Building Metadata Inference from Distributed Sensor Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing distributed sensor networks require significant and error-prone manual input for sensor location and orientation data, which becomes outdated when sensors are moved or added, hindering accurate building control systems.
Innovation Solution
A system that infers building metadata by analyzing data from multiple sensors to detect correlated events, generating a building layout and layout updates, using a controller with event detection, comparison, and analysis engines to filter and generate metadata for use in building control systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual input of sensor location and orientation data is used, then initial building metadata can be obtained, but the data becomes outdated when sensors are moved or added and requires time-consuming updates
Solution Approach 1:
The system enables automatic self-updating of building metadata by having sensors report their own location and orientation data periodically. The metadata system automatically processes this sensor-reported data to update the building layout information without requiring manual intervention, thus resolving the contradiction between maintaining accuracy and avoiding time-consuming updates.
Solution Approach 2:
The system implements continuous feedback loops where sensors monitor their environment and report data back to the central metadata system. This feedback mechanism allows the system to detect sensor movements and automatically update building metadata in real-time, eliminating the need for periodic manual updates while maintaining high accuracy.
2Reliability
If manual entry of sensor data is used, then building metadata can be established, but human error is introduced and updates are prone to mistakes
Solution Approach 1:
The system replaces the mechanical process of manual data entry with automated electronic data collection. Sensors automatically report their location and orientation data to the building metadata system, eliminating human operators from the data entry process and thereby eliminating human errors while maintaining ease of operation through automated processes.
Solution Approach 2:
Sensors perform self-reporting of their operational status, location, and orientation data. This self-service capability eliminates the need for manual data entry by operators, removing the source of human error while keeping the system easy to operate through automated workflows.
3Measurement precision
If frequent manual updates are performed to maintain accuracy, then building metadata remains current, but operational complexity and time consumption increase
Solution Approach 1:
The system uses continuous feedback mechanisms where sensors automatically report their status and the system automatically processes this information to update metadata. This eliminates the need for complex manual update procedures while maintaining current and accurate building metadata through real-time automated monitoring and updating.
Solution Approach 2:
The system transitions from static periodic manual updates to dynamic continuous automated updates. Sensors continuously report their data and the system dynamically processes this information in real-time, maintaining metadata currentness without requiring complex manual intervention or frequent scheduled updates.
Data Source
AI summary
Inferring building metadata from distributed sensors is described. In an embodiment multiple sensors are situated at various locations in a building detecting physical quantities (e.g. light, heat, motion). The data from at least one sensor is analyzed in order to detect events occurring in proximity to the sensor. Data about an event detected at a first sensor is compared with events detected at other sensors in order to identify correlated events from which connections between the sensor locations can be inferred and a building layout generated. In some embodiments a threshold may be applied to the data in order to filter out false events. In some embodiments the building layout may be used as part of a building control system. In some embodiments the sensor data may be used to determine if the sensor has been moved.