Database Reference
In-Depth Information
Expanding Sensor Networks to Automate
Knowledge Acquisition
Kenneth Conroy 1 ,GregoryC.May 1 , Mark Roantree 2 , and Giles Warrington 1
1 CLARITY: Centre for Sensor Web Technologies, Dublin City University
2 Interoperable Systems Group, School of Computing, Dublin City University,
Glasnevin, Dublin 9, Ireland
Abstract. The availability of accurate, low-cost sensors to scientists has
resulted in widespread deployment in a variety of sporting and health
environments. The sensor data output is often in a raw, proprietary or
unstructured format. As a result, it is often dicult to query multiple
sensors for complex properties or actions. In our research, we deploy a
heterogeneous sensor network to detect the various biological and phys-
iological properties in athletes during training activities. The goal for
exercise physiologists is to quickly identify key intervals in exercise such
asmomentsofstressorfatigue.Thisisnotcurrentlypossiblebecause
of low level sensors and a lack of query language support. Thus, our
motivation is to expand the sensor network with a contextual layer that
enriches raw sensor data, so that it can be exploited by a high level query
language. To achieve this, the domain expert specifies events in a tradi-
ational event-condition-action format to deliver the required contextual
enrichment.
1
Introduction
Many new applications employ sensors or networks of sensors to automatically
monitor and generate reports and analysis across domains. Increasingly, elite
sports men and women are monitored to determine the effects of various train-
ing sessions on their bodies. Multiple hetrogeneous sensors are often deployed
to discover physiological or biological information generated during the activity.
As these sensors generate output in unstandardised and proprietary formats,
examining it to identify key events or properties involves time consuming exam-
ination of multiple files. Manual alignment, integration and the application of
context from which this data was gathered is required to aid with querying the
information.
These issues can be demonstrated by examining a sport such as cycling. Lab-
oratory based cycling experiments attempt to quantify certain aspects of the
effect of cycling on the participant. This is facilitated by gathering data such
as power output (a measure of work created by the cyclist in order to overcome
the forces against them, such as gradient, drag, etc.), cadence (a measure of the
This work is supported by Science Foundation Ireland under grant 07/CE/I1147.
 
Search WWH ::




Custom Search