Lighting Network Audio Sensing for Localized Event Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing lighting fixtures primarily focus on measuring environmental factors related to light output and do not effectively utilize networking circuitry for detecting and identifying auditory events, limiting their functionality and control capabilities.
Innovation Solution
Incorporating audio sensors and machine learning algorithms, such as convolutional neural networks, into lighting fixtures to detect and identify auditory events, allowing for actions like notifications or sound cancellation based on the type of event detected.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If lighting fixtures incorporate audio sensors and machine learning algorithms to detect and identify auditory events, then the functionality and control capabilities of lighting fixtures are enhanced, but the device complexity increases
Solution Approach 1:
The patent applies multi-functionality by enabling lighting fixtures to perform both their traditional lighting function and new auditory event detection functions through integrated audio sensors and machine learning algorithms. The lighting fixture becomes a universal device that can detect various auditory events (air leaks, gunshots, glass breaking, etc.) and trigger appropriate responses, thereby enhancing functionality without requiring entirely separate dedicated devices.
Solution Approach 2:
The patent combines multiple functions into a single lighting fixture by integrating audio sensors, processing circuitry with machine learning algorithms, and networking capabilities into the existing lighting fixture structure. This merging approach allows the fixture to simultaneously provide lighting, auditory event detection, identification, and automated response capabilities, resolving the contradiction between enhanced functionality and device complexity.
2Adaptability or versatility
If lighting fixtures incorporate audio sensors and machine learning algorithms to detect and identify auditory events, then the control capabilities are enhanced, but the manufacturing complexity increases
Solution Approach 1:
The patent applies preliminary action by pre-training machine learning models with auditory event data before deployment in the lighting fixtures. The processing circuitry is pre-configured with trained algorithms that can automatically identify different types of auditory events. This preliminary preparation simplifies manufacturing because the complex AI modeling work is done beforehand, and the fixtures only need to be programmed with the pre-trained models rather than implementing complex training procedures during manufacturing.
3Adaptability or versatility
If networking circuitry is used to communicate auditory event detections across the network, then the coordination and response capabilities are improved, but the loss of time for data transmission may occur
Solution Approach 1:
The patent applies segmentation by dividing the auditory event detection and response system into distributed autonomous lighting fixtures, each capable of independent event detection, identification, and local response execution. Each fixture processes auditory events locally using embedded machine learning algorithms, enabling immediate local responses without network communication delays. Network communication is used only for coordination between fixtures and remote monitoring, thereby minimizing overall time loss while maintaining coordination capabilities.
Data Source
AI summary
Detection and identification of auditory events in distributed lighting networks is provided. Lighting fixtures or other devices in a distributed lighting network can incorporate an audio sensor (e.g., a microphone) through which auditory events (e.g., air leaks in compressed air systems, high noise events, shots fired, clapping, voice commands, etc.) are detected and measured. Through machine learning (e.g., a convolutional neural network), a type of auditory event can be identified, and action can be taken based on the type of the auditory event, such as to provide notification, alert nearby users, log events, provide sound cancelation, and so on. In some examples, the auditory event can be localized using multiple audio sensors. In some examples, a learning algorithm can fuse information from multiple sensor inputs, such as temperature sensors, cameras, occupancy sensors, light sensors, and so on.