Much research has been conducted that uses sensor-based modules with dedicated software to automatically distinguish the user's situation or context. The best results were obtained when powerful sensors (such as cameras or GPS systems) and/or sensor-specific algorithms (like sound analysis) were applied. A somewhat new approach is to replace the one smart sensor by many simple sensors. We argue that neural networks are ideal algorithms to analyze the data coming from these sensors and describe how we came to one specific algorithm that gives good results, by giving an overview of several requirements. Finally, wearable implementations are given to show the feasibility and benefits of this approach and its implications.