- 62 views
- 72 downloads
Simulation-based Sensor Configuration Optimization to Detect Human Activities in Smart Indoor Spaces
-
- Author / Creator
- Golestan-Irani, Shadan
-
Smart indoor spaces include a network of interconnected sensors, predictive models, and actuators to sense occupants’ activities and act to improve living. These ubiquitous systems are increasingly popular due to their potential to improve energy efficiency, comfort, and safety in buildings. Typically, the sensors collect data on the environment, while the predictive models use this data to predict the environment's activities and state. The actuators then act on the environment to change the environment's state to a desired one.
The design of smart indoor spaces is a challenging task that requires a lot of effort and time. One critical aspect of the design process is finding a suitable sensor configuration, as different applications require different sensor configuration deployments. The quality of the sensor configuration is critical for the system's overall effectiveness, as inaccurate or incomplete sensor data can lead to poor performance.
To address these challenges, designers of such systems iteratively deploy and modify different sensor configurations to find the one that meets their needs. This process is complex and time-consuming. Alternatively, simulation methodologies have been proposed to facilitate the design process because they offer fast, reproducible, and easy prototyping. Simulation allows designers to test and evaluate different sensor configurations in a virtual environment, reducing the need for expensive and time-consuming physical deployments. However, current simulation approaches still require significant effort and expertise to optimize the sensor configuration accurately.
This thesis proposes a simulation-driven sensor configuration evaluation framework that can optimize the sensor configuration effectively for various applications. Such a framework evaluates and optimizes different sensor configurations efficiently, leading to the development of more effective smart indoor spaces. The framework is evaluated in terms of 1) the fidelity of its simulation methodologies, 2) the quality of the sensor configurations it proposes, and 3) the framework’s scalability considering the sensor numbers and types.
-
- Subjects / Keywords
-
- Graduation date
- Fall 2023
-
- Type of Item
- Thesis
-
- Degree
- Doctor of Philosophy
-
- License
- This thesis is made available by the University of Alberta Libraries with permission of the copyright owner solely for non-commercial purposes. This thesis, or any portion thereof, may not otherwise be copied or reproduced without the written consent of the copyright owner, except to the extent permitted by Canadian copyright law.