Abstract

Spatial associative classification takes advantage of employing association rules for spatial classification purposes. In this work, we investigate spatial associative classification in multi-relational data mining setting to deal with spatial objects having different properties, which are modeled by as many data tables (relations) as the number of spatial object types (layers). Spatial classification is based on two alternative approaches: a propositional approach and a structural approach. The propositional approach uses spatial association rules to construct an attribute-value representation (propositionalisation) of spatial data and performs spatial classification according to well-known propositional classification methods. Since the attribute-value representation should capture relational properties of spatial data, multi-relational association rules are used in propositionalisation step. The structural approach resorts to an extension of naïve Bayes classifiers to multi-relational data where the classification is driven by multi-relational association rules modelling regularities in spatial data. In both cases the spatial associative classification is performed at different levels of granularity and takes advantage from domain knowledge expressed in form of hierarchies and rules. Experiments on realworld geo-referenced census data analysis show the advantage of the structural approach over the propositional one.

Citations

4072	JR: C4.5: Programs for Machine Learning - Quinlan
800	Fast effective rule induction - Cohen - 1995
560	Inverse Entailment and Progol - Muggleton - 1995
486	Pazzani M: On the optimality of the simple Bayesian classifier under zero-one loss - Domingos - 1997
358	Machine learning - Mitchell - 1997
341	Integrating Classification and Association Rule Mining - Liu
337	Y.: Discovery of multiple-level association rules from large databases - Han, Fu - 1995
194	Reasoning about Binary Topological Relations - Egenhofer - 1991
192	Efficient mining of emerging patterns: discovering trends and differences - Dong, Li - 1999
191	Adaptive Control Processes - Bellman - 1961
177	Levelwise search and borders of theories in knowledge discovery - Mannila, Toivonen - 1997
157	A Machine Oriented Logic Based on the Resolution Principle - Robinson - 1965
154	Discovery of spatial association rules in geographic information databases - Koperski, Han - 1995
154	CMAR: Accurate and efficient classification based on multiple class-association rules - Li, Han, et al. - 2001
115	Discovery of frequent datalog patterns - Dehaspe, Toivonen - 1999
110	Raedt. Top-down induction of first order logical decision trees - Blockeel, De - 1998
104	J.: CPAR: Classification Based on Predictive Association Rules - Yin, Han
104	Inductive logic programming: Techniques and applications - Lavrac, Dzeroski - 1994
93	Relational Data Mining - Dzeroski, Lavrac - 2001
81	Spatial data mining: a database approach - Ester, Kriegel, et al. - 1997
62	CAEP: Classification by aggregating emerging patterns - Dong, Zhang, et al. - 1999
62	Feature construction with inductive logic programming: A study of quantitative predictions of biological activity aided by structural attributes - Srinivasan, King - 1996
46	Using qualitative models to guide induction learning - Clark, Matwin - 1993
39	Feature selection using roughsets theory - Modrzejewski - 1993
36	Inductive logic programming for knowledge discovery in databases - Wrobel - 2001
34	Spatial contextual classification and prediction models for mining geospatial data - Shekhar, Schrater, et al.
33	Comparative evaluation of approaches to propositionalization - Krogel, Rawles, et al. - 2003
31	Beyond concise and colorful: learning intelligible rules - Pazzani, Mani, et al. - 1997
29	Mining Frequent Neighboring Class Sets in Spatial Databases - Morimoto - 2001
28	D.: Inducing multi-level association rules from multiple relations - Lisi, Malerba - 2004
26	Propositionalisation and Aggregates - Knobbe, Haas, et al. - 2001
19	A progressive refinement approach to spatiall data mining. A thesis submitted in partial fulfillment of the requirement for the degree of doctor of philosophy in the school of computing science - Koperski - 1999
19	A multi-relational decision tree learning algorithm - implementation and experiments - Atramentov, Leiva, et al. - 2003
18	Naive bayesian classification of structured data - Flach, Lachiche
15	Integrated spatial reasoning in geographic infomation systems: continuing topology and direction - Sharma, J - 1986
14	A.: “Discovery of spatial association rules in georeferenced census data: a relational mining approach - Appice, Ceci, et al. - 2003
14	Multi-relational data mining using probabilistic relational models: research summary - Getoor
13	Relative unsupervised discretization for association rule mining - Ludl, Widmer - 2000
12	Redundant feature elimination for multi-class problems - Appice, Ceci, et al. - 2004
10	Mr-SBC: a MultiRelational Naive Bayes Classifier - Ceci, Appice, et al.
10	Empowering a GIS with inductive learning capabilities: The case of ingens - Malerba, Esposito, et al.
10	Spatial reasoning: theory and practice - Aiello - 2002
5	D.: Spatial Associative Classification at Different Levels of Granularity: A Probabilistic Approach - Ceci, Appice, et al. - 2004
4	P.: Majority classification by means of association rules - Baralis, Garza - 2003
4	Neural networks and the bias/variance dilemma - German, Bienenstock, et al. - 1992
4	Relational learning vs. propositionalization: Investigations in inductive logic programming and propositional machine learning - Kramer - 1999
3	On propositionalization for knowledge discovery in relational databases - Krogel - 2005
2	Learning Recursive Theories in the Normal - Malerba
2	eds, Principles of Data Mining and Knowledge Discovery - Zighed, Komorowski, et al. - 2000
1	Mining spatial association rules from census data with ARES - Appice, Lanza, et al. - 2004