Slowinski, R., (1992), "Intelligent Decision Support - Handbook of Applications and Advances of the Rough Sets Theory", (Eds.) R. Slowinski, Kluwer Academic Publishers.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....dealt with conversions that are information preserving, i.e. all entries in the table are correctly classified and the structures are not used for making predictions. The rough sets community has been using the hypothesis space of decision tables for a few years (Pawlak 1987, Pawlak 1991, Slowinski 1992). Researchers in the field of rough sets suggest using the degrees of dependency of a feature on the label (called fl) to determine which features should be included in a decision table (Ziarko 1991, Modrzejewski 1993) Another suggestion was to use normalized entropy (Pawlak, Wong Ziarko 1988) ....

Slowinski, R. (1992), Intelligent decision support : handbook of applications and advances of the rough sets theory, Kluwer Academic Publishers.

....Table 3. 17: A set of meaningful rules after substitution Chapter 4 Rough Sets and A Generalized Rough Set Model Much attention has been paid recently by the expert systems research and machine learning community to the acquisition of knowledge and reasoning under vagueness and incompleteness [Paw91, Slo92, HCH93b]. Vagueness may be caused by the ambiguity of exact meaning of the terms used in the knowledge domain, uncertainty in data (e.g. due to noise) and uncertainty in knowledge itself (e.g. due to doubtful connection between the antecedent and the consequent in an inferred rule) Zia91] ....

.... rough set theory is that it does not need any preliminary or additional information about data (like probability in statistics, grade of membership, or the value of possibility in fuzzy set theory) Other advantages of the rough set approach include its ease of handling and its simple algorithms [Slo92]. Rough set theory has been successfully implemented in knowledge based systems in medicine and industry [Grz88] The rough set philosophy is based on the idea of classification. The most important issue addressed in the rough set theory is the idea of imprecise knowledge. In this approach, ....

[Article contains additional citation context not shown here]

Slowinski, R (ed.) (1992). Intelligent Decision Support: Handbook of Applications and Advances of Rough Sets Theory.

.... lack precise definition and whose meaning is context dependent; some ideas concerned with this topic include fuzzy sets (e.g. Zadeh, 1965; Dubois, Prade and Yager, 1993) two tiered concept representations (e.g. Michalski, 1990; Bergadano et al., 1992) and rough sets (e.g. Pawlak, 1991; Slowinski, 1992; Ziarko, 1994) Learning concepts at different levels of generality, i.e. learning descriptions that involve concepts from different levels of generalization hierarchies representing background knowledge (e.g. Kaufman and Michalski, 1996) Integrating qualitative and quantitative discovery, ....

Slowinski, R. (ed.), Intelligent Decision Support: Handbook of Applications and Advances of the Rough Sets Theory, Dordrecht/Boston/London, Kluwer Academic Publishers, 1992.

....0 i with p(X i = x i ; S 0 i = s 0 i ) 0 such that p(Y = y j X i = x i ; S 0 i = s 0 i ) 6= p(Y = y j S 0 i = s 0 i ) A feature is relevant if it is either weakly relevant or strongly relevant; otherwise, it is irrelevant. Borrowing some terminology from rough sets (Pawlak 1991, Slowinski 1992), the set of strongly relevant features form the core and any set of features that allow a Bayes classifier to achieve the highest possible accuracy forms a reduct. A reduct can only contain strongly relevant and weakly relevant features. Pawlak (1991) shows that the core is the intersection of ....

....dealt with conversions that are information preserving, i.e. all entries in the table are correctly classified and the structures are not used for making predictions. The rough sets community has been using the hypothesis space of decision tables for a few years (Pawlak 1987, Pawlak 1991, Slowinski 1992). Researchers in the field of rough sets suggested using the degrees of dependency of a feature on the label (called fl) to determine which features should be included in a decision table (Ziarko 1991, Modrzejewski 1993) Another suggestion was to use normalized entropy (Pawlak, Wong Ziarko ....

Slowinski, R. (1992), Intelligent decision support : handbook of applications and advances of the rough sets theory, Kluwer Academic Publishers.

.... Learning flexible concepts, i.e. concepts that inherently lack precise definition and whose meaning is context dependent; some ideas concerned with this topic include fuzzy sets (e.g. Zad65] DPY93] two tiered concept representations (e.g. Mic90] BMMZ92] and rough sets (e.g. Paw91] [Slo92], Zia94] Learning concepts at different levels of generality, i.e. learning descriptions that involve concepts from different levels of generalization hierarchies representing background knowledge (e.g. KM96] Integrating qualitative and quantitative discovery, i.e. determining sets of ....

Slowinski, R. (ed.) Intelligent Decision Support: Handbook of Applications and Advances of the Rough Sets Theory. Dordrecht/Boston/London, Kluwer Academic Publishers, 1992.

....decisions on statistical measures of the information entropy whereas the rough set al..gorithm is based on the theory of sets and topology. Rough set theory was introduced by Pawlak [2] and since then a number of applications have been reported in diverse fields such as medicine and process control [3]. Rough sets can either be used for the purpose of generating if. then rules (machine learning) or as a technique for eliminating redundant information (data analysis) prior to the use of, say, artificial neural networks. The next sections of the paper present a simple tutorial to introduce ....

Slowinski R (ed.) (1992) Intelligent decision support: Handbook of applications and advances of the rough sets theory, , Kluwer Academic publishers, Dordrecht.

....from, and complementary to, other generalizations, such as fuzzy sets and multisets [10,19,44,61] There has been a fast growing interest in this new emerging theory. The successful applications of rough set models in a variety of problems have amply demonstrated their usefulness and versatility [21,25,42,53,70]. In a rough set model, elements of the universe are described in the context of available information (knowledge) about them. For example, in a medical expert system patients are normally described by their symptoms. In a pattern recognition system, objects may be described by their features. ....

Slowinski, R. (Ed.), Intelligent Decision Support: Handbook of Applications and Advances of the Rough Sets Theory, Kluwer Academic Publishers, Boston, 1992.

....in the number of labels. The structures formed are isomorphic to oblivious read once decision graphs (OODGs) and to ordered binary decision diagrams (OBDDs) thus providing an alternative view of how algorithms that construct such graphs operate. 1 Introduction Rough sets theory [ Pawlak, 1991, Slowinski, 1992 ] defines a relative reduct as a subset of attributes such that the indiscernibility relation formed using this subset has the same positive region as the original set of attributes with respect to the label, or decision attribute. In many problems, the subset is prohibitively large, and ....

Roman Slowinski. Intelligent decision support : handbook of applications and advances of the rough sets theory. Kluwer Academic Publishers, 1992.

....imprecise if it contains any imprecise concept. A concept is precise if it can be expressed (defined) in terms of the assumed classification patterns; otherwise the concept is imprecise (Pawlak 1991) Applications of rough sets to machine learning area are given in (Chan 1991; Gezymala Busse 1988; Slowinski 1992; Pawlak 1991) Learnability of concepts is another important issue in inductive learning. If the learning task is to generate a description of a target concept based on a set of condition attributes, the whether or not it can be done depends on the granularity of the information represented by ....

....anomalies become harder to weed out, and noise sensitivity increase. As the result, the overfiting and incorrect rules may be generated and decrease prediction accuracy (Domingos 1995; Holte et al. 1989) To alleviate the splintering problem, other systems (Domingos 1995; Shan et al. 1995; Slowinski 1992) using the strategy of conquer without separating to induce rules from the data set. It can make effective use of statistic measures to combat noise, because each rule is generated taking into consideration the entire data set in a specific to general fashion. This method handles missing ....

Slowinski, R. 1992. Intelligent Decision Support: Handbook of Applications and Advances of Rough Sets Theory, Kluwer.

....of the important attributes and the patients classification. One of the possible data analysis methods which are used to solve the above tasks is the rough set theory introduced by Z.Pawlak (Pawlak 1991) In last years, the authors successfully applied it to several medical problems (see e.g. K. Slowinski 1992), K. Slowinski et al. 1989) K. Slowinski and Shariff 1994) Other medical applications described in (R.Slowinski 1992) or (Ziarko 1994) also confirm its usefulness. Such elements of the rough set theory as the approximations of objects classification, the quality of these approximations and ....

....solve the above tasks is the rough set theory introduced by Z.Pawlak (Pawlak 1991) In last years, the authors successfully applied it to several medical problems (see e.g. K.Slowinski 1992) K. Slowinski et al. 1989) K. Slowinski and Shariff 1994) Other medical applications described in (R. Slowinski 1992) or (Ziarko 1994) also confirm its usefulness. Such elements of the rough set theory as the approximations of objects classification, the quality of these approximations and notions of reducts could help in evaluating the attributes. Moreover, combination of the rough set theory with rule ....

[Article contains additional citation context not shown here]

Slowinski R. (ed.) 1992: Intelligent Decision Support - Handbook of Applications and Advances of the Rough Sets Theory, Kluwer Academic Publishers, Dordrecht.

....developed for over 25 years. In the ML community, we have seen papers on Presented at the November 1995 IEEE International Conference for Tools with Artificial Intelligence y Email: maxtell.dytn veda.com z Email: jgoldman mbvlab.wpafb.af. mil how Rough Set Theory is used for ML problems in [20] and we have seen how Rough Set Theory can be used for logic synthesis problems in [13] Moreover, we are beginning to see rule generation systems based heavily on circuit design techniques [8, 1] However, we have yet to see current state of the art logic synthesis tools applied directly to ML ....

Roman Slowinski. Intelligent Decision Support: Handbook of Applications and Advances of the Rough Sets Theory. Kluwer Academic Publishers, Boston, 1992.

....and in sections 3 and 4 we present our method in detail and illustrate the proposed method. Finally section 5 provides some conclusions. 2 Related Works Many classification systems have been implemented including decision tree systems [9, 1] neural networks [6] rough set based systems [11], etc. The basic assumption in all of these approaches is that we know the class of each example beforehand. But this assumption can be a limitation for the applicability of these systems since it is not always clear that we know exactly which attribute in a database table is the decision ....

....rules. Step 6: Find rules for the table. By going through the above steps, we now have a complete table and a decision attribute for rule generation. Rules can be generated using a conventional classification system like the decision tree based system, C4.5 [9] or a rough setbased system [11]. Step 7: Compute the confidence of each rules found. l 1 H with confidence of 100 l 2 M with confidence of 100 Note that the confidence does not count the rare case. 5 Conclusions Although it is difficult to say that there are only two situations that we surely know (classification) or ....

R. Slowinski, editor. Intelligent Decision Support: Handbook of Applications and Advances of the Rough Set Theory. Kluwer Academic Publishers, 1992.

....the universe are exactly the same, then one can say that the mentioned above subset is definable with respect to available information. Otherwise one can consider it as roughly definable. Some approaches to analysis of medical data sets based on the rough set theory are presented for example in [9, 15, 19, 7, 16, 18, 2, 20]. In this paper we discuss mining data in diabetes mellitus data table. We consider two sub tasks: ffl identification of the most important condition attributes, 1 ffl discovery of decision rules characterizing the dependency between values of condition attributes and decision attribute. The ....

Slowinski K.: Rough Classification of HSV Patients, (ed.) Slowinski R., Intelligent Decision Support - Handbook of Applications and Advances of the Rough Sets Theory. Kluwer Academic Publishers, Dordrecht, 1992, pp. 77-93.

No context found.

Slowinski, R., (1992), "Intelligent Decision Support - Handbook of Applications and Advances of the Rough Sets Theory", (Eds.) R. Slowinski, Kluwer Academic Publishers.

No context found.

R. Slowinski (Ed.), Intelligent Decision Support---Handbook of Applications and Advances of the Rough Sets Theory, Kluwer Academic Publishing, Boston, 1992.

No context found.

Slowinski, R. (ed.) (1992). Intelligent Decision Support: Handbook of Applications and Advances of the Rough Sets Theory, Kluwer Academic Publishers, Dordrecht.

No context found.

Slowinski, R. (ed.) (1992). Intelligent Decision Support: Handbook of Applications and Advances of the Rough Sets Theory . Dordrecht: Kluwer Academic Publishers.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC