Occupancy estimation based on multiple sensor inputs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Building control systems face increased complexity and cost due to the inclusion of multiple occupancy sensors with varying degrees of accuracy, necessitating a simplified model that can integrate and weigh estimates from different types of sensors to provide accurate occupancy data for efficient system control.
Innovation Solution
A method and system that monitor occupancy counts from multiple sensors, calculate error parameters, assign weights based on these errors, and use a trained model to determine an estimated occupancy count for controlling Building Management Systems (BMS), allowing for accurate and efficient operation of building systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple occupancy sensors are included to improve occupancy estimation accuracy, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent combines multiple occupancy sensors of different types (motion sensors, presence sensors, access control sensors) into a unified occupancy estimation system. The controller integrates data from all sensors and applies weighting factors to generate a single composite occupancy estimate, thereby improving measurement precision while managing system complexity through centralized processing.
Solution Approach 2:
The system dynamically adjusts weighting parameters for each sensor type based on their respective error parameters. By changing these parameters adaptively, the system optimizes occupancy estimation accuracy without requiring manual configuration or complex calibration procedures, thus resolving the contradiction between precision and complexity.
2Reliability
If multiple occupancy sensors with varying accuracy are integrated, then occupancy data reliability is improved, but ease of operation deteriorates
Solution Approach 1:
The system performs self-calibration by automatically determining error parameters for each sensor type during operation. The controller autonomously calculates weighting factors based on observed sensor performance and ground truth data, eliminating the need for manual calibration or complex user configuration, thereby maintaining ease of operation while improving reliability.
Solution Approach 2:
The system uses feedback from ground truth occupancy data to continuously refine error parameters and weighting factors for each sensor. This automated feedback loop improves occupancy data reliability over time without requiring user intervention, thus resolving the contradiction between reliability and ease of operation.
3Measurement precision
If a trained model is used to process data from multiple sensor types, then occupancy estimation accuracy is improved, but device complexity increases
Solution Approach 1:
The patent implements a universal trained model that can process data from multiple types of occupancy sensors (motion sensors, presence sensors, access control sensors) through a single interface. The model is designed to handle heterogeneous sensor inputs and generate unified occupancy estimates, thereby improving accuracy while avoiding the need for separate processing systems for each sensor type.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An occupancy count of the space of a building from each of a plurality of occupancy sensors may be monitored and an error parameter for each of the plurality of occupancy sensors may be identified, each error parameter representative of a difference between the occupancy count of the respective occupancy sensor and a ground truth occupancy count of the space, normalized over a period of time. An assigned weight for each of the plurality of occupancy sensors may be determined based at least in part on the respective error parameter. The estimated occupancy count of the space of the building is determined based at least in part on the occupancy count of each of the plurality of occupancy sensors and the assigned weight of each of the plurality of occupancy sensors. The BMS system is controlled based at least in part on the estimated occupancy count.