Camazotz

摘要: Long-term outdoor localisation with battery-powered devices remains an unsolved challenge, mainly due to the high energy consumption of GPS modules. The use inertial sensors and short-range radio can reduce reliance on prolong operational lifetime tracking devices, but they only provide coarse-grained control over activity. In this paper, we introduce our feature-rich lightweight Camazotz platform as enabler Multimodal Activity-based Localisation~(MAL), which detects activities interest by combining multiple sensor streams for fine-grained sampling times. Using case study long-term flying fox tracking, characterise connectivity, energy, activity recognition performance module under both static 3-D mobile scenarios. We collect empirical data illustrate utility individual composite modalities in classifying evaluate MAL foxes through simulations based retrospective data. results show that multimodal activity-based reduces power periodic single sensor-triggered up 77% 14% respectively, provides a richer event type dissociation sampling.