Pattern recognition in data is a well known classical problem that falls
under the ambit of data analysis. As we need to handle different data,
the nature of patterns, their recognition and the types of data analyses
are bound to change. Since the number of data collection channels
increases in the recent time and becomes more diversified, many
real-world data mining tasks can easily acquire multiple databases from
various sources. In these cases, data mining becomes more challenging
for several essential reasons. We may encounter sensitive data
originating from different sources - those cannot be amalgamated. Even
if we are allowed to place different data together, we are certainly not
able to analyze them when local identities of patterns are required to
be retained. Thus, pattern recognition in multiple databases gives rise
to a suite of new, challenging problems different from those encountered
before. Association rule mining, global pattern discovery and mining
patterns of select items provide different patterns discovery techniques
in multiple data sources. Some interesting item-based data analyses are
also covered in this book. Interesting patterns, such as exceptional
patterns, icebergs and periodic patterns have been recently reported.
The book presents a thorough influence analysis between items in
time-stamped databases. The recent research on mining multiple related
databases is covered while some previous contributions to the area are
highlighted and contrasted with the most recent developments.
