PPG Signal Processing for Virtual Vehicle Key
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing solutions for biometric identification using photoplethysmography (PPG) signals face issues with robustness, accuracy, and time-consuming processing, particularly when employing low-cost and low-complexity components, and are prone to noise and signal stabilization problems.
Innovation Solution
A method and system utilizing Silicon PhotoMultiplier (SiPM) detectors for processing PPG signals, which includes a pipeline with signal filtering, pattern recognition, and machine learning for robust car-driver profiling, avoiding frequency domain conversions and relying solely on PPG sensors for efficient, high-speed, and high-precision identification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If frequency-analysis based methods are used for PPG signal processing, then measurement precision is improved, but processing time increases significantly
Solution Approach 1:
The patent replaces frequency-domain analysis methods with time-domain signal processing techniques. Specifically, it uses temporal correlation analysis and dynamic time warping (DTW) algorithms to compare PPG waveforms directly in the time domain, avoiding the computationally intensive Fourier transforms and frequency spectrum analysis. This substitution maintains identification accuracy while dramatically reducing processing time and computational load.
Solution Approach 2:
The patent extracts only the essential temporal features from PPG signals that are necessary for identification, such as waveform morphology, pulse arrival time, and characteristic interval durations. By focusing on these specific temporal characteristics rather than analyzing the entire frequency spectrum, the system achieves accurate identification with minimal processing time.
2Device complexity
If low-cost PPG sensors are used, then device complexity is reduced, but signal robustness and stability deteriorate
Solution Approach 1:
The patent implements self-calibration and adaptive normalization algorithms that automatically adjust to varying signal quality conditions. The system continuously learns the user's baseline PPG characteristics and adapts to changes in sensor contact, lighting conditions, and physiological states, enabling reliable operation with simple low-cost sensors without requiring complex hardware stabilization.
Solution Approach 2:
The patent dynamically adjusts signal processing parameters such as filtering cutoff frequencies, sampling rates, and correlation window lengths based on the detected signal quality. When signal robustness is compromised, the system automatically modifies these parameters to optimize performance, allowing reliable operation across varying conditions with minimal hardware complexity.
3Device complexity
If simple signal filtering is applied, then device complexity is reduced, but identification precision deteriorates
Solution Approach 1:
The patent applies targeted pre-processing steps such as band-pass filtering and baseline correction before the main identification algorithm. These preliminary actions remove obvious noise and artifacts while preserving the essential waveform features needed for accurate comparison, achieving good identification precision with relatively simple processing.
Solution Approach 2:
The patent replaces complex multi-stage filtering systems with time-domain signal enhancement techniques that directly improve waveform quality for comparison purposes. Methods such as template subtraction and adaptive baseline removal are used instead of cascaded digital filters, maintaining identification precision while reducing processing complexity.
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 solution achieves robust and accurate near-real-time identification with high precision (approximately 99.7% accuracy) and resilience to hacking attempts, enhancing safety and security in ADAS and DADSS applications.
Implementation Method 1
A method and system utilizing Silicon PhotoMultiplier (SiPM) detectors for processing PPG signals
Data Source
AI summary
An embodiment method comprises collecting at least one electrophysiological signal of a human over a limited time duration, and computing a set of electrophysiological signal features. The computing comprises at least one of: providing at least one reference electrophysiological signal and applying dynamic time warping processing to the at least one collected and at least one reference electrophysiological signals, applying stacked-auto-encoder artificial neural network processing to the collected electrophysiological signal, or filtering the electrophysiological signal collected via joint low-pass and high-pass filtering. The method further comprises applying pattern recognition processing to the computed set of features, producing a virtual key signal indicative of an identity of the human, and applying the virtual key signal to a user circuit to switch it between a first state and a second state as a result of the virtual key signal matching an authorized key signal stored in the user circuit.