Data mining for association rules and sequential patterns : Sequential and parallel algorithms

Recent advances in the data collection and storage technologies have made it possible for companies (e.g. bar-code technology), administrative agencies (e.g. census data) and scientific laboratories (e.g. molecule databases in chemistry or biology) to keep vast amounts of data relating to their acti...

Mô tả đầy đủ

Đã lưu trong:
Chi tiết về thư mục
Tác giả chính: Adamo, Jean-Marc
Định dạng: Sách
Ngôn ngữ:Undetermined
Được phát hành: New York Springer c2001
Những chủ đề:
Các nhãn: Thêm thẻ
Không có thẻ, Là người đầu tiên thẻ bản ghi này!
Thư viện lưu trữ: Trung tâm Học liệu Trường Đại học Cần Thơ
Miêu tả
Tóm tắt:Recent advances in the data collection and storage technologies have made it possible for companies (e.g. bar-code technology), administrative agencies (e.g. census data) and scientific laboratories (e.g. molecule databases in chemistry or biology) to keep vast amounts of data relating to their activities. At the same time, the availability of cheap computing power has made automatic extraction of structured knowledge from these data feasible. Such an activity is referred to as data mining. More recently, the advent on the marketplace of cheap high performance (gigabit level) communication switches is even placing cheap parallel data mining within the reach of the majority. Data mining includes such activities as classification, clustering, similarity analysis, summarization, association rule and sequential pattern discovery, and so forth. This state-of-the-art monograph focuses on two key topics: association rules and sequential pattern discovery.