@ARTICLE{Cho_02,
    AUTHOR      = {Vincent Cho and Beat {W\"{u}thrich}},
    TITLE       = {{Distributed Mining of Classification Rules}},
    JOURNAL     = {{Knowledge and Information Systems}},
    YEAR        = {2002},
    VOLUME      = {4},
    NUMBER      = {1},
    PAGES       = {1-30},
    MONTH       = {January},
    NOTE        = {},
    KEYWORDS    = {},
    ISBN        = {},
    URL         = {http://portal.acm.org/citation.cfm?id=639626},
    ABSTRACT    = {Many successful data-mining techniques and systems have been developed. These
                   techniques usually apply to centralized databases with less restricted requirements
                   on learning and response time. Not so much effort has yet been put into mining
                   distributed databases and real-time issues. In this paper, we investigate issues of
                   fast-distributed data mining. We assume that merging the distributed databases into
                   a single one would either be too costly (distributed case) or the individual
                   fragments would be non-uniform so that mining only one fragment would bias the
                   result (fragmented case). The goal is to classify the objects O of the database
                   into one of several mutually exclusive classes Ci. Our approach to make mining fast
                   and feasible is as follows. From each data site or fragment dbk, only a single rule
                   rik is generated for each class Ci. A small subset {ri1,..., rih} of these individual
                   rules is selected to form a rule set Ri for each class Ci . These rule subsets
                   represent adequately the hidden knowledge of the entire database. Various selection
                   criteria to form Ri are discussed, both theoretically and experimentally.},
}