W. Z. Liu, A. P. White, S. G. Thompson, and M. A. Bramer. Techniques for dealing with missing values in classification. Lecture Notes in Computer Science, 1280, 1997.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....if data mining is one of the possible uses for example. But, most of the data to be mined are results of by product of some other activity that has the knowledge discovery process as a mean to explain something but not as a goal in itself. In these cases, missing values are likely to be present (Liu et al. 1997) and most of the time they are not representative of any subgroup of instances. There has been substantial research done on handling missing values in machine learning (Grzymala Busse and Hu, 2001, Liu et al. 1997, Ortega and Numao, 1999, Quinlan, 1989, Zheng and Low, 1999) Several of them ....

....not as a goal in itself. In these cases, missing values are likely to be present (Liu et al. 1997) and most of the time they are not representative of any subgroup of instances. There has been substantial research done on handling missing values in machine learning (Grzymala Busse and Hu, 2001, Liu et al. 1997, Ortega and Numao, 1999, Quinlan, 1989, Zheng and Low, 1999) Several of them provide a comparison between different methods of dealing with missing or unknown values (e.g. Quinlan, 1989) but others like (Ortega and Numao, 1999) propose new or improved methods. One of the first approaches to ....

Liu, W. Z., White, A. P., White, S. G., Thompson, S. G., and Bramer, M. A. Techniques for dealing with missing values in classifications. In X. Liu, P. Cohen and M. Berthold, editors, Advances on Intelligent Data Analysis, Springer-Verlag, 1997.

....values. This approach is inspired by one of the simplest way to treat missing values in machine learning methods. It consists in evaluating a rule only with known values, i.e ignoring missing values. Even though this approach causes a huge waste of data for a lot of methods, e. g decision trees [9] [14] it is particularly well suited for association rules: a cancelled data for a rule, i.e data containing missing values for values tested by the rule, can be used by others rules. Then, even if the whole database is not used to evaluate a rule, the whole database is used to discover the ....

....are the intersection between the data matched by f1 2 3g and f1 2 4g. In the next section the problem posed by the missing values is studied. 3 Association Rules and Data with Missing Values 3. 1 Data and Missing Values The problem of the missing values has been widely studied in the literature [9] [12] 6] A missing value hides a value of an attribute. There are various way in which missing values might occur. For example: values recorded are missing because they were too small or too large to be measured. values recorded are missing because they have been forgotten or they have ....

[Article contains additional citation context not shown here]

W.Z Liu, A.P White, S.G Thompson and M.A Bramer. Techniques for Dealing with Missing Values in Classification. In Second International Symposium on Intelligent Data Analysis, Birkbeck College, University of London, 4th-5th August 1997.

....The waste of data may be con siderable, and incomplete datasets can lead to biased statistical analyses. So it is important that the issue of nonresponse be addressed in an appropriate manner and we have to design alternatives approaches. A current one is to try and determine these values [12]. These techniques must be efficient, otherwise the completion introduces noise. A current approach is to fill the missing values with the most common values in the datasets. Such a technique is standard and offered, for example, in the SOLAS software [21] SOLAS is a Statsol development ....

.... method to deal with missing values, and many programs have developed specific and internal treatments (this is among others the case for decision trees) Secondly, critics of some methods, like the one used by c4.5, are that the treatment is not easy to understand, and that completion may be wrong [12] since the value is chosen in datasets constructed for the analysis task, and not to decide the missing value: the sub datasets are constructed to be homogeneous for the class attribute and not for the attributes with missing values. Thirdly, the most promising way seems to look for some ....

W.Z Liu, A.P White, S.G Thompson and M.A Bramer. Techniques for Dealing with Missing Values in Classification. In proceedings of the second Int'l Symposium on Intelligent Data Analysis, London, 1997.

....in machine learning is the occurrence of unknown attribute values for some instances in the available data. Missing values phenomenon is likely to occur after generating by products on different data collections, which is an operation commonly carried out during the process of knowledge discovery [5]. When missing values occur in the data, the learning algorithm fails to find an accurate representation of the concept (e.g. decision trees or rules) Properly filling missing values in data can help in reducing the error rate of the learned concepts. Thus, the purpose of this paper is to ....

W.Z. Liu, A.P. White, S.G. Thompson, and M.A. Bramer. Techniques for dealing with missing values in classification. In Proc of Advances in Intelligent Data Analysis (IDA'97), volume 1280 of Lecture notes in computer science, pages 527--536. Springer, 1997.

No context found.

W. Z. Liu, A. P. White, S. G. Thompson, and M. A. Bramer. Techniques for dealing with missing values in classification. Lecture Notes in Computer Science, 1280, 1997.

No context found.

W. Z. Liu, A. P. White, S. G. Thompson, and M. A. Bramer. Techniques for Dealing with Missing Values in Classification. In X. Liu, P. Cohen, and M. R. Berthold, editors, Advances in Intelligent Data Analysis, Lecture Notes in Computer Science, LNCS1280, pages 527--536, Springer Verlag, 1997.

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