Rough Sets, Fuzzy Sets, Data Mining, and Granular Computing: by Yiyu Yao, Qinghua Hu, Hong Yu, Jerzy W. Grzymala-Busse PDF

Read or Download Rough Sets, Fuzzy Sets, Data Mining, and Granular Computing: 15th International Conference, RSFDGrC 2015, Tianjin, China, November 20-23, 2015, Proceedings PDF

Similar international_1 books

• Modeling Decisions for Artificial Intelligence: 10th International Conference, MDAI 2013, Barcelona, Spain, November 20-22, 2013. Proceedings
• Fundamentals of Computation Theory: 15th International Symposium, FCT 2005, Lübeck, Germany, August 17-20, 2005. Proceedings
• Parallel Computation: 4th International ACPC Conference Including Special Tracks on Parallel Numerics (ParNum’99) and Parallel Computing in Image Processing, Video Processing, and Multimedia Salzburg, Austria, February 16–18, 1999 Proceedings
• A Simulation of the Fluctuations of International Atomic Time
• Typed Lambda Calculi and Applications: 9th International Conference, TLCA 2009, Brasilia, Brazil, July 1-3, 2009. Proceedings
• Proceedings of 20th International Conference on Industrial Engineering and Engineering Management: Theory and Apply of Industrial Engineering

Additional info for Rough Sets, Fuzzy Sets, Data Mining, and Granular Computing: 15th International Conference, RSFDGrC 2015, Tianjin, China, November 20-23, 2015, Proceedings

Sample text

The probability that a patient has the disease with this set of manifestations:SI(Satisfactory Index) 3. the ratio of the patients who satisfy the set to all the patients of this disease:CI(Covering Index) 4. 0 then end. Otherwise, goto 5. 5. For the patients with this disease who do not satisfy all the collected set of manifestations, goto 1. Therefore a positive rule is described by a set of manifestations, its satisfactory index (SI), which corresponds to accuracy measure, and its covering index (CI), which corresponds to total positive rate.

E) Diagnostic criteria gives temporal information about episodes of headache. In the previous studies, automated extraction of knowledge with respect to (a), (b), (c) has been solved. However, (d) and (e) still remains. Dealing with exceptions is related with complications detection, so partially (d) is solved. However, in some cases, exceptions are used for case-based reasoning by medical experts. Thus, combination of rule-based and case-based reasoning should be introduced. Acquisition of temporal knowledge is important because medical experts use temporal reasoning in a flexible way.

Sl Generalized Decision Measures From now on, we will assume a fixed set of decisions. We go back to notation A = (U, A ∪ D). Moreover, for simplicity, we will write ∂B instead of ∂D/B . The following measures can be used to evaluate subsets of attributes. Definition 6. Let A = (U, A ∪ D) be given. Functions g∂ , e∂ : 2A → (0, 1] and h∂ : 2A → [0, +∞) are defined as follows, for each B ⊆ A: g∂ (B) = 1 |U | u∈U 1 |∂B (u)| e∂ (B) = 1 |U | u∈U 1 2|∂B (u)|−1 h∂ (B) = u∈U log |∂B (u)| |U | For subsets C ⊆ B ⊆ A, there are always inequalities g∂ (C) ≤ g∂ (B), e∂ (C) ≤ e∂ (B) and h∂ (C) ≥ h∂ (B).

Download PDF sample