Discriminating sensor activation in activity recognition within multi-occupancy environments based on nearby interaction
This work addresses activity recognition in multi-occupancy environments, which is an incremental improvement for smart home or healthcare monitoring systems.
The paper tackles the problem of discriminating sensor activation in multi-occupancy environments for activity recognition by using proximity interaction to generate sensor interaction matrices for each inhabitant, enabling the application of classical human activity recognition models to reduce complexity, with a case study deployed using UWB and binary sensors.
This work presents a computer model to discriminate sensor activation in multi-occupancy environments based on proximity interaction. Current proximity-based and indoor location methods allow the estimation of the positions or areas where inhabitants carry out their daily human activities. The spatial-temporal relation between location and sensor activations is described in this work to generate a sensor interaction matrix for each inhabitant. This enables the use of classical HAR models to reduce the complexity of the multi-occupancy problem. A case study deployed with UWB and binary sensors is presented.