Heuristic RF Occupancy Detection in Lighting Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing RF-based occupancy detection systems in lighting systems face challenges such as high costs, inaccurate detection due to multiple transmitters, and reliance on satellite signals indoors, which reduce accuracy and require occupants to carry devices.
Innovation Solution
A heuristic occupancy detection system using machine learning algorithms that analyze RF perturbations with optimized coefficients to determine occupancy or non-occupancy conditions in real-time, integrating RF wireless communication in lighting devices without the need for occupants to carry devices, and capable of differentiating between sub-areas.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If multiple transmitters are used to cover different regions, then coverage area is improved, but detection accuracy deteriorates due to signal interference
Solution Approach 1:
The system segments the monitoring area into multiple sub-areas, each associated with a specific transmitter. By dividing the coverage area and assigning dedicated transmitters to specific zones, the system maintains detection accuracy within each sub-area while achieving comprehensive overall coverage. The heuristic algorithm determines which transmitter's signal to analyze based on the target sub-area, preventing interference from other transmitters.
Solution Approach 2:
The system applies local quality by optimizing RF signal analysis for each specific sub-area. Instead of using a uniform detection approach across the entire area, the heuristic algorithm selects and applies appropriate detection parameters and transmitter associations locally to each sub-area. This ensures high detection accuracy in each local region while maintaining system-wide coverage.
2Reliability
If traditional RF systems are used, then occupancy detection is achieved, but false positives occur due to inaccurate signal analysis
Solution Approach 1:
The system performs preliminary learning to optimize heuristic algorithm coefficients before real-time occupancy detection. During the learning phase, the system collects RF signal data and determines optimal coefficient values that minimize false positives. These pre-optimized coefficients are then applied in real-time detection, significantly improving signal analysis accuracy and reducing false occupancy detections.
Solution Approach 2:
The system implements feedback through ongoing learning that further optimizes heuristic algorithm coefficients during real-time operation. The heuristic algorithm continuously refines its detection parameters based on accumulated data, creating a feedback loop that improves detection accuracy over time and reduces false positives while maintaining reliable occupancy detection.
3Measurement precision
If video sensors are used for occupancy detection, then detection accuracy is improved, but system cost and complexity increase
Solution Approach 1:
The system makes lighting fixtures multi-functional by integrating both lighting and occupancy detection capabilities. Instead of requiring separate video sensor systems, the patent utilizes existing RF infrastructure (transmitters and receivers) for dual purposes: lighting control and occupancy detection. This universal approach achieves accurate detection while reducing system complexity and eliminating the need for additional dedicated sensors.
Solution Approach 2:
The system enables lighting fixtures to self-serve dual functions. The RF transmitters embedded in lighting fixtures not only provide illumination control but also serve as occupancy detection transmitters. The receivers analyze RF signal perturbations caused by occupants, allowing the lighting system to automatically detect occupancy without external dedicated detection equipment, thereby reducing overall system complexity.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Improves detection accuracy and reduces false positives by using machine learning to optimize RF signal analysis, enabling rapid and precise occupancy detection within lighting systems without the need for additional hardware on occupants.
Implementation Method 1
occupancy is sensed based on measurements of RF perturbations in an area or space
Data Source
AI summary
Disclosed herein is a lighting system configured to obtain an indicator data of a RF spectrum signal generated at a number of times in an area. At each respective one of the number of times, apply one of a plurality of heurist algorithm coefficients to each indicator data from each of the plurality of receivers for the respective time, based on results of the applications of the coefficients to indicator data, generate an indicator data metric value for each of the indicator data for the respective time, and process the indicator data metric values to compute an output value. The lighting system is further configured to compare the output value at each of the plurality of times with a threshold to detect one of an occupancy condition or a non-occupancy condition in the area and control the light source in response to the detected one of the occupancy condition or the non-occupancy condition in the area at each of the number of times.