Mobile Device Fall Detection Using Pre- and Post-Impact Motion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems for fall detection using mobile devices are inefficient and prone to false positives, leading to unnecessary resource consumption and waste in emergency responses.
Innovation Solution
A mobile device equipped with motion sensors analyzes motion data before, during, and after an impact to accurately determine if a user has fallen and if assistance is needed, using statistical models and sensor fusion techniques to generate targeted notifications.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing fall detection systems use simple impact detection, then the device complexity is low, but the measurement precision is poor leading to false positives
Solution Approach 1:
The patent combines multiple sensors (accelerometer, gyroscope, barometer) into an integrated fall detection system. The accelerometer detects impact forces, the gyroscope measures orientation changes, and the barometer tracks altitude variations. By merging these sensor inputs and analyzing them collectively through statistical models, the system achieves high detection accuracy while managing complexity through unified processing architecture.
Solution Approach 2:
The system employs statistical models that analyze multiple parameters simultaneously including acceleration magnitudes, orientation angles, altitude changes, and temporal patterns. By monitoring changes in these parameters before, during, and after impact events, the system distinguishes between genuine falls and false triggers with high precision, transforming simple impact detection into multi-parameter analysis.
2Reliability
If the system generates notifications for all detected impacts, then the reliability of fall detection is high, but the loss of time and resources increases due to false positives
Solution Approach 1:
The system incorporates feedback mechanisms where the statistical models continuously learn from detected events and adjust detection thresholds. After each impact event, the system analyzes the full sequence of sensor data and provides feedback to refine future detection accuracy. This feedback loop reduces false positives while maintaining high reliability by adapting to individual user patterns and environmental conditions.
Solution Approach 2:
The system performs preliminary analysis of motion patterns before triggering notifications. Statistical models evaluate pre-impact behaviors, impact characteristics, and post-impact recovery patterns to predict genuine falls in advance. This preliminary action filters out false positives before emergency responses are activated, saving time and resources while maintaining high detection reliability.
3Measurement precision
If the system analyzes motion data from multiple time intervals, then the measurement precision improves, but the use of energy increases
Solution Approach 1:
The patent segments the analysis into distinct time intervals: pre-impact baseline period, impact event period, and post-impact recovery period. Each interval is analyzed with appropriate computational intensity - the baseline period establishes normal patterns with lower processing, the impact period uses intensive analysis for accurate detection, and the recovery period monitors with reduced processing. This segmentation optimizes energy usage while maintaining high measurement precision.
Solution Approach 2:
The system employs periodic sampling of sensor data at different frequencies across time intervals. During stable periods, sampling occurs at lower frequencies to conserve energy, while during impact events, sampling frequency increases automatically. This periodic action with variable intensity maintains measurement precision during critical moments while reducing overall energy consumption during normal operation.
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 reduces false positives, efficiently deploying resources by accurately determining falls and the need for assistance, thereby optimizing the use of computational and network resources.
Implementation Method 1
A motion sensor is a device that measures the motion experienced by an object (e.g., the velocity or acceleration of the object with respect to time, the orientation or change in orientation of the object with respect to time, etc.)
Implementation Method 2
determining, by the mobile device, an impact experienced by the user based on the motion data, the impact occurring during a first interval of the time period
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
In an example method, a mobile device obtains a signal indicating an acceleration measured by a sensor over a time period. The mobile device determines an impact experienced by the user based on the signal. The mobile device also determines, based on the signal, one or more first motion characteristics of the user during a time prior to the impact, and one or more second motion characteristics of the user during a time after the impact. The mobile device determines that the user has fallen based on the impact, the one or more first motion characteristics of the user, and the one or more second motion characteristics of the user, and in response, generates a notification indicating that the user has fallen.