Addressing Context Awareness Techniques in Body Sensor Networks Barbara T. Korel and Simon G. M. Koo Department of Mathematics and Computer Science University of San Diego, San Diego, CA 92110 Email: {bkorel-07,koo}@sandiego.edu Abstract Context awareness in Body Sensor Networks (BSNs) has the significance of associating physiological user activity and environment to the sensed signals of the user. The con- text information derived in a BSN can be used in pervasive healthcare monitoring for relating importance to events and specifically for accurate episode detection. In this paper, we address the issues of context-aware sensing in BSNs, along with a comparison of different techniques for deduc- ing context awareness, namely, Artificial Neural Networks, Bayesian Networks, and Hidden Markov Models. 1 Introduction Context is defined as any information that can be used to characterize the situation of an entity, where an entity can be a person, place or physical object [3]. Context awareness can then be defined as detecting a user’s internal or external state. Context-aware computing describes the situation of a wearable or mobile computer being aware of the user’s state and surroundings, and modifying its behavior based on this information [9]. Context awareness plays a significant role in Body Sensor Networks (BSNs) because it allows for interpreting physical and biochemical signals coming from the BSN based on information regarding the current state of the user and the state of the environment. Context-aware sensing is an integral part of the BSN design to achieve the ultimate goal of long-term pervasive health care monitoring. There are three main approaches that have been applied in deducing context in a sensor network: Artificial Neural Networks, Bayesian Networks and Hidden Markov Models. Research in context awareness or activity recognition using these methods has primarily been done in wireless sensor networks or wearable sensor networks, so the application of context aware sensing in BSNs is still new and faces many technical challenges. This paper will address some of these issues raised, describe the characteristics of each of these methods, and discuss how these algorithms handle the chal- lenges that need to be faced in context sensing for BSNs. 2 Context Awareness in BSNs Wireless medical body sensor devices, either im- plantable or wearable, are used to monitor a patients’ phys- iological state including EKG, heart rate, blood pressure, oxygen saturation and sweat volume/rate. The wireless BSN framework is designed to provide such pervasive mon- itoring of the human body; this ultimately has a huge impact on medical healthcare and monitoring vital signs of elderly patients or patients with chronic cardiac disease. BSNs present a method to continuously monitor physiological pa- rameters to detect life threatening abnormalities that could lead to mortality. In addition to a patient’s vital signs, a person is physiologically very sensitive to context or envi- ronment changes. Such contextual factors include the per- son’s activity, current temperature of the outside environ- ment, and time of day, etc. For instance, if a body sensor detects a rapid increase in a patient’s heart rate, the patient might not be having a cardiac episode but rather experienc- ing a change in his physical activity such as jogging. Incor- porating contextual awareness into the BSN by evaluating environmental factors and the state of the patient, changes in the physiological state of the body can be rationalized according to the events that triggered such changes. There are various algorithms in context-aware sensing, each have different characteristics and accomplish different tasks, which can be applied towards deducing context in a BSN. Many of these approaches are actually used in com- bination with one another to achieve context from the en- vironment. The first step in achieving context awareness in a sensor network is to gather the low-level sensor readings from all sensor nodes; these data readings will always con- stitute as the input for context sensing. It is often beneficial for the input data to be ordered in some way, thus the data is typically clustered into subgroups such that distance is small among data entries in the same cluster and distance is large among data entries of different clusters [6]. This is ac- complished by a clustering algorithm. To actually achieve 21st International Conference on Advanced Information Networking and Applications Workshops (AINAW'07) 0-7695-2847-3/07 $20.00 © 2007