Touch Screen Event Classification Using Spatiotemporal Weighting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Touch screen technologies often misclassify input types, leading to errors due to the inability to accurately distinguish between different hand parts and users, resulting in reduced accuracy and increased ambiguity in touch event analysis.
Innovation Solution
The method involves detecting touch events on a touch-sensitive surface, generating vibro-acoustic waveform signals, converting them into domain signals, extracting distinguishing features, and employing spatiotemporal event data to weight the analysis, thereby improving classification accuracy by leveraging non-random patterns of human interaction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional touch screen event analysis is used, then the system is simple and fast, but the classification accuracy is reduced and errors increase
Solution Approach 1:
The system performs preliminary classification of individual touch events before combining them into sequences. Each touch event is classified in advance using vibro-acoustic features, and these pre-classified events are then weighted based on their position in the sequence. This preliminary action allows the system to maintain accuracy while reducing the computational complexity of analyzing complete sequences from scratch.
Solution Approach 2:
The touch event analysis is segmented into multiple independent classification stages. Instead of analyzing the entire sequence as one complex task, the system divides it into individual touch event classifications, each handled separately with its own feature extraction and classification process. These segmented classifications are then combined using spatiotemporal weighting to produce the final result, improving both accuracy and manageability.
2Measurement precision
If touch events are analyzed without spatiotemporal weighting, then the processing is faster, but the accuracy in distinguishing hand parts and users is reduced
Solution Approach 1:
The system applies partial weighting to touch events based on their position in the sequence rather than analyzing all possible sequence variations. By focusing computational effort on the most informative events (those with higher weights) and using approximate weighting schemes, the system achieves high accuracy without the excessive processing time that would result from exhaustive sequence analysis.
Solution Approach 2:
The system changes the parameter of time weighting dynamically based on the position of touch events in the sequence. Recent touch events are assigned higher temporal weights while older events receive lower weights, allowing the system to adaptively focus on the most relevant events for current classification decisions. This parameter change enables accurate real-time classification without processing the entire historical sequence at full resolution.
3Measurement precision
If vibro-acoustic waveform analysis is added to touch events, then the classification accuracy is improved, but the computational complexity increases
Solution Approach 1:
The system extracts only the most distinguishing features from the complex vibro-acoustic waveform signals rather than analyzing the complete signal spectrum. By identifying and extracting key features that are most indicative of different hand parts and touch types, the system reduces the computational complexity of waveform analysis while maintaining high classification accuracy. This selective feature extraction separates the essential information from the redundant data in the vibro-acoustic signals.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enhances the accuracy of touch screen event analysis by correctly identifying hand parts and users, reducing errors and ambiguities through the use of spatiotemporal weighting of touch event sequences, leading to improved user authentication and intentional input recognition.
Implementation Method 1
generating vibro-acoustic waveform signals using at least one sensor detecting each such touch event
Data Source
AI summary
A method of classifying touch screen events uses known non-random patterns of touch events over short periods of time to increase the accuracy of analyzing such events. The method takes advantage of the fact that after one touch event, certain actions are more likely to follow than others. Thus if a touch event is classified as a knock, and then within 500 ms a new event in a similar location occurs, but the classification confidence is low (e.g., 60% nail, 40% knuckle), the classifier may add weight to the knuckle classification since this touch sequence is far more likely. Knowledge about the probabilities of follow-on touch events can be used to bias subsequent classification, adding weight to particular events.