M. Taylor, K. Stoffel, , and J. Hendler. Ontology based induction of high level classification rules. In SIGMOD Workshop on Research Issues on Data Mining and Knowledge Discovery, 1997.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....[1] proposed handling tree structured attributes directly by routing examples in hierarchies, which count the class frequency of every concept node, then apply decision tree learning algorithm to score and find the best concept node in the hierarchy to build the decision tree. Taylor et al. [12] proposed an algorithm for rule learning using taxonomies and data. Against this background, it is of interest to formalize the problem of learning from ontologies and data and to explore the design space of algorithms for data driven knowledge acquisition using explicitly specified ontologies. ....

....search through the hypothesis space of decision trees defined with respect to a set of attribute taxonomies. 6 Jun Zhang et al. 3. 1 Illustration of the Working of the ODT Algorithm The preliminary test of our algorithm is based on a simple customer purchase database that used in Taylor s paper [12]. Each of the attributes used to describe instances in this data set has a taxonomy associated with it. The two taxonomies are ISA hierarchies for Beverage and Snack. For concepts in the Beverage taxonomy, there are three different levels of abstraction, and in the Snack taxonomy, we have two ....

Taylor, M., Stoffel, K., Hendler, J.: Ontology-based Induction of High Level Classification Rules. SIGMOD Data Mining and Knowledge Discovery workshop proceedings. Tuscon, Arizona (1997)

....inference operators so that they can work efficiently with very large databases. Since there are many operators involved, such a research project will require a significant effort. An interesting topic is to integrate one of the existing knowledge base systems, for example, PARKA (Taylor, Stoffel, and Hendler, 1997; Stoffel,Taylor, and Hendler, 1997) with INLEN 3. Other topics for future research include the development of operators for temporal trend prediction and for scaling up the conceptual clustering operator. 1 5 Acknowledgments The authors thank Jim Logan for providing the American Cancer ....

....so that they can work efficiently with very large databases. Since there are many operators involved, such a research project will require a significant effort. An interesting topic is to integrate one of the existing knowledge base systems, for example, PARKA (Taylor, Stoffel, and Hendler, 1997; Stoffel,Taylor, and Hendler, 1997) with INLEN 3. Other topics for future research include the development of operators for temporal trend prediction and for scaling up the conceptual clustering operator. 1 5 Acknowledgments The authors thank Jim Logan for providing the American Cancer Society database and discussing ....

Stoffel K., Taylor M., and Hendler, J., "Ontology-based Induction of High Level Classification Rules," Proceedings of the SIGMOD Datamining and Knowledge Discovery Workshop, May 1997.

....ONTOLOGY A ONTOLOGY B Figure 2: Two ontologies: A and B. A; B;C;F; G; and H are objects from ontology A, and D and E are objects from ontology B. The arcs show intra and inter ontology relationships among objects. generate something semantically more complex like Soda SaltySnacks. Taylor [12] describes the implementation of such ideas in the context of ParkaDB which is a knowledge representation system developed by the PLUS group at the University of Maryland. Their authors claim that this approach led to the generation of rules that provide a clearer synopsis of the database. This ....

....Doe LCI John Doe AT T Nevertheless, even more interesting utilization can be implemented using the libpq interface 4 . The implementation of complex data mining or hypothesis testing queries can be easily achieved and so we can, for example, implement the algorithms like the ones described in [12] or [9] Another intriguing possibility is the extension of the work of Meo et al..li [7] and implementing the MINE RULE operator in an ontology aware fashion such as the example bellow suggests: MINE RULE SimpleAssociations AS SELECT DISTINCT 1. n item AS BODY, 1. 1 item AS HEAD, SUPPORT, ....

[Article contains additional citation context not shown here]

M. G. Taylor, K. Stoffel, and J. A. Hendler. Ontology-based induction of high level classification rules. SIGMOD Data Mining and Knowledge Discovery workshop Proceedings, 1997.

....To evaluate these queries, ParkaDB merges concept taxonomies with databases evaluate queries and evaluating queries with out caches. The Mushroom database contains 8416 tuples and 23 attributes. We used 7 attributes which were selected based on their computed discriminating measure defined in [7]. The Mushroom database was merged with concept taxonomies defined on all of the attributes. The taxonomies were needed to induce high level discriminant rules. ParDRI was configured to find discriminant rules that were supported by 10 of the database and have a confidence of 90 . Table 1 ....

Merwyn Taylor, Kilian Stoffel, and James A. Hendler. Ontology-based induction of high level classification rules. In Proceddings of the SIGMOD Dataming and Knowledge Discovery Workshop, May 1997.

....discriminating measure defined in 4 This expression does not reflect the complexity of evaluating all queries in ParkaDB. Constraints in ParDRI may contain high level values which are ancestors of values in a database. To evaluate these queries, ParkaDB merges concept taxonomies with databases [6]. The Mushroom database was merged with concept taxonomies defined on all of the attributes. The taxonomies were needed to induce high level discriminant rules. ParDRI was configured to find discriminant rules that were supported by 10 of the database and have a confidence of 90 . Table 1 ....

Merwyn Taylor, Kilian Stoffel, and James A. Hendler. Ontology-based induction of high level classification rules. In Proceddings of the SIGMOD Dataming and Knowledge Discovery Workshop, May 1997.

No context found.

M. Taylor, K. Stoffel, , and J. Hendler. Ontology based induction of high level classification rules. In SIGMOD Workshop on Research Issues on Data Mining and Knowledge Discovery, 1997.

No context found.

Taylor, M., Sto#el, K., Hendler, J.: Ontology-based Induction of High Level Classification Rules. SIGMOD Data Mining and Knowledge Discovery workshop proceedings. Tuscon, Arizona (1997)

No context found.

Taylor, M., Sto#el, K., Hendler, J.: Ontology-based induction of high level classification rules. In: SIGMOD Data Mining and Knowledge Discovery workshop proceedings, Tuscon, Arizona (1997)

No context found.

M. Taylor, K. Stoffel, , and J. Hendler. Ontology based induction of high level classification rules. In SIGMOD Workshop on Research Issues on Data Mining and Knowledge Discovery, 1997.

No context found.

Taylor, M., Stoffel, K., , Hendler, J.: Ontology based induction of high level classification rules. In: SIGMOD Workshop on Research Issues on Data Mining and Knowledge Discovery. (1997)

No context found.

M. Taylor, K. Stoffel, , and J. Hendler. Ontology based induction of high level classification rules. In SIGMOD Workshop on Research Issues on Data Mining and Knowledge Discovery, 1997.

No context found.

M. G. Taylor and K. Stoffel and J. A. Hendler, Ontology-based Induction of High Level Classification Rules, SIGMOD Data Mining and Knowledge Discovery workshop proceedings, Tuscon, Arizona, 1997.

No context found.

M. G. Taylor, K. Stoffel, and J. A. Hendler. Ontology-based induction of high level classification rules. SIGMOD Data Mining and Knowledge Discovery workshop Proceedings, 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