Edge Model Detection for Distributed Data Collection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The high costs of data transfer from vehicle event recorders to central servers limit the ability to upload and analyze sensor data fully, reducing the realization of its value due to bandwidth constraints.
Innovation Solution
A system that distributes data analysis to vehicle event recorders equipped with modular detectors, allowing on-device data identification and uploading only relevant data, thereby minimizing bandwidth usage and enabling extensive data processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If sensor data is uploaded to central server for analysis, then data analysis capabilities are improved, but data transfer costs increase significantly
Solution Approach 1:
The system segments the data analysis function by deploying modular detectors at the edge device (vehicle event recorder) rather than relying solely on central server processing. This allows local identification and filtering of relevant data, reducing the volume of data that needs to be transferred to the central server for analysis.
Solution Approach 2:
The system performs preliminary data identification and filtering at the edge device using modular detectors before uploading data to the central server. Relevant data is identified and selected locally in advance, so only necessary data is transferred, reducing transfer costs while maintaining analysis capabilities.
2Productivity
If more sensor data is uploaded for analysis, then analysis comprehensiveness is improved, but bandwidth requirements increase
Solution Approach 1:
The system extracts and identifies relevant data using modular detectors at the edge device before uploading to the central server. By taking out only the necessary data elements that meet identification criteria, the system reduces bandwidth requirements while maintaining analysis comprehensiveness for the identified data.
Solution Approach 2:
The system applies local data identification and filtering quality at the edge device using modular detectors. Each detector is optimized for specific data characteristics, allowing local quality control to ensure only relevant data is uploaded, reducing overall bandwidth requirements while maintaining comprehensive analysis of identified data.
3Productivity
If modular detectors are distributed to vehicles, then data processing capabilities at edge are improved, but system complexity increases
Solution Approach 1:
The system uses universal modular detectors that can be deployed across multiple vehicle event recorders. These detectors are designed with multi-functionality to handle various data types and identification tasks, allowing the same detector framework to serve multiple purposes while reducing overall system complexity through standardization.
Solution Approach 2:
The system implements a nested architecture where modular detectors are contained within the vehicle event recorder, which itself is part of the larger distributed system. This nesting allows complex functionality to be organized in hierarchical layers, with detectors nested within vehicles nested within the central management system, making the overall complexity manageable through modular organization.
Data Source
AI summary
The system includes a device database, an interface, and a processor. The device database stores a set of times and corresponding set of locations associated with a device. The interface is configured to receive a request for identification of sensor data associated with a target. The request includes a request time and/or a request location. The processor is configured to: determine a set of devices associated with the time and/or the location using the device database; provide a request to search for the sensor data associated with the target at the time and/or the location to each device of the set of devices; and receive an indication of the identification of sensor data associated with the target from an identifying device of the set of devices.