|
| Abstract: |
| Serial remote sensing images offer a valuable means of tracking the evolutionary changes and growth of a specific geographical area over time. Although the original images may provide limited insights, they harbor considerable potential for identifying clusters and patterns. The aggregation of these serial remote sensing images (SRSI) becomes increasingly viable as distinct patterns emerge in diverse scenarios, such as suburbanization, the expansion of native flora, and agricultural activities. In a novel approach, we propose an innovative method for extracting sequential patterns by combining Ant Colony Optimization and Empirical Mode Decomposition. This integration of the newly developed Empirical Mode Decomposition (EMD) and Ant Colony Optimization (ACO) techniques proves remarkably effective in identifying the most significant characteristic features within serial remote sensing images, guided by specific criteria. Our findings highlight a substantial improvement in the efficiency of sequential pattern mining through the application of this unique hybrid method, seamlessly integrating EMD and ACO for feature selection. This study exposes the potential of our innovative methodology, particularly in the realms of urbanization, native vegetation expansion, and agricultural activities. |
| Key words: Spatial pattern analysis, Empirical Mode Decomposition, Ant Colony Optimization |
| DOI：10.11916/j.issn1005-9113.2023072 |
| Clc Number:TP751 |
| Fund: |
