Sensor Array Subject Identification for Breathing Monitoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Sensor-based monitoring systems, such as those using Doppler Radar sensors, face challenges in adapting to individual users due to sensitivity to subject-specific characteristics like BMI and thorax size, making it difficult to optimize signal acquisition and analysis for accurate breathing activity monitoring.
Innovation Solution
A method that involves acquiring subject-related sensor signals, extracting signal patterns in the time, frequency, or time-frequency domains, and comparing them to pre-stored patterns to identify the subject, allowing for configuration of the sensor array and signal processing parameters for personalized monitoring.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If all sensors in the array are used to detect breathing activity, then measurement precision is improved, but device complexity and energy consumption increase
Solution Approach 1:
The sensor array is divided into multiple sensor groups, where each group is responsible for monitoring a specific region or aspect of the subject's breathing. This segmentation allows the system to achieve comprehensive monitoring coverage while reducing the computational complexity of processing signals from all sensors simultaneously, as each group can be processed independently.
Solution Approach 2:
The system dynamically selects and activates only the necessary sensors or sensor groups based on the subject's position, body characteristics, and breathing patterns. This dynamic adaptation allows the system to maintain high measurement precision while reducing device complexity and energy consumption by avoiding the use of all sensors in all conditions.
2Measurement precision
If radiant power emitted by radar sensors is increased, then signal quality and measurement precision improve, but energy consumption increases
Solution Approach 1:
The radiant power of the radar sensors is dynamically adjusted based on the detected subject characteristics, distance, and signal quality requirements. The system increases power only when necessary to maintain measurement precision, and reduces power during stable monitoring or when subjects are closer, thereby optimizing the trade-off between signal quality and energy consumption.
Solution Approach 2:
The system changes the radiant power parameter adaptively based on real-time conditions such as subject distance, body size, and breathing amplitude. By adjusting this parameter dynamically rather than using a fixed high power setting, the system maintains measurement precision while significantly reducing overall energy consumption during normal operation.
3Measurement precision
If the system is adapted to individual users, then measurement precision and ease of operation improve, but device complexity increases
Solution Approach 1:
The system performs preliminary measurements and analysis during an initial setup phase to automatically determine subject-specific characteristics such as body size, thorax cross-section, and optimal sensor configurations. These preliminary actions create stored profiles that enable precise individualized monitoring without requiring complex real-time adjustments during actual use, thus improving precision while managing complexity.
Solution Approach 2:
The system automatically adapts to individual users through self-service mechanisms, where the monitoring system itself performs the analysis and configuration optimization without requiring external intervention or complex manual setup. The system extracts signal patterns, compares them to reference data, and automatically configures optimal parameters, making the adaptation process simple and automated.
4Measurement precision
If signal processing algorithms are optimized for specific subjects, then measurement precision improves, but ease of operation deteriorates
Solution Approach 1:
The signal processing algorithms automatically adapt to individual subjects through self-service optimization, where the system extracts signal patterns from raw sensor data, compares them to reference patterns, and automatically selects or adjusts processing parameters. This automation eliminates the need for manual algorithm configuration by operators, maintaining high measurement precision while preserving ease of operation.
Solution Approach 2:
The system performs preliminary signal pattern extraction and algorithm optimization during an initial setup or learning phase, storing the optimized parameters for later use. This preliminary action allows the system to achieve subject-specific measurement precision without requiring complex real-time algorithm adjustments, thereby maintaining ease of operation during actual monitoring.
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
Enables clear identification of subjects, allowing the system to automatically adapt and optimize sensor configuration for accurate breathing activity monitoring, improving the system's ability to distinguish between different users and personalize settings.
Implementation Method 1
Sensor based monitoring systems exist that comprise an array of contactless sensors such as radar sensors based on the Doppler Radar principle. Each of these sensors is able to detect a change of a distance of an object from the sensor.
Data Source
AI summary
The invention relates to a method and device for identifying a subject in a sensor based monitoring system. This method comprises an acquisition step wherein sensors of a sensor array acquire subject related sensor signals, a pattern extraction step wherein a signal pattern is derived from the sensor signals acquired in the preceding acquisition step, and an identification step wherein the signal pattern derived in the preceding pattern extraction step is compared to predetermined signal patterns, each predetermined signal pattern being related to a subject profile, to identify a subject profile whose predetermined signal pattern related thereto matches the derived signal pattern.