Abstract—The handshake gesture is an important part of the social etiquette in many cultures. It lies at the core of many human interactions, either in formal or informal settings: exchanging greetings, offering congratulations, and finalizing a deal are all activities that typically either start or finish with a handshake. The automated detection of a handshake can enable wide range of pervasive computing scanarios; in particular, different types of information can be exchanged and processed among the handshaking persons, depending on the physical/logical contexts where they are located and on their mutual acquaintance. This paper proposes a novel handshake detection system based on body sensor networks consisting of a resource-constrained wristwearable sensor node and a more capable base station. The system uses an effective collaboration technique among body sensor networks of the handshaking persons which minimizes errors associated with the application of classification algorithms and improves the overall accuracy in terms of the number of false positives and false negatives.

We present a mobile platform for body sensor networking based on a smartphone for lightweight signal processing of sensor mote data. The platform allows for local processing of data at both the sensor mote and smartphone levels, reducing the overhead of data transmission to remote services. We discuss how the smartphone platform not only provides the ability for wearable signal processing, but it allows for opportunistic sensing strategies, in which many of the onboard sensors and capabilities of modern smartphones may be collected and fused with body sensor data to provide environmental and social context. We propose that this can help refine data reduction at the local level. We describe three examples related to health and wellness, to which our system has been applied. Categories and Subject Descriptors

Wireless sensor networks (WSNs) are emerging as powerful platforms for distributed embedding computing. Currently, flexible frameworks and middlewares are emerging to facilitate WSN application development which is usually very applicationspecific and involves the programming of low-level mechanisms for enabling sensing, communication and energy saving. SPINE is a domain-specific framework for distributed processing of sensed data which is currently being applied to the rapid prototyping of body sensor networks applications for human body activity recognition. In this paper we present ASPINE, an agent-oriented design of the SPINE framework. According to the agentparadigm, each base station-side and sensor node-side component of SPINE (coordinator, sensor manager, function manager, communication manager) is designed as a software interacting agent with specific capabilities. The set of agents of a node constitute a local multi-agent system (MAS) which carries out a local goal (e.g. sensing and feature extraction on sensed data) whereas a set of cooperating nodes represents a distributed MAS pursuing a global goal (e.g. classification of human body postures). Finally, we also describe the design of an implementation of ASPINE based on MAPS, an agent platform for Java SunSPOTs.

which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Blood pressure self-measurement (BPSM) requires patients to follow a range of recommendations in order to be considered reliable for diagnostic use. We investigated currently used BPSM interventions at four medical clinics combined with an online questionnaire targeting BPSM users. We found that the participating healthcare personnel perceived BPSM as a relevant and useful intervention method providing that the recommendations are followed. A total of six challenges were identified: (1) existing devices do not guarantee that the recommendations are followed, (2) healthcare providers cannot verify whether self-monitoring patients follow the recommendations, (3) patients are not aware of all recommendations and the need to follow them, (4) risk of patient induced reporting bias, (5) risk of healthcare provider induced data-transfer bias, and (6) risk of data being registered as belonging to the wrong patient. We conclude that existing BPSM interventions could be significantly affected by user-induced bias resulting in an indeterminable quality of the measurement data. Therefore, we suggest applying context-aware technological support tools to better detect and quantify user errors. This may allow us to develop solutions that could overcome or compensate for such errors in the future. 1. Background Hypertension is defined as elevated blood pressure (BP) above 140 mm Hg systolic and 90 mm Hg diastolic when

Abstract not found