Activity Model Anomaly Detection for Emergency Alerting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Elderly individuals living alone or in care centers without constant caregiver supervision often experience emergency situations, such as falls, which may go undiscovered for days, reducing treatment success and increasing damage.
Innovation Solution
A system and method using a machine with processors and memory to track user activity across multiple devices, develop an activity model, detect anomalies, calculate confidence and severity values, and alert emergency contacts via a network when assistance is needed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If elderly people live alone or without constant caregiver supervision, then their independence and quality of life are improved, but their safety and ability to receive timely emergency assistance deteriorate
Solution Approach 1:
The system enables elderly individuals to independently monitor their own activity patterns and automatically detect anomalies without requiring constant caregiver supervision. The activity model continuously learns from user behavior and autonomously identifies when assistance may be needed, allowing the user to maintain independence while ensuring safety.
Solution Approach 2:
The system provides continuous feedback by monitoring activity signals from multiple devices, comparing them against the learned activity model, and automatically generating alerts when anomalies are detected. This closed-loop feedback mechanism ensures timely emergency detection while allowing the user to live independently.
2Measurement precision
If multiple devices are used to track user activity, then the accuracy and reliability of emergency detection is improved, but the system complexity and difficulty of implementation increases
Solution Approach 1:
The system combines signals from multiple devices (smartphone, wearable, tablet, computer, TV, refrigerator) into a unified activity model. By merging data from these diverse sources, the system achieves high detection accuracy while managing complexity through integrated signal processing and a centralized anomaly detection algorithm.
Solution Approach 2:
The activity model serves multiple functions: it learns normal user behavior patterns, detects anomalies, generates emergency alerts, and adapts to changing user habits. This multi-functional approach allows a single system component to handle diverse detection needs across multiple devices, reducing overall system complexity.
Data Source
AI summary
In example embodiments, a machine, including one or more processors and a memory, tracks, by communicating over a network with a plurality of devices associated with a user, activity of the user. The machine develops, using the one or more processors, an activity model for the user based on the tracked activity of the user. The machine determines, an anomaly in a current activity of the user relative to the developed activity model, the anomaly having a type and a duration. The machine calculates, based on the type and the duration of the anomaly, a confidence value corresponding to whether the user needs assistance and a severity value indicating severity of the user's need for assistance. The machine provides, to an emergency contact and via the network, an alert indicating that the user needs assistance based on the confidence value or the severity value.