IoT Fleet Stop Detection Using Geofence Transition Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing fleet management systems struggle to accurately distinguish between true and false arrival/departure events at planned stops due to proximity-based geo-fence evaluations, leading to false positives and the need for human intervention.
Innovation Solution
Implementing a transition region and a waiting time duration window to filter out false arrival and departure events, using a combination of location-based and time-based filters to determine true arrival and departure times.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a simple geofence boundary is used to detect arrival/departure events, then the detection speed is fast, but the accuracy is low due to false positives from overlapping geofences and GPS inaccuracies
Solution Approach 1:
The geofence boundary is segmented into two distinct regions: a transition region (inner boundary) and a geofence boundary (outer boundary). This segmentation allows the system to detect when a vehicle enters the transition region (potential arrival) and when it exits the geofence boundary (confirmed departure), thereby improving detection accuracy by filtering out false positives from overlapping geofences while maintaining reasonable system complexity.
2Reliability
If a transition region and waiting time filter are added to improve detection accuracy, then false positives are reduced, but the time required to confirm arrivals increases
Solution Approach 1:
The system performs preliminary detection when the vehicle enters the transition region, marking it as a potential arrival event. The waiting time filter is then applied to confirm whether the vehicle remains in the geofence for a sufficient duration. This preliminary action allows the system to identify potential arrivals quickly while using the waiting time filter to confirm reliability, balancing between speed and accuracy.
3Measurement precision
If the geofence boundary is made larger to account for GPS inaccuracies, then more arrivals are captured, but false positives from overlapping geofences increase
Solution Approach 1:
The transition region acts as an intermediary buffer between the vehicle and the geofence boundary. When the vehicle enters the transition region, the system initiates an arrival detection process that requires the vehicle to remain in the geofence for a waiting time period. This intermediary mechanism allows the system to account for GPS inaccuracies by capturing vehicles that approach within the transition region while filtering out false positives by requiring sustained presence within the geofence boundary.
Data Source
AI summary
Embodiments detect stops by an entity on a pre-planned trip including a plurality of stops and a planned sequence of stops, each stop including a geofence boundary. For each stop, embodiments add an arrival transition region extending inward from the geofence boundary. Embodiments receive a first geo-location message indicating a first location and corresponding to a first time for the entity and determine whether the first location falls within a first arrival transition region corresponding to a first stop having a first geofence boundary. When the first location falls within the first arrival transition region, embodiments wait for a predefined transitional time period. During the predefined transitional time period, when a second geo-location message is received indicating a second location inside the first geofence boundary and outside the first arrival transition region, the first time is determined to be an arrival time for the first stop.