Automated Hot Area Detection in Heat Map Visualizations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for detecting hot areas in heat maps require human intervention, leading to inconsistencies and resource-intensive processing times, and struggle to identify areas of different shapes and patterns effectively.
Innovation Solution
A computer-implemented method using a density-based clustering algorithm to convert two-dimensional heat maps to one-dimensional data, cluster cells, calculate mean values, and automatically identify dense regions as hot areas without prior shape assumptions, enabling consistent and efficient detection across multiple areas.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual methods are used to identify hot areas in heat maps, then domain knowledge and expertise can be applied, but processing time increases and consistency across multiple users is difficult to achieve
Solution Approach 1:
The patent replaces manual visual inspection and manual threshold adjustment with an automated computer-implemented system. The system uses image processing techniques including converting the heat map to grayscale, applying binary thresholding, and performing contour detection to automatically identify hot areas. This substitution of manual mechanical processes with automated computational processes eliminates the time consumption and inconsistency associated with manual methods while maintaining or improving detection accuracy.
2Productivity
If fixed threshold methods are used to detect hot areas, then processing is faster, but areas of different shapes and patterns cannot be effectively identified
Solution Approach 1:
The patent employs dynamic contour detection that adapts to different hot area shapes and patterns. Instead of using fixed geometric assumptions, the system performs contour detection on the binary thresholded image, which automatically identifies regions of interest regardless of their shape. The contour detection algorithm dynamically adjusts to the actual distribution of high-value cells in the heat map, enabling it to detect circular, rectangular, irregular, or complex-shaped hot areas effectively.
Solution Approach 2:
The system changes parameters dynamically during processing. The threshold value is determined through image processing rather than being fixed beforehand. The contour detection parameters adapt to the specific heat map being analyzed, allowing the system to identify hot areas of various shapes and sizes. This parameter adaptability enables the system to maintain high processing speed while effectively recognizing diverse hot area patterns.
3Loss of time
If automated methods are implemented, then processing time decreases, but the system requires complex algorithms and computational resources
Solution Approach 1:
The patent segments the hot area detection process into distinct, manageable steps: (1) converting the heat map visualization to a grayscale image, (2) applying binary thresholding to create a binary image that separates high-value cells from low-value cells, and (3) performing contour detection to identify the boundaries of hot areas. This segmentation of the detection process into modular stages reduces the complexity of any single algorithm while achieving fast automated detection through the coordinated execution of multiple simpler operations.
Data Source
AI summary
The present disclosure involves systems, software, and computer implemented methods for automatically detecting hot areas in heat map visualizations. One example method includes identifying a two-dimensional heat map. The identified two-dimensional heat map is converted to a one-dimensional heat map. Cells of the one-dimensional heat map are clustered using a density-based clustering algorithm to generate at least one dense region of cells. A mean value of cells in each dense region is calculated and the dense regions are sorted by mean value in descending order. An approach for identifying hot areas is selected and the selected approach is used to identify at least one dense region as a hot area of the one-dimensional heat map.