Opportunistic human activity and context recognition
Although the Internet of Things allows seamless access to billions of sensors readily deployed throughout the world, current context- and activity-recognition approaches restrict ambient intelligence to domains where dedicated sensors are deployed. The big data delivered by the Internet of Things calls for a new opportunistic recognition paradigm. Instead of setting-up information sources for a specific recognition goal, the methods themselves adapt to the data available at any time. We present enabling methods that allow for opportunistic recognition in dynamic sensor configurations. This could be the missing link to fulfill the promise of ambient intelligence anywhere.