Wearable Fall Detection Using Multi-Threshold Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing fall detection technologies often produce false positives due to inability to accurately differentiate between falls and other movements, such as drops or tosses, leading to unnecessary alerts and resource allocation.
Innovation Solution
A wearable device equipped with accelerometers, barometers, and optional sensors for light, sound, temperature, magnetic, and electric fields, uses multiple acceleration magnitude thresholds and orientation change analysis to categorize movement data into distinct fall signature sets, reducing false indications by comparing data against empirical criteria for various types of falls.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a single acceleration threshold is used for fall detection, then the device complexity is low, but the measurement precision deteriorates leading to false positives
Solution Approach 1:
The patent segments fall detection into multiple characteristic segmentations based on empirical fall data, where each segmentation has its own acceleration thresholds and criteria. This allows the system to differentiate between various types of falls (e.g., forward fall, backward fall, side fall) with different motion patterns, thereby improving detection accuracy without requiring a single complex algorithm to handle all cases
Solution Approach 2:
The patent changes the parameters (acceleration thresholds, orientation angles, duration criteria) based on the specific characteristic segmentation being evaluated. By adjusting these parameters according to the type of fall being detected, the system achieves high precision for different fall scenarios while maintaining relatively simple detection logic for each segment
2Reliability
If multiple characteristic segmentations with different criteria are used, then the reliability of fall detection improves, but the device complexity increases
Solution Approach 1:
The detection system is segmented into multiple independent characteristic segmentations, each with its own set of criteria derived from empirical fall data. The processor evaluates data against these segmentations in a structured manner, improving reliability by covering diverse fall scenarios while maintaining manageable complexity through modular evaluation
Solution Approach 2:
The patent performs preliminary action by pre-establishing multiple characteristic segmentations and their corresponding criteria based on empirical fall data before deployment. This allows the system to have ready-made evaluation frameworks for different fall types, reducing the complexity of real-time decision-making while maintaining high reliability
3Measurement precision
If empirical fall data from multiple sources is collected and analyzed, then the measurement precision improves, but the loss of time for data processing increases
Solution Approach 1:
The patent performs preliminary action by collecting and analyzing empirical fall data from multiple sources (wearable devices, emergency calls, law enforcement, medical personnel) before deployment to establish the characteristic segmentations. This pre-processing of data creates ready-to-use criteria that can be quickly applied during actual fall detection, improving precision without causing time delays during critical detection moments
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 effectively reduces false alerts by accurately distinguishing between falls and other movements, ensuring that only confirmed falls trigger alerts and minimize unnecessary resource allocation.
Implementation Method 1
The device includes accelerometers, barometer(s), and optionally other sensors that detect, among other environmental conditions
Implementation Method 2
The processor determines whether sensor data meets a first criterion for a parameter (such as whether the data exceeds an acceleration or barometric pressure maximum, or threshold)
Data Source
AI summary
A device monitors sensor data generated by movement of a wearer and determines whether the data indicates a fall. The device may include accelerometers, barometer(s), and sensors that detect, light, sound, temperature, magnetic and electric fields, strain-force on the device, and other environmental conditions. A processor determines whether the data meets a first criterion for a parameter (i.e., exceeding an acceleration or barometric pressure maximum threshold). The first criterion corresponds to a first set of known-fall event data sets. If the first criterion is met, the processor generates a full indication. If the data does not meet the first criterion, the processor compares the data to a second criterion for the same, or different, parameter. If the second parameter is met, further processing confirms a fall determination by comparing the data to other criteria corresponding to known-fall event data sets that differ from the first set.