that is relevant to the interaction between patients and application, including location, time, activities, and the preferences of each entity (Dey, 2001). Mobile devices are typically equipped with sensors that enable the development of context-aware software applications (Liu, 2011).

The context data capturing is very important when designing context-aware systems since it predefines the architectural style of the system at least to some extend (Baldauf, 2007). Several frameworks have been proposed that capture context information from sensors or high level models of context information (Devaraju, 2007).

Chen (2004) states three different context acquisition methods. The first method refers to direct sensor access where the sensors are integrated into the devices and the client software collects the desired information directly from these sensors. The second method includes middle-ware infrastructure that facilitates the low-level sensing details. The context acquisition middle-ware is built into the hosting device that the context-aware application is operated. The third method allows multiple access to remote data resources by introducing a context server and overcomes the drawbacks of the limited computing resource.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 5: 4 Issues (2017): 2 Released, 2 Forthcoming
Volume 4: 4 Issues (2016)
Volume 3: 4 Issues (2015)
Volume 2: 4 Issues (2014)
Volume 1: 4 Issues (2013)
View Complete Journal Contents Listing