粗糙集合理論不依賴於所需處理的資料集合之外的任何先驗資訊,它對不精確、不確定、不完整的資訊和知識具有很強的分析處理能力。傳統的粗糙集理論在資料探勘中的應用,大多是透過結構化的方法來實現的,但是這種方法存在著資料模型結構性不強、軟體再利用率低、可擴充性不佳等主要問題。為瞭解決這些問題,本文將物件導向理論和粗糙集合理論相結合,在傳統粗糙集理論應用的基礎上引入物件導向資料庫,設計了一種用於屬性約簡的物件模型和約簡模型,並充分考慮到物件導向資料庫對複雜物件具有優越的儲存、檢索能力,從而提出了一個基於物件導向資料庫的粗糙集模型。研究工作首先利用資料庫技術處理大資料集問題的優越性,提出了一種基於預儲程式的屬性約簡演算法以解決處理大量資料時,基於主記憶體式(main memory)的粗糙集屬性約簡演算法效率低落問題,次而採用物件導向理論來分析Rough集的研究對象,設計了一種用於屬性約簡的物件模型,並使用物件導向資料庫DB4O (Database for objects)對此進行模型建立。再則在傳統的粗糙集理論的基礎上引入物件導向資料庫,提出了一種基於物件導向資料庫的粗糙集模型。最後探討實現屬性約簡演算法的關鍵技術,並實作了一個資料處理軟體系統「基於物件導向資料庫的粗糙集模型的屬性約簡系統」,透過將模型應用到具體實例,用於驗證上述研究成果。
Rough set theory is independent of any foregoing information which is excluded of processed data sets, and it is a new effective mathematic tool to deal with the uncertainty, imprecision and in completion. Although traditional Rough set theory applications in data mining are almost based on structured method, it can possibly involve issues such as poor structural integrity of data model, low software reuse and lack of extensibility. To solve this problem, this paper combines object-oriented theory with rough set attribute reduction methodology to design an object model and an attribute reduction model, which can be viewed as an object-oriented attribute reduction model based on rough set. The experimental results show that the model not only effectively reduces the attribute of rough set, but also has the advantages of simple structure and good extensibility. The reaserch works in this paper proposes an algorithm for attribution reduction based on stored procedure, using the superiority of the database technology to solve this problem which The efficiency of the algorithm for attribution reduction in Rough Set based on main memory will be significantly reduced when dealing with larger data sets. In the Secondary, the paper analyses the subjects of Rough Set using object-oriented theory and designs an Object Model for the attribute reduction, modeling it with object-oriented database DB4O.And then, this paper proposes a Rough Set Model based on the object-oriented database on the basis of the traditional Rough Set theory with the introduction of object-oriented databases. Finally, A thorough discussion is given to the key technologies to achieve the attribute reduction algorithm. A professional data-processing software system, which is an attribute reduction system of Rough Set Model based on object-oriented database, is developed to verify the research results mentioned above.