324 research outputs found
Beam search induction and similarity constraints for predictive clustering trees
No full textMuch research on inductive databases (IDBs) focuses on local models, such as item sets and association rules. In this work, we investigate how IDBs can support global models, such as decision trees. Our focus is on predictive clustering trees (PCTs). PCTs generalize decision trees and can be used for prediction and clustering, two of the most common data mining tasks. Regular PCT induction builds PCTs top-down, using a greedy algorithm, similar to that of C4.5. We propose a new induction algorithm for PCTs based on beam search. This has three advantages over the regular method: (a) it returns a set of PCTs satisfying the user constraints instead of just one PCT; (b) it better allows for pushing of user constraints into the induction algorithm; and (c) it is less susceptible to myopia. In addition, we propose similarity constraints for PCTs, which improve the diversity of the resulting PCT set.sponsorship: This work was supported by the IQ project(IST-FET FP6-516169).Jan Struyf is a postdoctoral fellow of the Fund for Scientific Research of Flanders(FWO-Vlaanderen). (IQ|IST-FET FP6-516169)status: Publishe
Analysis of time series data with predictive clustering trees
No full textPredictive clustering is a general framework that unifies clustering and prediction. This paper investigates how to apply this framework to cluster time series data. The resulting system, Clus-TS, constructs predictive clustering trees (PCTs) that partition a given set of time series into homogeneous clusters. In addition, PCTs provide a symbolic description of the clusters. We evaluate Clus-TS on time series data from microarray experiments. Each data set records the change over time in the expression level of yeast genes as a response to a change in environmental conditions. Our evaluation shows that Clus-TS is able to cluster genes with similar responses, and to predict the time series based on the description of a gene. Clus-TS is part of a larger project where the goal is to investigate how global models can be combined with inductive databases.sponsorship: This work was supported by the IQ project(IST-FET FP6-516169). Jan Struyf is a postdoctoral fellow of the Fund for Scientific Research of Flanders(FWO-Vlaanderen). (IQ|IST-FET FP6-516169)status: Publishe
Integrating decision tree learning into inductive databases
No full textIn inductive databases, there is no conceptual difference between data and the models describing the data: both can be stored and queried using some query language. The approach that adheres most strictly to this philosophy is probably the one proposed by Calders et al. (2006): in this approach, models are stored in relational tables and queried using standard SQL. The approach has been described in detail for association rule discovery. In this work, we study how decision tree induction can be integrated in this approach. We propose a representation format for decision trees similar to the format proposed earlier for association rules, and queryable using standard SQL; and we present a prototype system in which part of the needed functionality is implemented. In particular, we have developed an exhaustive tree learning algorithm able to answer a wide range of constrained queries.status: Publishe
Analysis of time series data with predictive clustering trees
No full textPredictive clustering is a general framework that unifies clustering and prediction. This paper investigates how to apply this framework to cluster time series data. The resulting system, Clus-TS, constructs predictive clustering trees (PCTs) that partition a given set of time series into homogeneous clusters. In addition, PCTs provide a symbolic description of the clusters. The paper considers several distance metrics to measure cluster homogeneity (both quantitative and qualitative). We evaluate Clus-TS on time series data from microarray experiments. Each data set records the change over time in the expression level of yeast genes in response to a change in environmental conditions. Our evaluation shows that Clus-TS is able to identify interesting clusters of genes with similar responses. Clus-TS is part of a larger project where the goal is to investigate how global models can be combined with inductive databases.status: Publishe
Ensembles of multi-objective decision trees
No full textEnsemble methods are able to improve the predictive performance of many base classifiers. Up till now, they have been applied to classifiers that predict a single target attribute. Given the non-trivial interactions that may occur among the different targets in multi-objective prediction tasks, it is unclear whether ensemble methods also improve the performance in this setting. In this paper, we consider two ensemble learning techniques, bagging and random forests, and apply them to multi-objective decision trees (MODTs), which are decision trees that predict multiple target attributes at once. We empirically investigate the performance of ensembles of MODTs. Our most important conclusions are: (1) ensembles of MODTs yield better predictive performance than MODTs, and (2) ensembles of MODTs are equally good, or better than ensembles of single-objective decision trees, i.e., a set of ensembles for each target. Moreover, ensembles of MODTs have smaller model size and are faster to learn than ensembles of single-objective decision trees.sponsorship: This work was supported by the EU FET IST project Inductive Querying, contract number FP6-516169. Jan Struyf is a post-doctoral fellow of the Research Foundation - Flanders (FWO-Vlaanderen). The authors would like to thank Hendrik Blockeel for providing valuable suggestions. (EU FET IST|FP6-516169)status: Publishe
Hoe zacht kan de avond zijn : voor zangstem en klavier /
No full textBezetting: klavier en zangstem, voor barytonPartituurHerkomst: Collectie Jan Broeck
Change of representation for statistical relational learning
No full textStatistical relational learning (SRL) algorithms learn statistical models from relational data, such as that stored in a relational database. We previously introduced view learning for SRL, in which the view of a relational database can be automatically modified, yielding more accurate statistical models. The present paper presents SAYU-VISTA, an algorithm which advances beyond the initial view learning approach in three ways. First, it learns views that introduce new relational tables, rather than merely new fields for an existing table of the database. Second, new tables or new fields are not limited to being approximations to some target concept; instead, the new approach performs a type of predicate invention. The new approach avoids the classical problem with predicate invention, of learning many useless predicates, by keeping only new fields or tables (i.e., new predicates) that immediately improve the performance of the statistical model. Third, retained fields or tables can then be used in the definitions of further new fields or tables. We evaluate the new view learning approach on three relational classification tasks.sponsorship: This work was supported in part by U.S. National Science Foundation grant IIS 0534908 and by an NLM training grant to the Computation and Informatics in Biology and Medicine Training Program (NLM 5T15LM007359). Jan Struyf is a postdoctoral fellow of the Fund for Scientific Research of Flanders (FWO-Vlaanderen). We would also like to thank Pedro Domingos, Stanley Kok and the rest of Alchemy team for answering our questions regarding the Alchemy system and for providing the Cora dataset. (U.S. National Science Foundation|IIS 0534908, NLM training grant|NLM 5T15LM007359)status: Publishe
Proceedings of The 5th International Workshop on Knowledge Discovery in Inductive Databases (KDID'06)
No full textThe 5th International Workshop on Knowledge Discovery in Inductive Databases
(KDID 2006) was held on September 18, 2006 in Berlin, Germany, in conjunction
with ECML/PKDD 2006: The 17th European Conference on Machine Learning
(ECML) and the 10th European Conference on Principles and Practice of
Knowledge Discovery in Databases (PKDD).
Inductive databases (IDBs) represent a database view on data mining and
knowledge discovery. IDBs contain not only data, but also generalizations (patterns
and models) valid in the data. In an IDB, ordinary queries can be used
to access and manipulate data, while inductive queries can be used to generate
(mine), manipulate, and apply patterns. In the IDB framework, patterns become
“first-class citizens” and KDD becomes an extended querying process in
which both the data and the patterns/models that hold in the data are queried.
The IDB framework is appealing as a general framework for data mining, because
it employs declarative queries instead of ad-hoc procedural constructs. As
declarative queries are often formulated using constraints, inductive querying
is closely related to constraint-based data mining. The IDB framework is also
appealing for data mining applications, as it supports the entire KDD process,
i.e., nontrivial multi-step KDD scenarios, rather than just individual data mining
operations. The goal of the workshop was to bring together database and
data mining researchers interested in the areas of inductive databases, inductive
queries, constraint-based data mining, and data mining query languages.
This workshop followed the previous four successful KDID workshops organized
in conjunction with ECML/PKDD: KDID’02 held in Helsinki, Finland,
KDID’03 held in Cavtat-Dubrovnik, Croatia, KDID’04 held in Pisa, Italy,
and KDID’05 held in Porto, Portugal. Its scientific program included nine regular
presentations and two short ones, as well as an invited talk by Kiri Wagstaff
(Jet Propulsion Laboratory, California Institute of Technology, USA).status: Publishe
Aangeboren torticollis : contra-indicatie voor sportbeoefening? Een case report
No full textEen 13-jarige jongen kwam samen met zijn ouders voor raadpleging naar het Centrum voor Sportgeneeskunde vanwege een asymptomatische torticollis. De medische vraagstelling van de sporter was of de torticollis een contra-indcatie vormde voor het beoefenen van zijn huidige sporten kanovaren en iaido (Japanse zwaardkunst) of andere sporten. Aangezien een aangeboren torticollis geassocieerd kan zijn met mogelijk levensbedreigende afwijkingen werder verder orthopedisch, cardiaal en nefrologisch onderzoek verricht. Orthopedisch onderzoek toonde een partieele fusie van C2-C3-C4 en een hemiwervel tussen C6 en C7, een dextroconvexe dorsale scoliose en een syrinx van D2-D12. Cardiologisch onderzoek was normaal. Nefrologisch onderzoek toonde een afwezige linker nier. Voor kanovaren en iaido waren er geen contra-indcaties. Voor contactsport vormde de hoge cervicale fusie wel een contra-indcatie. Omdat anomalieen ter hoogte van de hals vaak gepaard gaan met mogelijk levensbedreigende afwijkingen is het belangrijk sporters met deze afwijking te screenen op orthopedisch, cardiologisch, neus- keel- oor- en nefrologisch vlak.A 13 year old boy presented with his parents to the Center of Sports Medicine for an asymptomatic torticollis. They seeked medical advice concerning any risk of his (canoeing, iaido) and other sports for his torticollis. Because a congenital torticollis can be associated with lethal conditions, the boy had an orthopaedic, cardial and nephrologic screening. Orthopaedic examination disclosed a partial fusion of C2-C3-C4, a hemivertebra between C6 and C7, a dextroconvex scoliosis and a syrinx from D2-D12. Cardiac assessment was normal. Nephrologic screening showed agenesis of the left kidney. There were no contra-indcations for his sports. However the cervical fusion was a contra-indcation for contactsport. The risk of associated laesions with congenital cervical anomalies, necessitates an orthopaedic,cardiac, nephrologic and nose- ear- throat- evaluation in patients with this condition
- …
