Touch Input Handedness Classification Using Drift Diffusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing touch-based input systems struggle to accurately determine user handedness due to the inter-dependent nature of touch inputs, which conventional machine learning models fail to handle effectively, requiring large sample sizes and resource-intensive processing.
Innovation Solution
A drift diffusion model-based technique is employed to approximate inter-dependencies between touch-based inputs, generating scores and classifications to determine handedness using a smaller number of samples, allowing for efficient resource utilization and accurate classification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional machine learning models are used to determine handedness, then large sample sizes are required, but resource consumption increases and processing becomes less efficient
Solution Approach 1:
The patent changes the fundamental parameters of the analysis approach by using drift diffusion model parameters (drift rate, boundary separation, non-decision time) instead of traditional machine learning features. This parameter transformation allows for more efficient processing with fewer samples while maintaining accuracy in determining handedness from touch input sequences.
Solution Approach 2:
The patent substitutes conventional machine learning mechanical systems with a cognitive modeling approach based on drift diffusion theory. This replacement uses probabilistic diffusion processes to model decision-making, which is more computationally efficient for sequential touch input analysis while providing better interpretability of the decision process.
2Measurement precision
If conventional machine learning models process touch inputs, then large sample sizes are needed, but the inter-dependent nature of inputs makes processing less efficient
Solution Approach 1:
The patent implements feedback mechanisms where the drift diffusion process continuously updates the accumulated evidence from each touch input sequence. The model uses feedback from intermediate classification results to adjust the diffusion process, allowing for more efficient processing of inter-dependent inputs while maintaining high classification accuracy with fewer samples.
Solution Approach 2:
The patent applies dynamics by using a time-varying drift diffusion process that adapts to the sequential nature of touch inputs. The model dynamically adjusts the diffusion parameters based on the evolving evidence from each touch event, enabling efficient handling of inter-dependent inputs without requiring large static sample sizes.
3Measurement precision
If more touch input samples are collected to improve handedness determination, then accuracy improves, but time consumption and resource usage increase
Solution Approach 1:
The patent performs preliminary action by pre-defining the drift diffusion model parameters and decision boundaries before processing touch inputs. This preliminary setup allows the system to quickly process touch sequences without requiring extensive sampling, as the decision framework is already optimized for efficient handedness determination with minimal input sequences.
Solution Approach 2:
The patent implements skipping by using the drift diffusion model's ability to reach decision boundaries quickly with limited evidence. The model can skip through the need for large sample sizes by accumulating sufficient evidence faster through the diffusion process, reducing both the number of required samples and the overall processing time while maintaining accuracy.
Data Source
AI summary
Methods, systems, apparatuses, and computer program products are provided herein for determining the handedness of input provided by a user via a touch interface. For instance, for each touch-based input detected, a score indicating a probability whether the touch-based input was inputted by a particular hand of the user is generated. A classification for the touch-based input is then generated based on a drift diffusion model-based technique in which inter-dependencies between a series of touch-based input are approximated. The determined classifications are used to determine the handedness of the user.