Data Clustering via Fixed Center Matrix and Circle Merging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional data clustering algorithms, such as K-means, are inefficient for large datasets, requiring excessive computational time and bandwidth due to their reliance on dynamic center points and sequential processing.
Innovation Solution
A data clustering method that defines a region of interest, constructs a center matrix with fixed center points, maps data points to corresponding circles, merges overlapping circles based on data point distribution, and identifies clusters through graph traversal, optimized for implementation on heterogeneous computer systems with parallel processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional data clustering algorithms (e.g., K-means) are implemented on heterogeneous platforms with multiple processors, then parallel processing capability is utilized, but computational time remains prohibitively long for large datasets
Solution Approach 1:
The patent segments the data clustering problem into multiple independent processing tasks by dividing the dataset into partitions that can be processed in parallel across multiple processors. Each processor handles a specific partition, performing local clustering operations independently, which significantly reduces the overall computational time compared to sequential processing of the entire dataset.
Solution Approach 2:
The patent performs preliminary actions by pre-processing the dataset to identify potential cluster centers and partition the data before the main clustering execution. This pre-computation step prepares the data in an optimized format that enables faster parallel processing during the actual clustering phase, reducing the time required for the computationally intensive operations.
2Reliability
If conventional data clustering algorithms process large datasets, then comprehensive data analysis is achieved, but transmission bandwidth requirements become excessive
Solution Approach 1:
The patent segments the large dataset into smaller partitions that can be processed locally on different processors. This segmentation reduces the amount of data that needs to be transmitted across the network, as each processor works with only its local partition. The segmented approach maintains analysis completeness by ensuring that all partitions are processed and their results aggregated, while significantly reducing transmission bandwidth requirements.
Solution Approach 2:
The patent introduces an intermediary mechanism in the form of a coordination layer that manages data partitioning and result aggregation. This intermediary handles the minimal necessary data exchange between processors, coordinating the distributed processing without requiring excessive bandwidth. The intermediary ensures that only essential information is transmitted between nodes, maintaining data analysis completeness while optimizing bandwidth usage.
Data Source
AI summary
A data-clustering method generates data clusters for a set of data points. A region of interest containing the data points and a center matrix for the region of interest are defined, where the center matrix includes an array of center points defining centers of overlapping circles. The data points are mapped to corresponding circles based on near center points. Pairs of overlapping circles are merged based on relative numbers of data points lying in overlap regions of the pairs of overlapping circles compared to total numbers of data points within the corresponding circles. Circles belonging to the one or more data clusters are identified based on merged pairs of overlapping circles, and data points belonging to the one or more data clusters are identified based on the corresponding circles. The method may be performed by a computer having a heterogeneous architecture with parallel processors.