Acoustic Occupancy Estimation for Sparse Lighting Sensor Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing lighting systems face challenges in accurately detecting occupancy in large spaces with sparse motion sensor networks, leading to inefficiencies in energy consumption and user comfort.
Innovation Solution
A system that utilizes sound sensors to derive sound parameters and combines them with motion sensor data to create an occupancy estimation model, allowing for more accurate detection of occupancy through a learning process that adapts lighting control based on historical data and environmental characteristics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If motion sensors are sparsely distributed in large spaces, then device complexity is reduced, but occupancy detection reliability deteriorates
Solution Approach 1:
The patent combines multiple sensing modalities (acoustic sensors, passive infrared sensors, and other motion sensors) into an integrated occupancy detection system. By merging different sensor types that detect occupancy through different physical principles, the system achieves reliable occupancy detection in large spaces without requiring dense deployment of any single sensor type, thus resolving the contradiction between device complexity and detection reliability.
2Reliability
If motion sensors are densely distributed in large spaces, then occupancy detection reliability is improved, but device complexity increases
Solution Approach 1:
The patent implements a multi-functional sensor system where acoustic sensors detect both occupancy presence and audio characteristics, passive infrared sensors detect thermal signatures, and the system integrates multiple sensing functions into a unified occupancy detection framework. This multi-functionality allows the system to achieve high reliability without proportionally increasing device complexity, as each sensor serves multiple detection purposes.
3Device complexity
If lighting control is based solely on motion sensor data, then device complexity is reduced, but measurement precision deteriorates
Solution Approach 1:
The patent implements a feedback mechanism where the system continuously monitors occupancy conditions using multiple sensor inputs (acoustic, passive infrared, motion sensors) and adjusts lighting control decisions based on the integrated feedback from all sensors. The control entity receives feedback from each sensor type and synthesizes this information to make precise occupancy-based lighting control decisions, resolving the contradiction between system complexity and measurement precision.
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
Enhances the reliability and efficiency of occupancy detection, enabling precise lighting adjustments that improve user comfort while minimizing energy waste.
Implementation Method 1
a sensor portion comprising a sound sensor arranged to capture a sound sensor signal that represents sounds in a space
Implementation Method 2
occupancy in the space is predominantly detected via application of motion sensors such as passive infrared (PIR) sensors
Data Source
Figure 1~2
Figure 3~4
Figure 5
AI summary
According to an example embodiment, a sensor apparatus (140, 140-k) is provided, the sensor apparatus (140, 140-k) comprising: a sensor portion (142, 142-k) comprising a sound sensor arranged to capture a sound sensor signal that represents sounds in a space illuminated by a plurality of luminaires (120, 220); a sensor control portion (144, 144-k) arranged to derive, based on the sound sensor signal, one or more sound parameters, where each sound parameter is descriptive of a respective sound characteristics in said space; and a learning portion (145, 145-k) arranged to: receive, from a plurality of other devices (120, 220) arranged in said space, respective remote occupancy state indications that are descriptive of motion in respective locations of said space, store history data including a history of the one or more sound parameters and respective histories of the occupancy state indications, and carry out a learning procedure to determine, based on the history data, an occupancy estimation model that is applicable for deriving an occupancy likelihood coefficient based on the one or more sound parameters, where the occupancy likelihood coefficient is descriptive of a likelihood of occupancy in at least one location of said space, wherein the sensor control portion (144, 144-k) is arranged to apply the determined occupancy estimation model for facilitating controlling of respective light output of at least one luminaire (120-k, 220-k) of the plurality of luminaires (120, 220).