G. Das, H. Mannila. Context-Based Similarity Measures for Categorical Databases. PDKK Conference, 2000. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Feature Selection For Effective Calculation - Of Similarity Measure (2002) (Correct)
....for useful information from databases, an increasing number of features (attributes) makes worse results and loses much time. We propose a feature selection technique which saves computation time and does not spoil effect of mining. We take an algorithm called Iterated Contextual Distances (ICD) [1], show its problems for practical applications, and propose a feature selection method, which mitigates these problems. Then we show effects of the feature selection by experiments performed on a real dataset. KEY WORDS feature selection, attribute selection, similarity measure, distance 1. ....
....Contextual Distances In this section, we explain an algorithm to induce distances, called the Iterated Contextual Distances (ICD) algorithm, which is a techniques of evaluating and searching for the similarities between instances automatically. This algorithm was proposed by G. Das and H. Mannila [1]. This algorithm uses three different similarity notions, that is, similarities between instances, between attributes, and between subrelations or sets of instances. In this paper, we pay attention for subrelations whose instances commonly have a certain attribute. We call a set of instances which ....
[Article contains additional citation context not shown here]
G. Das and H. Mannila. Context-Based Similarity Measures for Categorical Database. In Proc. of PKDD2000.
Map Classification With A Similarity Measure - Yamada, Inuzuka (2002) (Correct)
....in a class will be relatively large and examples in different classes will take small similarity. However the meaning of the absolute magnitude of the similarities is not clear. Another similarity measure is proposed. It is the way based on the context in which the features of instance appear [3]. This approach calculates similarity based on mutual relations of a feature of example, an example and a set of examples which explain the feature, and the relations are formulated as a system of nonlinear equations of distances between the features, examples and sets of examples. Similarities ....
Gautan Das and Heikki Mannila, Context-Based Similarity Measures for Categorical Databases, in Proceedings of Principles of Data Mining and Knowledge Discovery, 4th European Conference, PKDD, pp.201-210, 2000.
Discovering Associations in Clinical Data.. - Durand.. (2001) (Correct)
....medicine, a cluster can group patients 2 N. Durand et al. having similar and or related features. The production of meaningful clusters in data mining is a hot topic. Similarity measures are often used. When data are complex and include categorical attributes, these measures are not easy to de ne [1]. Such situations are very usual in medical area. However, association rules method o ers a background to produce clusters without requiring a similarity measure. An association rule [2] is a statement of the form 95 of patients that have gender = male and mediastinum = enlarged also get ....
G. Das and H. Mannila. Context-based similarity measures for categorical databases. In proceedings of the Fourth European Conference on Principles and Practice of Knowledge Discovery in Databases, PKDD 00, number
Local and Global Methods in Data Mining: Basic Techniques and.. - Mannila (2002) (17 citations) Self-citation (Mannila) (Correct)
....using the answers of i on d. Similarity of attributes in discrete data sets Problem 17 Given a set of attributes S = fB 1 ; B p g, where each B i can obtain values from a nite domain D i , nd a good way of de ning the similarity of values in each D i . Some attempts have been made [25, 16, 15]. Especially the algorithm in [25] is intriguing: why does it work What does it do Framework for data mining Problem 18 What is a good theoretical framework for data mining See [30] for a relatively recent discussion on the alternatives. The approach in the paper [28] deserves very careful ....
G. Das and H. Mannila. Context-based similarity measures for categorical databases. In PKDD 2000, 2000.
Towards Systematic Design of Distance Functions for Data.. - Charu Aggarwal Ibm (2003) (4 citations) (Correct)
No context found.
G. Das, H. Mannila. Context-Based Similarity Measures for Categorical Databases. PDKK Conference, 2000.
ECCLAT: a New Approach of Clusters Discovery in Categorical.. - Durand, Cremilleux (2002) (Correct)
No context found.
Das, G. & Mannila, H. Context-based Similarity Measures for Categorical Databases. In Proceedings of the Fourth European Conference on Principles and Practice of Knowledge Discovery in Databases, PKDD 00, volume 1910 of LNAI, pages 201-210, Lyon, France, 2000. Springer-Verlag
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