S. Dzeroski, L. De Haspe, B. Ruck, W. Walley. Classification of river water quality data using machine learning. In Proc. of the Fifth Int. Conference on the Development and Application of Computer Technologies to Environmental Studies, Vol. I: Pollution Modelling., pp. 129--137. Computational Mechanics Publications, Southampton, 1994.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....quite successful in extracting comprehensible models of relational data. Indeed, for over a decade, ILP systems have been used to construct predictive models for data drawn from diverse domains. These include the sciences [16] engineering [10] language processing [33] environment monitoring [11], and software analysis [5] In a nutshell, ILP systems repeatedly examine candidate clauses (the search space ) to find good rules. Ideally, the search will stop when the rules cover nearly all positive examples with only a few negative examples being covered. Unfortunately, the search space ....

S. Deroski, L. Dehaspe, B. Ruck, and W. Walley. Classification of river water quality data using machine learning. In Proceedings of the 5th International Conference on the Development and Application of Computer Techniques to Environmental Studies, 1995.

.... Logic Programming (ILP) It is a measure of the promise offered by this setting that ILP programs have already been applied with some success on non trivial problems in molecular biology [13, 14, 19] stress analysis in engineering [6] electronic circuit diagnosis [9] environmental monitoring [8], software engineering [2] and natural language processing [27] These results were all achieved using problem specific background knowledge encoded as logic programs, and without recourse to other methods of statistical analysis. While in theory, the effect of all such methods could be ....

S. Dzeroski, L. Dehaspe, B. Ruck, and W. Walley. Classification of river water quality data using machine learning. In Proceedings of the Fifth International Conference on the Development and Application of Computer Techniques Environmental Studies, 1994.

....background knowledge to construct automatically clausal definitions that in some sense, generalise a set of instances. This has allowed a novel form of data analysis in molecular biology [15, 16, 25] stress analysis in engineering [8] electronic circuit diagnosis [11] environmental monitoring [10], software 1 engineering [1] and natural language processing [45] Of these, some, such as those described in [1, 10, 11, 25, 45] are naturally classificatory. Others, such as those described in [8, 15, 16] are essentially concerned with predicting values of a numerical response variable ....

.... This has allowed a novel form of data analysis in molecular biology [15, 16, 25] stress analysis in engineering [8] electronic circuit diagnosis [11] environmental monitoring [10] software 1 engineering [1] and natural language processing [45] Of these, some, such as those described in [1, 10, 11, 25, 45], are naturally classificatory. Others, such as those described in [8, 15, 16] are essentially concerned with predicting values of a numerical response variable (for example, chemical activity of a compound) For problems of this latter type, ILP programs have largely been restricted to ....

S. Dzeroski, L. Dehaspe, B. Ruck, and W. Walley. Classification of river water quality data using machine learning. In Proceedings of the Fifth International Conference on the Development and Application of Computer Techniques Environmental Studies, 1994.

.... the techniques described here to bio chemical research concerned with structure activity relationships has been reported to that readership in [18] 2 ASHWIN SRINIVASAN AND ROSS KING ogy [20, 21, 30] stress analysis in engineering [9] electronic circuit diagnosis [12] environmental monitoring [11], software engineering [2] and natural language processing [51] These results were all achieved using problem specific background knowledge encoded as logic programs, and without recourse to other methods of statistical analysis. While in theory the effect of all such methods could be ....

S. Dzeroski, L. Dehaspe, B. Ruck, and W. Walley. Classification of river water quality data using machine learning. In Proceedings of the Fifth International Conference on the Development and Application of Computer Techniques Environmental Studies, 1994.

....background knowledge to construct automatically clausal definitions that in some sense, generalise a set of instances. This has allowed a novel form of data analysis in molecular biology [15, 16, 26] stress analysis in engineering [7] electronic circuit diagnosis [11] environmental monitoring [10], software engineering [1] and natural language processing [49] Of these, 2 some, such as those described in [1, 10, 11, 26, 49] are naturally classificatory. Others, such as those described in [7, 15, 16] are essentially concerned with predicting values of a numerical response variable ....

.... This has allowed a novel form of data analysis in molecular biology [15, 16, 26] stress analysis in engineering [7] electronic circuit diagnosis [11] environmental monitoring [10] software engineering [1] and natural language processing [49] Of these, 2 some, such as those described in [1, 10, 11, 26, 49], are naturally classificatory. Others, such as those described in [7, 15, 16] are essentially concerned with predicting values of a numerical response variable (for example, chemical activity of a compound) For problems of this latter type, ILP programs have largely been restricted to ....

S. Dzeroski, L. Dehaspe, B. Ruck, and W. Walley. Classification of river water quality data using machine learning. In Proceedings of the Fifth International Conference on the Development and Application of Computer Techniques Environmental Studies, 1994.

....illustrating the predictive and descriptive ILP settings. Given a list of biological indicators present at a river water sampling site and their abundance levels (300 samples) the predictive knowledge discovery task is to classify the sample into one of the five classes B1a, B1b, B2, B3 and B4 [13]. Knowledge about biological indicators (families of macro benthis invertebrates) consisted of eighty predicates of the form family(X,A) each denoting that family is present in sample X with aboundance level A (e.g. tipulidae(X,A) asellidae(X,A) etc. and the background knowledge about the ....

S. Dzeroski, L. De Haspe, B. Ruck, W. Walley. Classification of river water quality data using machine learning. Proc. Fifth Int. Conference on the Development and Application of Computer Technologies to Environmental Studies, Vol. I: Pollution Modelling., pp. 129--137. Computational Mechanics Publications, Southampton, 1994.

....concerned with learning clausal theories in first order logic. Two main approaches exist to learning in first order logic, known under the names of explanatory and descriptive learning. The first [ Muggleton, 1995 ] is also called learning from entailment or normal ILP, the second [ De Raedt and Dzeroski, 1994 ] is also called learning from interpretations or nonmonotonic ILP. The first setting is concerned with the induction of rules that explain (correctly classify) the given observations, whereas the latter is concerned with the induction of constraints that describe the (dependencies in the) given ....

....theoretical ideas and a basis for the future development of a system for integrated learning. Several experiments were carried out on the real life problem of characterizing river water quality. The task is to interpret a biological sample taken from a river in terms of five quality classes (see [ Dzeroski et al. 1994 ] A fact of the form family(X) resp. family(X; A) indicates that the bioindicator family is present in sample X (resp. at abundance level A) The five classes are denoted class0(X) to class4(X) Several machine learning systems have been applied on this problem, including CN2 [ Clark and ....

S. Dzeroski, L. Dehaspe, B. Ruck, and W.J. Walley. Classification of river water quality data using machine learning. In P. Zannetti, editor, Computer Techniques in Environmental Studies V Vol. I: Pollution modelling, pages 129--137, 1994.

.... b3) same(b1; b3) In this knowledge base, the Claudien system discovered 65 rules such as: mesh(E; 1) notimportant(E) mesh(E1; 12) circuit(E1) free(E1) neighbour(E1; E2) mesh(E2; 2) short(E2) The second application is taken from the domain of environmental monitoring (see also [6]) The goal here is to capture the expertise of an expert river ecologist who classified 292 field samples of benthic communities from British Midland Rivers. Each sample is described by means of the abundances (recorded on a scale of 0 to 6) of eighty different microinvertebrate families. The ....

S. Dzeroski, L. Dehaspe, B.M. Ruck, and W.J. Walley. Classification of river water quality data using machine learning. In Proceedings of the 5th International Conference on the Development and Application of Computer Techniques to Environmental Studies (ENVIROSOFT'94), to appear.

....unclassified data. Claudien 1 combines data mining principles with inductive logic programming. It can be considered the first system that discovers clausal regularities from unclassified data. To this aim, a novel semantics for inductive logic programming has been developed, cf. De Raedt and Dzeroski, 1994], in which examples are represented by Herbrand interpretations and the aim is to discover a logically maximally general hypothesis that has all the examples as models. The novel semantics is said to define characteristic induction from closed observations. The special case, where the data ....

....induction tasks such as finding functional or multi valued dependencies and association rules. By tuning Claudien s parameters, especially the declarative bias, Claudien is able to address these tasks. The second experiment, in finite element mesh design [Dol sak and Muggleton, 1992; Lavrac and Dzeroski, 1994], shows that Gamma although Claudien is not intended to perform classification tasks Gamma it can also be successfully applied in this context. Two further experiments (on mutagenesis [Srinivasan et al. 1995b] and water quality ( Dzeroski et al. 1994] show Claudien s performance on ....

[Article contains additional citation context not shown here]

S. Dzeroski, L. Dehaspe, B. Ruck, and W. Walley. Classification of river water quality data using machine learning. In Proceedings of the 5th International Conference on the Development and Application of Computer Techniques to Environmental Studies, 1994.

.... b3) same(b1; b3) In this knowledge base, the Claudien system discovered 65 rules such as: mesh(E; 1) notimportant(E) mesh(E1; 12) circuit(E1) free(E1) neighbour(E1; E2) mesh(E2; 2) short(E2) The second application is taken from the domain of environmental monitoring (see also [8]) The goal here is to capture the expertise of an expert river ecologist who classified 292 field samples of benthic communities from British Midland Rivers. Each sample is described by means of the abundances (recorded on a scale of 0 to 6) of eighty different microinvertebrate families. 8 As ....

S. Dzeroski, L. Dehaspe, B.M. Ruck, and W.J. Walley. Classification of river water quality data using machine learning. In Proceedings of the 5th International Conference on the Development and Application of Computer Techniques to Environmental Studies (ENVIROSOFT'94), to appear.

No context found.

S. Dzeroski, L. De Haspe, B. Ruck, W. Walley. Classification of river water quality data using machine learning. In Proc. of the Fifth Int. Conference on the Development and Application of Computer Technologies to Environmental Studies, Vol. I: Pollution Modelling., pp. 129--137. Computational Mechanics Publications, Southampton, 1994.

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