AI CBR Event Source Tracking via Pollution Spread Modeling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional CBR pollution tracking devices are limited in their ability to accurately track the source of pollution due to high costs and limited installation areas, leading to difficulties in determining the initial point of occurrence and time elapsed since an event.
Innovation Solution
An AI-based CBR event source tracking system that uses pollution spread information data from a CBR pollution spread prediction modeling tool to quickly and reliably track CBR pollution sources through artificial intelligence technology, rather than relying on real sensor data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional sensor devices are installed to detect pollution, then detection capability is improved, but installation cost and device complexity increase significantly
Solution Approach 1:
The patent replaces physical sensor devices with an AI-based virtual tracking system. Instead of using mechanical/electronic sensors to detect pollution, the system uses pollution spread prediction modeling tools combined with AI algorithms (transformer technique) to track and identify pollution sources computationally, thereby eliminating the need for expensive physical sensor installations.
Solution Approach 2:
The patent creates a virtual model of pollution spread rather than physically measuring it. By using pollution spread prediction modeling tools to generate simulated pollution concentration data and then applying AI techniques to this modeled data, the system creates a digital copy of the pollution tracking process that avoids the need for expensive physical sensing infrastructure.
2Device complexity
If sensors are installed in limited areas, then device cost is reduced, but the ability to accurately track pollution source and determine time elapsed deteriorates
Solution Approach 1:
The patent transitions from spatial measurement (physical sensor locations) to temporal-dimension measurement. By using pollution spread prediction modeling that simulates pollution concentration over time and space, the AI system can backtrack through time dimensions to identify when and where pollution originated, providing accurate source tracking without requiring spatially distributed physical sensors.
Solution Approach 2:
The system performs preliminary modeling of pollution spread patterns before actual pollution events occur. By pre-establishing pollution spread prediction models that account for various environmental conditions and dispersion patterns, the system can quickly and accurately trace back pollution sources when events occur, without needing pre-installed sensors in all possible locations.
3Loss of information
If real sensor data is used for tracking, then data availability is improved, but processing time and response time worsen due to limited sensor coverage
Solution Approach 1:
The patent uses copied and synthesized pollution spread data from modeling tools instead of relying solely on sparse real sensor data. By generating comprehensive pollution concentration distributions through prediction models, the system has sufficient data to perform accurate source tracking and provide rapid responses without being constrained by limited sensor coverage.
Solution Approach 2:
The system changes the parameter representation from discrete sensor readings to continuous pollution concentration fields. By modeling pollution spread as continuous concentration distributions across space and time rather than discrete point measurements, the AI system can perform more efficient source identification and provide faster responses.
Data Source
AI summary
The present invention relates to an A.I. based event source tracking system and a controlling method for the same, and may track a CBR pollution source which is quicker and more reliable by using pollution spread information data for each time zone calculated from a CBR pollution spread prediction modeling tool in a protection region through artificial intelligence technology rather than using real sensor data measured under various environmental conditions in a given zone when a CBR situation occurs, and predict an initial event occurrence source by learning pollution spread (pollution material concentration and deposition amount) information distributed for each time zone on a given space (map) in an image format by using an A.I. based video prediction or next frame prediction).