An empirical study of domain knowledge and its benefits to substructure discovery

• Published in: IEEE transactions on knowledge and data engineering Vol. 9; no. 4; pp. 575 - 586
• Main Authors: Djoko, S., Cook, D.J., Holder, L.B.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.07.1997; IEEE Computer Society
• Subjects: Acceleration; Applied sciences; Artificial intelligence; Circuits; Computer science; control theory; systems; Data analysis; Data compression; Design automation; Design methodology; Exact sciences and technology; Information retrieval. Graph; Information systems. Data bases; Learning and adaptive systems; Memory organisation. Data processing; Process design; Programming; Software; Theoretical computing; Transaction databases; System architecture; Circuit design; Domain knowledge; Data compression; Expert system; Knowledge representation; Knowledge base; Data mining; Algorithm; Computational complexity; Graph; System performance; Coding; Database; Minimum description lenght principle; Inference rule; Computer aided design; Software engineering
• ISSN: 1041-4347
• DOI: 10.1109/69.617051

Discovering repetitive, interesting, and functional substructures in a structural database improves the ability to interpret and compress the data. However, scientists working with a database in their area of expertise often search for predetermined types of structures or for structures exhibiting characteristics specific to the domain. The paper presents a method for guiding the discovery process with domain specific knowledge. The SUBDUE discovery system is used to evaluate the benefits of using domain knowledge to guide the discovery process. Domain knowledge is incorporated into SUBDUE following a single general methodology to guide the discovery process. Results show that domain specific knowledge improves the search for substructures that are useful to the domain and leads to greater compression of the data. To illustrate these benefits, examples and experiments from the computer programming, computer aided design circuit, and artificially generated domains are presented.