Ultrasonic Finger Press Detection Without Fixed Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing finger pressing state detection solutions in electronic devices suffer from low generalization capability due to variations in emission frequency, temperature, and differences in ultrasonic modules, leading to inconsistent signal intensity and difficulty in setting benchmark threshold values.
Innovation Solution
A finger pressing state detection method utilizing a neural network model, such as a recurrent neural network or convolutional neural network, that processes ultrasonic echo signals through pre-processing and normalization to generate model input data, eliminating the need for benchmark threshold values and enhancing generalization across various conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a benchmark threshold value is used for finger pressing state detection, then the detection process is simple, but the generalization capability is low due to variations in emission frequency, temperature, and ultrasonic modules
Solution Approach 1:
The patent transforms the detection approach from using fixed benchmark threshold values to using dynamic reference values generated through signal processing. The ultrasonic echo signal undergoes preprocessing including filtering, envelope detection, and normalization to adapt to varying conditions such as temperature, emission frequency, and ultrasonic module differences, thereby maintaining both simplicity and generalization capability
Solution Approach 2:
The patent replaces the mechanical threshold comparison method with a signal processing-based detection mechanism. Instead of directly comparing raw signal intensity against fixed thresholds, the system uses preprocessing operations (filtering, envelope detection, normalization) to transform the signal into a form that is invariant to environmental variations, substituting rigid thresholding with adaptive signal transformation
2Adaptability or versatility
If large amount of data covering different conditions is collected to set benchmark threshold values, then the detection coverage is improved, but the system complexity and difficulty in covering all cases increases
Solution Approach 1:
The patent extracts the essential characteristics of finger pressing states through signal preprocessing operations rather than relying on large datasets. By applying filtering, envelope detection, and normalization to extract key signal features, the system achieves comprehensive detection coverage without needing to collect and process extensive data covering all possible conditions
Solution Approach 2:
The patent performs preliminary signal processing (filtering, envelope detection, normalization) on the ultrasonic echo signal before detection. This preprocessing prepares the signal in advance to be invariant to environmental variations, eliminating the need for complex post-processing or extensive dataset collection to handle different conditions
3Use of energy by moving object
If traditional threshold-based detection is used, then the computational resources are saved, but the detection accuracy decreases under varying environmental conditions
Solution Approach 1:
The patent applies selective signal processing operations (filtering, envelope detection, normalization) that provide sufficient transformation to achieve environmental invariance without excessive computation. These targeted preprocessing steps improve detection accuracy under varying conditions while maintaining reasonable computational efficiency, avoiding both oversimplification and over-processing
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
The method achieves higher generalization capability and accuracy in detecting finger pressing states by accounting for variations in ultrasonic modules and environmental conditions, including temperature and moisture, without relying on threshold comparisons.
Implementation Method 1
An ultrasonic system may obtain a digital signal through emitting an ultrasonic wave and receiving a reflected sound wave
Implementation Method 2
due to influence of acoustic impedance on sound wave propagation, there are differences in acoustic impedance of different reflection surfaces
Data Source
AI summary
The present disclosure relates to the technical field of signal detection, and discloses a finger pressing state detection method, training method, electronic device, and medium, for improving generalization capability of finger pressing state detection. The method partially includes: pre-processing an ultrasonic echo signal to obtain model input data, where the ultrasonic echo signal is a corresponding ultrasonic echo signal after an ultrasonic array emits an ultrasonic signal to a pressing area; and inputting the model input data into a trained neural network model, so that the neural network model outputs a finger pressing state.