A cell phone that behaves in a manner reflective of the current context has been a goal for the pervasive and ubiquitous research communities for a long time. This paper aims to demonstrate how two aspects of context – location and activity – can be inferred using GSM data present on standard cell phones.
A background knowledge of GSM networks is provided, followed by an assessment of the stability of signal strength levels in order to establish their usefulness in inferring aspects of context. A qualitative location system using GSM signals is presented and how to infer the current activity of the cell phone carrier is demonstrated.
The paper shows that by using the patterns of signal strength fluctuations and changes to the current serving cell and monitored neighbouring cells it is possible to distinguish between various states of movement such as walking, driving a car and remaining stationary.
The paper focuses on the practical aspects of deploying and managing location based services in dynamic outdoor environments.
