Inferring Cognitive Load from Gait via Motion Sensors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current immersive computing technologies, such as head-mounted displays (HMDs), lack effective methods to infer cognitive load, which is crucial for applications like wayfinding, immersive training, and telepresence operations.
Innovation Solution
The use of motion sensors integrated with HMDs to capture gait features, combined with machine learning models, to infer cognitive load by correlating head movement data with foot movement data, allowing for the prediction of cognitive load through trained classifiers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If motion sensors are integrated with HMDs to capture gait features, then cognitive load inference capability is improved, but device complexity increases
Solution Approach 1:
The motion sensor serves multiple functions: it captures head movement data for immersive computing operations and simultaneously captures gait features for cognitive load inference. This multi-functionality approach allows the system to gain new capabilities (cognitive load monitoring) without adding separate dedicated hardware, thereby resolving the contradiction between improved adaptability and device complexity.
2Measurement precision
If machine learning models are used to infer cognitive load from gait data, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent replaces direct physiological measurement mechanisms with an indirect computational approach. Instead of using complex physiological sensors to directly measure cognitive load, the system uses machine learning models to infer cognitive load from gait data collected by motion sensors. This substitution achieves high measurement precision while avoiding the complexity of direct physiological measurement hardware.
3Measurement precision
If gait features are correlated with head movement data, then cognitive load inference accuracy is improved, but loss of time increases
Solution Approach 1:
The system performs preliminary actions by continuously collecting and pre-processing motion sensor data in the background, preparing gait feature extracts and head movement data before cognitive load inference is needed. This preliminary data preparation reduces the time required for real-time cognitive load assessment, as the machine learning model can process pre-processed features rather than raw data, thereby resolving the contradiction between inference accuracy and processing time.
Data Source
AI summary
In various examples, a cognitive load of a user may be inferred. Motion sensor data indicative of head movement of the user may be generated with a motion sensor disposed adjacent a head of the user. The motion sensor data may be analyzed to infer a feature of a gait of the user. The user's cognitive load may be inferred based on the feature of the gait.