Context-driven approach for high realism, scalable simulation of human activities in smart spaces

As demands for human activity recognition technology increase, simulation of human activities for training and testing purposes becomes increasingly more important. The simulation generates synthetic datasets which provide resources for developing activity recognition and enables evaluation of the new activity recognition approaches. Traditional simulations, however, are based on an event-driven approach, which focuses on single sensor events and models within a single human activity. It requires detailed description and processing of every low-level event that enters into an activity scenario. For many realistic and complex human scenarios, the event-driven approach burdens the simulator users with complicated low-level specifications required to configure and run the simulation. It also increases computational complexity and impedes scalable simulation. We propose a novel, context-driven approach to simulating human activities in smart spaces. In the proposed approach, vectors of sensors rather than single sensor events drive the simulation quicker from one context to another. Abstracting the space state into contexts highly simplifies the number of tasks efforts of the simulation user in set up and configuration of the simulation components for smart space and human activities. We present the context-driven simulation approach and show how it works. We implement the context-driven simulation engine and equip it into Persim with 3D visualization engine, called Persim 3D for validating the performance of context-driven simulation. It will show that it can generate datasets similar to the actual datasets collected in the real world, and also reduce human efforts in simulation so that it enables scalable simulation.