Crowd-Size Estimation via Learned Cost Function
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing population estimation methods require extensive external information and large learning datasets for supervised learning, and semi-supervised estimation schemes struggle with manually determining a suitable cost function, especially when data is limited, leading to inaccurate predictions.
Innovation Solution
A computer-based system estimates time-specific interareal movement probabilities and area populations using a learned cost function, leveraging observed data and a collective flow diffusion model to efficiently estimate populations at unobserved times without requiring external features or large datasets.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If supervised learning is used for population prediction, then prediction capability is improved, but large amounts of learning data and external information are required
Solution Approach 1:
The invention extracts and utilizes only the necessary movement probability information from the observed population data, rather than requiring large volumes of external feature data. By focusing on the essential movement patterns between areas, the system achieves accurate prediction with minimal data requirements.
Solution Approach 2:
The system performs self-learning by automatically determining the cost function from the observed data itself, rather than requiring external information or manual specification. The learning process uses the data's inherent structure to generate the prediction model, eliminating the need for large external datasets.
2Ease of operation
If manual cost function determination is used in semi-supervised estimation, then estimation process is simplified, but prediction accuracy deteriorates when data is limited
Solution Approach 1:
The invention introduces an automatic cost function determination mechanism that acts as an intermediary between the observed data and the prediction model. This intermediary component learns the appropriate cost function from the data itself, bridging the gap between simplicity and accuracy without requiring manual intervention or large datasets.
Solution Approach 2:
The system dynamically adjusts the cost function parameters based on the observed data characteristics rather than using fixed manual specifications. This adaptive parameter adjustment allows the system to maintain both operational simplicity and prediction accuracy by automatically adapting to the data at hand.
Data Source
AI summary
Disclosed is a time-specific area population estimation method executed by a computer. The method includes estimating a time-specific interareal movement probability, based on observed time-specific population in an area and a set of candidate areas for a movement from the area in a unit time; and estimating a population in the area at a time at which no observation is performed by using a cost function learned in the estimating of the time-specific interareal movement probability.