Wrist-Worn Fall Detection Using Phased Acceleration Alerts
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems fail to effectively detect and communicate specific conditions such as falls, seizures, and sleepwalks in humans, lacking a tailored approach for human movement complexity and variation.
Innovation Solution
A body-worn sensor, particularly a wrist-mounted device, uses an accelerometer and timer to analyze acceleration patterns relative to a reference frame, applying algorithms to detect falls, seizures, and sleepwalks, and communicate alerts to remote locations or locally, with AI-enhanced learning for improved reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a body-worn sensor is used to detect human fall conditions, then detection capability is improved, but device complexity increases due to the need for specialized algorithms and reference frame calculations
Solution Approach 1:
The fall detection system segments the complex detection task into distinct phases: initial low acceleration detection (first phase), high acceleration detection (second phase), and immobility confirmation (third phase). Each phase has specific acceleration thresholds and time durations that must be met, breaking down the complex problem of detecting various fall types into manageable sequential steps that improve accuracy while maintaining reasonable system complexity
Solution Approach 2:
The system introduces a temporal dimension by requiring that acceleration patterns be sustained for specific minimum durations (e.g., low acceleration for a first time period, high acceleration for a second time period). This time-based differentiation adds a new dimension to fall detection, allowing the system to distinguish between actual falls and transient movements, thereby improving measurement precision without requiring overly complex hardware
2Ease of operation
If a wrist-mounted sensor is used for sensing, then ease of operation is improved, but measurement precision deteriorates due to limb movement complexity
Solution Approach 1:
The system applies local quality by treating the wrist-mounted sensor data in context-specific ways. Rather than assuming all movements represent falls, the system analyzes acceleration patterns locally in time and space, applying different interpretation rules based on the phase of detection. This allows the simple wrist-mounted device to achieve accurate fall detection by focusing analysis on relevant local patterns rather than requiring complex global body motion capture
3Reliability
If multiple detection phases with time periods are implemented, then reliability is improved, but loss of time increases due to extended detection process
Solution Approach 1:
The system performs preliminary actions by first detecting low acceleration patterns before requiring high acceleration confirmation. This preliminary detection phase prepares the system for the actual fall detection, allowing it to distinguish between normal movements and potential falls more reliably. The multi-phase approach with minimum time requirements ensures that false alarms are reduced while maintaining relatively quick overall detection times
Solution Approach 2:
The system uses feedback mechanisms where each detection phase builds on the previous phase. The completion of the first time period with low acceleration triggers the second phase with high acceleration requirements, and successful completion of both triggers the third immobility confirmation phase. This feedback loop ensures reliable detection by requiring cumulative evidence across multiple phases, while the structured progression prevents indefinite detection delays
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 system provides accurate detection and communication of falls, seizures, and sleepwalks, enhancing user safety by improving detection accuracy over time through machine learning and customizable settings, allowing real-time monitoring and data analysis.
Implementation Method 1
the sensor can sense at least acceleration of the body relative to a reference frame
Data Source
AI summary
A system is provided which, in at least some embodiments, can read the vital signs of the body of a user utilizing a sensing device such as a smartwatch or smart phone (for example utilizing the IOS, Android or Pebble operating systems) and apply algorithms to interpret the vital signs and then send a notification with an escalation process to nominated carriers if the patient is interpreted as having a fall or fit or seizure. In at least some embodiments doctors or other parties can log in to a secured dashboard and check a patient data in real time. Doctors or other parties can analyze the history of the patient. In at least some embodiments, users/patients can also use data to keep track of fall or fit or seizure episodes and monitor their progress.