Mobile Sensor Wellness Event Detection With Predictive Activity Profiles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wellness monitoring systems rely on wearable technologies that suffer from user non-compliance and incapacity, leading to inaccurate reporting of health incidents, and lack the ability to verify actual events from a remote distance.
Innovation Solution
A system utilizing mobile device sensors and AI-enabled predictive models to detect and respond to impending events, leveraging existing sensors in mobile devices and property monitoring systems to analyze sensor data for proactive wellness event detection and reporting.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If wearable technologies are used to capture user input and characterize movements, then wellness monitoring capability is provided, but user non-compliance and health-related incapacitation reduce general efficacy
Solution Approach 1:
The system uses the mobile device itself (which the user already carries and interacts with) to perform wellness monitoring functions. The mobile device's existing sensors (camera, microphone, accelerometer, GPS) are leveraged to detect wellness events without requiring separate wearable devices, thereby eliminating the compliance issue associated with wearing dedicated safety devices.
Solution Approach 2:
The mobile device is used for multiple purposes: it serves as both a communication tool and a wellness monitoring device. By integrating wellness monitoring capabilities into the mobile device's existing sensor suite, the system eliminates the need for dedicated wearable equipment, thereby improving user compliance and reliability.
2Reliability
If dedicated personal safety devices are required for monitoring, then monitoring functionality is provided, but the system cannot verify incidence of actual or suspected well-being events
Solution Approach 1:
The system combines multiple sensor types (camera, microphone, accelerometer, GPS) within the mobile device to create a comprehensive monitoring system. This multi-sensor approach allows the system to cross-validate information and verify the occurrence of wellness events more accurately, as each sensor provides complementary data that can be correlated to confirm event incidence.
Solution Approach 2:
The system continuously monitors sensor data and provides feedback to determine whether a wellness event has occurred. By analyzing patterns across multiple sensors and comparing them against baseline behavior, the system can verify whether detected events are actual incidents or normal variations, thereby improving measurement precision and reducing false alarms.
3Productivity
If reactive assistance is provided after events occur, then response capability is established, but proactive intervention to prevent pending wellness issues is not enabled
Solution Approach 1:
The system performs preliminary analysis of sensor data to detect patterns that indicate impending wellness events before they actually occur. By continuously monitoring and comparing current sensor readings against learned behavioral patterns, the system can identify deviations that suggest a wellness issue is developing, enabling proactive intervention to prevent the event from happening in the first place.
Solution Approach 2:
The system rapidly analyzes sensor data in real-time to detect wellness events as they occur or are about to occur, skipping the traditional reactive approach of waiting for event confirmation. This rapid detection and response capability allows the system to intervene proactively, reducing the time loss associated with reactive assistance and enabling prevention of wellness issues before they manifest.
Data Source
AI summary
Methods and systems, including computer programs encoded on a computer storage-medium, are disclosed for implementing intelligent detection of wellness events using mobile device sensors and cloud-based learning systems. A system obtains sensor data generated by sensors integrated in a mobile device of a user. A machine-learning (ML) engine of the system generates a predictive model that identifies behavioral trends of the user. The model is generated using a neural network trained to identify patterns representing user trends in the sensor data. Based on communications with the device, the model is used to generate activity profiles of the user from the behavioral trends. The model is used to detect abnormal events involving the user when a parameter value of the activity profile exceeds a threshold. Notifications directed to assisting the user with alleviating the abnormal event are generated after detecting the abnormal events.