Bayesian-based scenario generation method for human activities
Proceedings of the 2013 ACM SIGSIM conference on Principles of advanced discrete simulation
A context-driven approach to scalable human activity simulation
Proceedings of the 2013 ACM SIGSIM conference on Principles of advanced discrete simulation
| Hi-index | 0.00 |
For smart home researchers, it is essential to test activity recognition algorithms with various sets of sensory data. However, diverse sensory datasets are not always available due to several constraints, including limited budgets. Consequently, smart home simulators have recently grown in importance. However, there is still a need for realistic synthetic sensory data. This paper presents a simulator, 隆®Persim 3D', which relies on automatic scenario generation to create realistic sensory data. Persim 3D provides a 3D graphical user interface to help users' spatial perception, sensors that operate in real-time, similar to actual sensors, and a virtual character that lives in a virtual environment. These features allow users to generate longitudinal simulation data and eventually contribute to activity recognition research.