Fatigue Prediction Model Using Pupillary Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for predicting visual fatigue are limited in their ability to objectively and precisely measure fatigue levels, particularly for general visual tasks, and do not account for various types of visual content, leading to inefficiencies and inaccuracies in assessing and preventing fatigue.
Innovation Solution
A computer-implemented method using a predictive model that combines subjective and objective measurements, such as questionnaire responses and pupillary data, to quickly and accurately predict changes in visual fatigue levels, enabling the provision of personalized anti-fatigue optical articles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional subjective questionnaires are used for visual fatigue assessment, then the assessment can be performed, but the objectivity and precision of measurement is insufficient
Solution Approach 1:
The patent combines multiple measurement approaches (subjective questionnaire responses, objective pupillary measurements, and demographic data) into a unified predictive model. This integration allows the system to leverage both the simplicity of questionnaires and the objectivity of physiological measurements, resolving the contradiction between measurement precision and device complexity by creating a composite assessment system that achieves high precision without requiring overly complex individual components
Solution Approach 2:
The patent introduces a machine learning predictive model as an intermediary that processes multiple input data types (subjective responses, objective measurements, demographic information) and transforms them into a unified fatigue prediction output. This intermediary component enables the system to integrate diverse data sources effectively, achieving precise objective measurement while maintaining manageable system complexity through standardized processing architecture
2Measurement precision
If objective measurements like pupillary data are used, then measurement precision improves, but the device complexity and cost increase
Solution Approach 1:
The patent employs a pupillary measurement device that serves multiple functions: it captures pupillary response data for fatigue assessment, records demographic information, and provides objective physiological measurements. By making the device multi-functional, the system achieves high measurement precision without proportionally increasing device complexity, as the same hardware infrastructure supports multiple assessment capabilities
Solution Approach 2:
The patent uses pupillary measurements as a proxy or copy of the underlying physiological fatigue state, rather than requiring direct measurement of complex brain or muscle fatigue indicators. This indirect measurement approach achieves high precision in assessing fatigue levels while keeping the measurement device relatively simple, as pupillary response can be captured with standard optical equipment rather than complex neurophysiological instrumentation
3Measurement precision
If traditional fatigue induction methods are used (prolonged visual tasks), then fatigue levels can be measured, but the assessment time becomes excessively long
Solution Approach 1:
The patent collects and processes multiple types of data (subjective baseline responses, objective pupillary measurements, demographic information) simultaneously or in parallel rather than sequentially. This preliminary gathering of comprehensive data allows the predictive model to generate accurate fatigue assessments without requiring prolonged visual task induction, significantly reducing assessment time while maintaining measurement precision through multi-source data integration
Solution Approach 2:
The patent replaces the mechanical approach of inducing fatigue through prolonged visual tasks with a computational predictive model that calculates fatigue levels based on multiple input parameters. This substitution eliminates the need for time-consuming fatigue induction protocols, achieving accurate measurement without the temporal cost of traditional methods by using algorithmic prediction rather than physiological induction
4Adaptability or versatility
If existing prediction models are used, then some prediction capability is provided, but they are limited to specific visual content types and not suitable for general visual tasks
Solution Approach 1:
The patent develops a predictive model that is designed to handle multiple types of visual tasks and content categories (stereoscopic content, videos, images, general visual tasks) through a unified framework. The model incorporates demographic variables and adjusts predictions based on task type, achieving both high versatility across different visual activities and maintained prediction accuracy through task-specific parameter adjustments within the same system architecture
Data Source
AI summary
This computer-implemented method for providing an automated prediction of a change of a state of fatigue of a subject carrying out a visual task involving any kind of visual content comprises: providing a plurality of input data, relating to the subject, to a fatigue state change predictive model, wherein the plurality of input data comprises at least one subjective measurement relating to the subject and/or at least one objective measurement relating to the subject and/or at least one other subject-related datum; obtaining, by a processor implementing the model, a value representing a level of change of the state of fatigue of the subject.