Human-Centric Lighting Platform Using EEG-Based Emotion Grading
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for determining emotional states using electroencephalographs (EEG) or functional Magnetic Resonance Imaging (fMRI) are expensive and impractical for commercial applications, as EEG brainwave patterns vary among individuals and cannot replace the accuracy of fMRI's blood oxygen-level dependent (BOLD) contrast responses.
Innovation Solution
Establish a correlation between EEG brainwave patterns and fMRI's BOLD responses to create a grading method for emotional responses using an intelligent human-centric lighting system, involving specific color temperatures to stimulate emotions, record EEG files, and use artificial intelligence to classify and grade these responses, constructing a spectral recipe database for commercial use.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If fMRI system is used to measure blood oxygen-level dependent (BOLD) contrast response for emotion judgment, then measurement precision is improved, but device complexity and cost increase significantly
Solution Approach 1:
The patent creates a mapping relationship between fMRI BOLD responses and EEG brainwave patterns, allowing EEG to serve as a simplified copy or surrogate for fMRI. By training a model on fMRI data and applying it to EEG data, the system replicates fMRI's emotion judgment capability using a less complex device
Solution Approach 2:
The patent replaces the complex mechanical and physical system of fMRI with a simpler EEG system. Through machine learning modeling, the patent substitutes the expensive, complex fMRI measurement approach with an affordable EEG-based approach that achieves comparable emotion detection accuracy
2Device complexity
If EEG brainwave patterns are used for emotion judgment, then device complexity is reduced, but measurement precision deteriorates due to individual variations
Solution Approach 1:
The patent transforms EEG data by changing parameters through machine learning processing. It converts raw, variable EEG signals into standardized emotion predictions by applying trained models that adjust for individual differences, thereby maintaining measurement precision while using the simpler EEG device
Solution Approach 2:
The patent uses feedback from fMRI data to train and refine the EEG-based emotion detection model. By continuously improving the mapping relationship between EEG patterns and emotional states through learned feedback, the system compensates for individual variations and maintains high measurement precision
3Measurement precision
If fMRI system is used for commercial human centric lighting applications, then measurement precision is improved, but loss of energy and cost increase
Solution Approach 1:
The patent replaces expensive, energy-intensive fMRI systems with affordable, low-cost EEG devices. By using disposable or reusable EEG headsets instead of costly fMRI scanners, the system achieves comparable functionality at a fraction of the cost and energy consumption, making commercial applications feasible
Data Source
AI summary
A lighting environment sharing platform includes an intelligent human-centric lighting system comprising a cloud, a lighting field terminal, and a client terminal interconnected via the Internet. The cloud manages a database of multi-spectrum lighting parameters, light scenes based on emotional needs, and spectrum recipes shared by users. The client terminal selects light scenes according to emotional needs, controls multi-spectrum devices, accordingly, uploads effective scenes to the cloud, and accesses shared spectrum recipes.