ML-Based Tracking Routines for Low-Power Location Alerts
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic tracking devices consume excessive power and transmit unnecessary alerts due to reliance on GPS and cellular signals, which are not always available, leading to inefficient power usage and user annoyance.
Innovation Solution
A tracking device that scans access point signals, learns movement patterns using machine learning, and adjusts power consumption based on detected routines, reducing unnecessary transmissions and conserving power by predicting deviations from predefined paths.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS and cellular signals are used for tracking, then location accuracy is improved, but power consumption increases
Solution Approach 1:
The system uses periodic scanning of access point signals instead of continuous GPS tracking. The machine learning model processes signals at intervals, determining location only when necessary, thereby reducing power consumption while maintaining acceptable tracking accuracy through pattern recognition of periodic movement routines.
Solution Approach 2:
The patent replaces the mechanical/GPS-based location system with a signal-processing approach using access point scans and machine learning. Instead of relying on satellite signals, the system uses wireless signal patterns combined with ML algorithms to infer location and movement patterns, significantly reducing power requirements.
2Reliability
If continuous monitoring and alerting is implemented, then tracking reliability is improved, but user annoyance increases due to unwanted notifications
Solution Approach 1:
The machine learning model continuously learns from historical signal data and feedback about actual movement patterns. This feedback mechanism allows the system to refine its understanding of routines over time, improving tracking reliability while learning to distinguish between significant deviations and normal variations, thereby reducing false alerts.
Solution Approach 2:
The system dynamically adjusts alerting parameters based on learned routines. Instead of using fixed thresholds, the ML model adapts notification criteria to match the tracked subject's typical behavior patterns, ensuring alerts are generated only for genuine anomalies rather than normal routine variations.
3Measurement precision
If GPS transmissions are performed frequently, then location data accuracy is improved, but transmission costs increase
Solution Approach 1:
The system performs partial location updates by transmitting only when routine deviations are detected, rather than continuous GPS reporting. This partial action approach maintains sufficient location data accuracy for monitoring purposes while dramatically reducing transmission frequency and associated costs.
Solution Approach 2:
The machine learning model performs local processing and decision-making about when transmissions are necessary, eliminating the need for constant cloud-based location verification. The device serves itself by autonomously determining transmission timing based on learned patterns, reducing overall system transmission requirements.
Data Source
AI summary
A method comprises accessing historical signal and other information received from a tracking device configured to scan for signals transmitted by local devices and record other data as the tracking device moves within the geographic area during each of a plurality time intervals. A training dataset is generated based on the historical signal and other information and used to train a machine learning model configured to predict tracking device movement patterns. The machine learning model is applied to current signal and other information to detect a variance from one or more predefined routines associated with the tracking device. A notification is sent to a monitoring device associated with the tracking device in response to detecting the variance from the one or more predefined routines associated with the tracking device.