Neural Network Lighting Control Using Biomarker State Correlations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current lighting design workflows are inefficient due to a fragmented market with limited and inaccurate information about lighting products, leading to suboptimal results and underutilization of intelligent lighting features in installations.
Innovation Solution
A platform that utilizes automated search engines, machine learning, and near-field illumination characterization to facilitate the design, acquisition, installation, and operation of lighting installations, including a visual representation of lighting spaces, aesthetic filters, and data structures to match lighting objects with desired illumination patterns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If designers use physical samples and manual evaluation methods, then they can assess lighting products, but the process takes days or weeks and produces suboptimal results
Solution Approach 1:
The system creates digital copies (virtual models) of physical lighting fixtures that replicate their optical, electrical, and physical characteristics. These digital twins enable designers to evaluate lighting products computationally rather than through physical samples, dramatically reducing evaluation time while maintaining or improving accuracy through precise photometric data and rendering simulations.
Solution Approach 2:
The patent replaces manual physical evaluation processes with automated computational systems. Machine learning models and simulation software substitute for human designers physically handling samples, performing measurements, and making comparisons. This automation accelerates the design process while improving consistency and objectivity through standardized algorithms.
2Adaptability or versatility
If the lighting market remains fragmented with multiple suppliers, then product variety is available, but information about lighting products is unavailable, limited, or inaccurate
Solution Approach 1:
The system merges data from multiple fragmented lighting suppliers into a unified digital platform. By aggregating photometric data, electrical specifications, and physical characteristics from various manufacturers into a centralized database, the system provides comprehensive product information while maintaining the diversity of available lighting options. This consolidation eliminates information gaps caused by market fragmentation.
Solution Approach 2:
The patent creates a universal data structure and platform that can accommodate lighting products from any supplier with different specifications and formats. The standardized digital model framework enables diverse lighting products to be represented consistently, allowing designers to access and compare information from multiple sources through a single interface.
3Extent of automation
If lighting fixtures are configured as IoT devices, then they can be controlled remotely and operate autonomously, but most lighting installations do little to take advantage of this increased intelligence
Solution Approach 1:
The system performs preliminary configuration and programming of intelligent lighting fixtures during the design phase. Control strategies, scheduling parameters, and automation rules are established before installation, enabling fixtures to operate autonomously from day one. This pre-programming ensures that the intelligence built into IoT fixtures is actually utilized in the installed system.
Solution Approach 2:
The patent implements feedback loops where sensor data from occupied spaces continuously informs lighting control decisions. Occupancy sensors, ambient light sensors, and user preferences feed back to the control system, which automatically adjusts lighting parameters. This closed-loop control ensures intelligent fixtures adapt to actual conditions and are fully utilized rather than operating on fixed, inadequate schedules.
Data Source
AI summary
Method includes recording biomarker information being indicative of at least one biological state of user remaining in lighting control environment over time frame, biomarker information being generated by at least one physiological sensor remaining with user in lighting control environment over time frame; recording light control settings for at least one light remaining in lighting control environment with user and with physiological sensor generating biomarker information over time frame; and training a neural network to determine correlations between biological state of user remaining in lighting control environment over time frame and lighting effects caused by at least one light remaining in lighting control environment with user over time frame, based on recordings of biomarker information and recordings of light control settings, and utilizing the correlations for controlling the at least one light. Computer readable medium for executing method.