English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In recent years, KDD (Knowledge Discovery in Databases) (Fayyad et al., 1996) has been widely known as a process to extract useful knowledge from databases. In the research field of KDD, ‘Temporal (Time-Series) Data Mining’ is one of important issues to mine useful knowledge such as patterns, rules, and structured descriptions for a domain expert. However, huge numerical temporal data such as stock market data, medical test data, and sensor data have been only stored to databases. Besides, many temporalmining schemes such as temporal pattern extraction methods and frequent itemset mining methods have been proposed to find out useful knowledge from numerical temporal databases. Although each method can find out partly knowledge of each suggested domains, there is no systematic framework to utilize each given numerical temporal data through whole of the KDD process. To above problems, we have developed an integrated temporal data mining environment, which can apply numerical temporal data to find out valuable knowledge systematically. The environment consists of temporal pattern extraction, mining, mining result evaluation support system to attempt numerical temporal data from various domains. In this chapter, we describe a classification rule mining framework by combining temporal pattern extraction and rule mining. This framework has been developed for mining if-then rules consisting of temporal patterns in left hand side of the rules. The right hand side of the rules is indicated to predict both of important events and temporal patterns of important index. In order to show the effectiveness of the framework, we implemented this framework for a medical sequential data of laboratory test results for chronic hepatitis patients and a sequential data consisting of technical indexes for Japanese stocks. By using the implementations and experimental results, we present the following merits achieved by the classification rules with considering temporal patterns of the target attributes:

Development of a Classification Rule Mining Framework by Using Temporal Pattern Extraction