ÁP DỤNG THUẬT TOÁN PHÂN CỤM C-MEANS MỜ BÁN GIÁM SÁT DỰA TRÊN MÔ HÌNH PHÂN CỤM CỘNG TÁC ĐỂ PHÂN LOẠI LỚP PHỦ ĐẤT TỪ ẢNH LANDSAT-7=APPLYING SEMI-SUPERVISED FUZZY C-MEANS CLUSTERING ALGORITHM BASED ON COLLABORATIVE CLUSTERING MODEL FOR LAND COVER CLASSIFICATION FROM LANDSAT-7 IMAGERY

0 Người đánh giá. Xếp hạng trung bình 0

Tác giả: Chí Hiểu Lê, Đình Sinh Mai, Tuấn Kiệt Nguyễn, Lê Hùng Trịnh

Ngôn ngữ: vie

Ký hiệu phân loại:

Thông tin xuất bản: Journal of Science and Technique: Section on Special Construction Engineering, 2024

Mô tả vật lý: tr.171

Bộ sưu tập: Metadata

ID: 251755

Thêm vào giỏ

Sự phát triển nhanh chóng của các vệ tinh quan sát trái đất đã dẫn đến sự bùng nổ về các nguồn dữ liệu viễn thám. Việc lưu trữ tập trung các nguồn dữ liệu lớn ngày càng trở nên khó khăn, các giải pháp lưu trữ phi tập trung trên các hệ thống phân tán ngày càng được chú ý nhiều hơn. Các kỹ thuật khai phá dữ liệu truyền thống đã trở nên lỗi thời và không còn phù hợp để giải quyết các vấn đề dữ liệu lớn, đa chiều và phân tán. Các tập dữ liệu này vì một vài lý do như bảo mật, đường truyền dữ liệu, tính riêng tư... nên không thể chia sẻ trực tiếp giữa các máy tính mà chỉ có thể chia sẻ thông tin về cấu trúc cụm. Bài báo trình bày một thuật toán phân cụm c-means mờ bán giám sát dựa trên mô hình phân cụm cộng tác trên các hệ thống phân tán áp dụng cho bài toán phân loại lớp phủ đất từ dữ liệu ảnh viễn thám. Mô hình đề xuất nhằm giải quyết vấn đề phân loại lớp phủ đất mà dữ liệu ảnh viễn thám phi tập trung được lưu trữ trên một hệ thống phân tán các máy tính được kết nối qua mạng. Các thử nghiệm trên bốn tập dữ liệu ảnh vệ tinh quang học cho thấy phương pháp đề xuất mang lại kết quả tốt hơn đáng kể cả về chất lượng phân loại và thời gian phân loại so với việc phân cụm cục bộ trên các tập dữ liệu riêng lẻ. Kết quả này cho thấy việc phát triển các thuật toán phân tích dữ liệu dựa trên mô hình cộng tác có thể giúp giải quyết tốt vấn đề phân tích dữ liệu ảnh viễn thám từ xa hoặc phân tán.The rapid development of artificial satellites has led to an explosion of remote sensing data sources. Centralized storage of large data sources is becoming increasingly complex, and decentralized storage solutions on distributed systems are increasingly gaining attention. Traditional data mining techniques have become obsolete and are no longer suitable for solving large, multidimensional, distributed data problems. These datasets, for some reasons such as security, data transmission, privacy, etc., cannot be shared directly between computers but can only share information about cluster structure. This article presents a semi-supervised fuzzy c-means clustering algorithm based on the collaborative clustering model (CSFCM) on distributed systems applied to the problem of land cover classification from remote sensing data. The proposed model aims to solve the problem of land cover classification where remote sensing data is decentralized and stored on a distributed system of computers connected via the network. Experiments on four optical satellite image datasets show that the proposed method provides significantly better results in both classification quality and classification time compared to local clustering on individual datasets. This result suggests that developing collaborative model-based data analysis algorithms can help solve the problem of remote or distributed remote sensing image data analysis.

1. Đọc trực tuyến

1. Đọc trực tuyến

Tạo bộ sưu tập với mã QR