Eye-Tracking Algorithm Validation for Mobile Device Precision
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current eye-tracking technologies face challenges in comparing data from stationary and mobile devices due to differences in resolution and algorithms, limiting the use of mobile eye-trackers in clinical and low-resource settings.
Innovation Solution
A method and system that apply a common data processing algorithm, such as the Velocity-Threshold Identification (I-VT) algorithm, to both static and mobile eye-tracking devices to compare and validate the attributes of saccadic movements, allowing for the determination of modification actions or design changes to align mobile device results with static device standards.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If mobile eye-tracking devices are used, then cost is reduced and accessibility is improved, but measurement precision and data reliability deteriorate due to differences in resolution and algorithms compared to static devices
Solution Approach 1:
The patent applies parameter changes by modifying the data processing approach rather than the hardware specifications. It uses the Velocity-Threshold Identification (I-VT) algorithm with adjusted parameters to process mobile device data, transforming the raw data into standardized saccadic attributes that match static device outputs. This allows lower-cost mobile devices to achieve comparable measurement precision through software optimization.
Solution Approach 2:
The patent introduces a common data processing algorithm as an intermediary between mobile device raw data and standardized saccadic attributes. This intermediary processing layer (the I-VT algorithm) translates diverse mobile device outputs into a unified format that can be directly compared with static device measurements, bridging the gap between different device types.
2Productivity
If different data processing algorithms are used for static and mobile devices, then device-specific optimization is achieved, but data comparability and validation between devices deteriorate
Solution Approach 1:
The patent implements universality by developing a common data processing algorithm (I-VT) that serves multiple functions: it processes data from both static and mobile devices, extracts saccadic attributes from diverse data formats, and produces standardized outputs suitable for clinical validation. This single algorithm handles multiple device types and data formats, ensuring consistency across different platforms.
3Measurement precision
If mobile eye-trackers are validated against static device standards, then measurement accuracy is improved, but device complexity and validation requirements increase
Solution Approach 1:
The patent uses copying by replicating the successful data processing pipeline from static devices and applying it to mobile devices. The I-VT algorithm, originally developed for static device data, is copied and adapted for mobile device inputs. This copying approach allows mobile devices to be validated against the same standards without requiring entirely new validation methodologies, reducing overall system complexity.
Data Source
AI summary
Systems and techniques disclosed herein include receiving static device data in response to detected first biometric movements, receiving mobile device data in response to detected second biometric movements, applying an analysis algorithm to the static data to determine static attributes, applying the analysis algorithm to the mobile data to determine mobile attributes, comparing the static attributes to the mobile attributes, and determining a modification action based on the comparing. A mobile device may be validated based on the determining that the static attributes are within a threshold parameter of the mobile attributes.