Context-Awareness in Ambient Intelligence

Introduction

Context awareness can be defined as “...any information that can be used to characterize the situation of an entity. An entity is a person, place, or object that is considered relevant to the interaction between a user and an application, including the user and applications themselves” (Dey & Abowd, 2000). This definition makes no assumptions about the types of information which are relevant to context such as time, location, identity and so on. Following the more open ended definition above caters for situations where the context may be derived from one, many or all of these types of information as well as other types of information which are not defined from the outset. This understanding of context is necessary in creating truly intelligent environments for the future which are extensible in order to keep up with the rapidly changing and increasingly diverse contexts in which human-computer interactions are taking place.

Context-Awareness in computing can be seen as the existence of computer systems and applications which can gather and make sense of “information about the immediate situation—the people, roles, activities, times, places, devices, and software that define the situation” (Vian et al., 2006) and then demonstrate the appropriate related behaviour based on the perceived context. Such behaviour might include the presentation of customised or specially formatted information or the performance of some action to avoid a potentially hazardous situation. Future revelations in the area of context-awareness have the potential to dramatically improve the way in which ubiquitous and intelligent computing environments support our everyday activities as well as provide richer experiences in human-computer interaction.

Ubiquitous computing expert Mark Weiser talked about a new wave of pervasive computing which he described as “the age of calm technology, when technology recedes into the background of our lives” and where computers would be “embedded in our daily lives and supporting them”. Research into context-aware computing holds the key to realising this vision of seamless human-computer interaction where all information relevant to context will be gleaned automatically by intelligent systems. When discussing this point it is important to re-evaluate what environmental information is relevant to context. For example, information on the identity of users might be implicitly gathered by the application as the user approaches the computer or the point of interface. This could be done using facial recognition, for example. Alternatively, the user might explicitly provide identity information to the application via a more conventional log-in prompt. In both cases, the information on the user's identity provides context but in the latter case the system is not necessarily intelligent or context-aware. If we were to have computing devices embedded in our environments but we still had to interact explicitly with them, then we would gain no real benefit from the ubiquitous computing paradigm. In fact, copious devices and computer applications which expect explicit user involvement would serve as more of an hindrance in carrying out our everyday activities rather than a means of supporting them. In order to achieve the sort of innovation discussed by Weiser and others, we must continue to investigate and develop truly context-aware applications which can gather and make sense of information relevant to the current context and then exhibit some behaviour depending on the context. Some of the possibilities for Ambient Intelligence to support our daily activities include working out quick routes for car journeys and applications which infer our shopping list by gathering information about the contents of our fridge and combining this with the information that you are having friends over for dinner (Shadbolt, 2003). In this sense, these applications must be truly context aware so that they integrate seamlessly into people's daily lives and avoid becoming “ubiquitous clutter” rather than useful pervasive computing services.