Force Sensor Classification for Reliable Virtual Button Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing sensor systems face challenges in accurately classifying sensor samples due to noise and non-linearities, particularly when using multiple force sensors to detect virtual button presses, leading to erroneous interpretations of user inputs.
Innovation Solution
A classification system comprising a classifier and determiner that processes sensor signals from multiple force sensors to generate classification results, with a controller for controlling the system based on input signals, to accurately identify defined target events and reduce errors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple force sensors are used to detect virtual button presses, then the coverage and detection capability are improved, but noise and non-linearities increase leading to classification errors
Solution Approach 1:
The patent segments the sensor system into multiple independent force sensors (N sensors) distributed across different locations, each providing individual measurements. This segmentation allows the system to cover a larger area and detect presses at multiple locations simultaneously, improving detection capability while maintaining the ability to analyze individual sensor responses to filter out noise and anomalies.
2Reliability
If virtual buttons are implemented using force sensors, then physical button wear is eliminated and waterproofing is improved, but erroneous interpretation of user inputs occurs due to noise
Solution Approach 1:
The patent implements a feedback mechanism where the controller receives sensor responses from multiple force sensors, analyzes the pattern and magnitude of responses, and uses this feedback to determine whether a valid button press has occurred. The system continuously monitors sensor outputs and adjusts its interpretation based on the collective response pattern, enabling it to distinguish between intentional presses and noise-induced anomalies.
3Ease of operation
If sensor responses are interpreted to detect button presses, then user input detection is enabled, but anomalies such as pinching or bending are erroneously classified as valid presses
Solution Approach 1:
The patent merges the responses from multiple force sensors (N sensors) to make a unified determination about button press validity. By combining and analyzing the collective response pattern across all sensors rather than relying on individual sensor readings, the system can distinguish between genuine button presses (which produce characteristic response patterns across multiple sensors) and anomalies like pinching or bending (which produce different response patterns), thereby reducing false positives while maintaining ease of operation.
Data Source
AI summary
A classification system for classifying sensor samples in a sensor system, the sensor system comprising N force sensors each configured to output a sensor signal, where N≥1, each sensor sample comprising N sample values from the N sensor signals, respectively, the classification system comprising: a classifier configured, for each of a series of candidate sensor samples, to perform a classification operation based on the N sample values concerned and generate a classification result which labels the candidate sensor sample as indicative of a defined target event, thereby generating a series of classification results corresponding to the series of candidate sensor samples, respectively; a determiner configured to output at least one event determination based on the series of classification results; and a controller configured to control the classifier and/or the determiner based on one or more controller input signals.