To see the other types of publications on this topic, follow the link: Ruleset generation.
Dissertations / Theses on the topic 'Ruleset generation'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 48 dissertations / theses for your research on the topic 'Ruleset generation.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Haq, Ikram. "Fraud detection for online banking for scalable and distributed data." Thesis, Federation University Australia, 2020. http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/171977.
Full textAbstract:
Online fraud causes billions of dollars in losses for banks. Therefore, online banking fraud detection is an important field of study. However, there are many challenges in conducting research in fraud detection. One of the constraints is due to unavailability of bank datasets for research or the required characteristics of the attributes of the data are not available. Numeric data usually provides better performance for machine learning algorithms. Most transaction data however have categorical, or nominal features as well. Moreover, some platforms such as Apache Spark only recognizes numeric data. So, there is a need to use techniques e.g. One-hot encoding (OHE) to transform categorical features to numerical features, however OHE has challenges including the sparseness of transformed data and that the distinct values of an attribute are not always known in advance. Efficient feature engineering can improve the algorithm’s performance but usually requires detailed domain knowledge to identify correct features. Techniques like Ripple Down Rules (RDR) are suitable for fraud detection because of their low maintenance and incremental learning features. However, high classification accuracy on mixed datasets, especially for scalable data is challenging. Evaluation of RDR on distributed platforms is also challenging as it is not available on these platforms. The thesis proposes the following solutions to these challenges: • We developed a technique Highly Correlated Rule Based Uniformly Distribution (HCRUD) to generate highly correlated rule-based uniformly-distributed synthetic data. • We developed a technique One-hot Encoded Extended Compact (OHE-EC) to transform categorical features to numeric features by compacting sparse-data even if all distinct values are unknown. • We developed a technique Feature Engineering and Compact Unified Expressions (FECUE) to improve model efficiency through feature engineering where the domain of the data is not known in advance. • A Unified Expression RDR fraud deduction technique (UE-RDR) for Big data has been proposed and evaluated on the Spark platform. Empirical tests were executed on multi-node Hadoop cluster using well-known classifiers on bank data, synthetic bank datasets and publicly available datasets from UCI repository. These evaluations demonstrated substantial improvements in terms of classification accuracy, ruleset compactness and execution speed.Doctor of Philosophy
2
Gundavarapu, Madhavi. "RuleGen – A Rule Generation Application Using Multiset Decision Tables." University of Akron / OhioLINK, 2005. http://rave.ohiolink.edu/etdc/view?acc_num=akron1140111266.
Full text
3
Koh, Yun Sing, and n/a. "Generating sporadic association rules." University of Otago. Department of Computer Science, 2007. http://adt.otago.ac.nz./public/adt-NZDU20070711.115758.
Full textAbstract:
Association rule mining is an essential part of data mining, which tries to discover associations, relationships, or correlations among sets of items. As it was initially proposed for market basket analysis, most of the previous research focuses on generating frequent patterns. This thesis focuses on finding infrequent patterns, which we call sporadic rules. They represent rare itemsets that are scattered sporadically throughout the database but with high confidence of occurring together. As sporadic rules have low support the minabssup (minimum absolute support) measure was proposed to filter out any rules with low support whose occurrence is indistinguishable from that of coincidence. There are two classes of sporadic rules: perfectly sporadic and imperfectly sporadic rules. Apriori-Inverse was then proposed for perfectly sporadic rule generation. It uses a maximum support threshold and user-defined minimum confidence threshold. This method is designed to find itemsets which consist only of items falling below a maximum support threshold. However imperfectly sporadic rules may contain items with a frequency of occurrence over the maximum support threshold. To look for these rules, variations of Apriori-Inverse, namely Fixed Threshold, Adaptive Threshold, and Hill Climbing, were proposed. However these extensions are heuristic. Thus the MIISR algorithm was proposed to find imperfectly sporadic rules using item constraints, which capture rules with a single-item consequent below the maximum support threshold. A comprehensive evaluation of sporadic rules and current interestingness measures was carried out. Our investigation suggests that current interestingness measures are not suitable for detecting sporadic rules.
4
Ma, Liangjun, and Shouchuan Zhang. "Generating Fuzzy Rules For Case-based Classification." Thesis, Mälardalens högskola, Akademin för innovation, design och teknik, 2012. http://urn.kb.se/resolve?urn=urn:nbn:se:mdh:diva-16444.
Full textAbstract:
As a technique to solve new problems based on previous successful cases, CBR represents significant prospects for improving the accuracy and effectiveness of unstructured decision-making problems. Similar problems have similar solutions is the main assumption. Utility oriented similarity modeling is gradually becoming an important direction for Case-based reasoning research. In this thesis, we propose a new way to represent the utility of case by using fuzzy rules. Our method could be considered as a new way to estimate case utility based on fuzzy rule based reasoning. We use modified WANG’s algorithm to generate a fuzzy if-then rule from a case pair instead of a single case. The fuzzy if-then rules have been identified as a powerful means to capture domain information for case utility approximation than traditional similarity measures based on feature weighting. The reason why we choose the WANG algorithm as the foundation is that it is a simpler and faster algorithm to generate if-then rules from examples. The generated fuzzy rules are utilized as a case matching mechanism to estimate the utility of the cases for a given problem. The given problem will be formed with each case in the case library into pairs which are treated as the inputs of fuzzy rules to determine whether or to which extent a known case is useful to the problem. One case has an estimated utility score to the given problem to help our system to make decision. The experiments on several data sets have showed the superiority of our method over traditional schemes, as well as the feasibility of learning fuzzy if-then rules from a small number of cases while still having good performances.
5
Johnson, Christopher Wayne Bagai Rajiv. "Mechanical generation of concrete syntax rules for the Schütz semantic editor." Diss., A link to full text of this thesis in SOAR, 2007. http://soar.wichita.edu/dspace/handle/10057/1141.
Full textAbstract:
Thesis (M.S.)--Wichita State University, College of Liberal Arts and Sciences., Dept. of Computer Science."May 2007." Title from PDF title page (viewed on Dec. 26, 2007). Thesis adviser: Rajiv Bagai. Includes bibliographical references (65-66 leaves).
6
Powell, Anastasia. "Generation Y : re-writing the rules on sex,love and consent /." Connect to thesis, 2007. http://eprints.unimelb.edu.au/archive/00004035.
Full text
7
Fry, John, T. Galla, and J. M. Binner. "Quantitative decision-making rules for the next generation of smarter evacuations." Springer, 2015. http://hdl.handle.net/10454/17563.
Full text
8
Hall, A. R. "Automatic speech recognition using morpheme structure rules for word hypothesis and dictionary generation." Thesis, London South Bank University, 1989. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.352963.
Full text
9
Bakshi, Arjun. "Methodology For Generating High-Confidence Cost-Sensitive Rules For Classification." University of Cincinnati / OhioLINK, 2013. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1377868085.
Full text
10
Kuri, Bless. "Sustainable generation mix as a reference in effective design of electricity market structures and rules." Thesis, University of Bath, 2006. https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.440360.
Full text
11
Johnston, Cristin D. "Observation training evaluating a procedure for generating self-rules in the absence of reinforcement /." abstract and full text PDF (UNR users only), 2008. http://0-gateway.proquest.com.innopac.library.unr.edu/openurl?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:dissertation&res_dat=xri:pqdiss&rft_dat=xri:pqdiss:3316373.
Full text
12
Petersen, Henry. "Generating High Precision Classification Rules for Screening of Irrelevant Studies in Systematic Review Literature Searches." Thesis, The University of Sydney, 2016. http://hdl.handle.net/2123/15454.
Full textAbstract:
Systematic reviews aim to produce repeatable, unbiased, and comprehensive answers to clinical questions. Systematic reviews are an essential component of modern evidence based medicine, however due to the risks of omitting relevant research they are highly time consuming to create and are largely conducted manually. This thesis presents a novel framework for partial automation of systematic review literature searches. We exploit the ubiquitous multi-stage screening process by training the classifier using annotations made by reviewers in previous screening stages. Our approach has the benefit of integrating seamlessly with the existing screening process, minimising disruption to users. Ideally, classification models for systematic reviews should be easily interpretable by users. We propose a novel, rule based algorithm for use with our framework. A new approach for identifying redundant associations when generating rules is also presented. The proposed approach to redundancy seeks to both exclude redundant specialisations of existing rules (those with additional terms in their antecedent), as well as redundant generalisations (those with fewer terms in their antecedent). We demonstrate the ability of the proposed approach to improve the usability of the generated rules. The proposed rule based algorithm is evaluated by simulated application to several existing systematic reviews. Workload savings of up to 10% are demonstrated. There is an increasing demand for systematic reviews related to a variety of clinical disciplines, such as diagnosis. We examine reviews of diagnosis and contrast them against more traditional systematic reviews of treatment. We demonstrate existing challenges such as target class heterogeneity and high data imbalance are even more pronounced for this class of reviews. The described algorithm accounts for this by seeking to label subsets of non-relevant studies with high precision, avoiding the need to generate a high recall model of the minority class.
13
Morak, Michael. "The impact of disjunction on reasoning under existential rules." Thesis, University of Oxford, 2014. https://ora.ox.ac.uk/objects/uuid:b8f012c4-0210-41f6-a0d3-a9d1ea5f8fac.
Full textAbstract:
Ontological database management systems are a powerful tool that combine traditional database techniques with ontological reasoning methods. In this setting, a classical extensional database is enriched with an ontology, or a set of logical assertions, that describe how new, intensional knowledge can be derived from the extensional data. Conjunctive queries are therefore answered against this combined knowledge base of extensional and intensional data. Many languages that represent ontologies have been introduced in the literature. In this thesis we will focus on existential rules (also called tuple-generating dependencies or Datalog± rules), and three established languages in this area, namely guarded-based rules, sticky rules and weakly-acyclic rules. The main goal of the thesis is to enrich these languages with non-deterministic constructs (i.e. disjunctions) and investigate the complexity of the answering conjunctive queries under these extended languages. As is common in the literature, we will distinguish between combined complexity, where the database, the ontology and the query are considered as input, and data complexity, where only the database is considered as input. The latter case is relevant in practice, as usually the ontology and the query can be considered as fixed, and are usually much smaller than the database itself. After giving appropriate definitions to extend the considered languages to disjunctive existential rules, we establish a series of complexity results, completing the complexity picture for each of the above languages, and four different query languages: arbitrary conjunctive queries, bounded (hyper-)treewidth queries, acyclic queries and atomic queries. For the guarded-based languages, we show a strong 2EXPTIME lower bound for general queries that holds even for fixed ontologies, and establishes 2EXPTIME-completeness of the query answering problem in this case. For acyclic queries, the complexity can be reduced to EXPTIME, if the predicate arity is bounded, and the problem even becomes tractable for certain restricted languages, if only atomic queries are used. For ontologies represented by sticky disjunctive rules, we show that the problem becomes undecidable, even in the case of data complexity and atomic queries. Finally, for weakly-acyclic rules, we show that the complexity increases from 2EXPTIME to coN2EXPTIME in general, and from tractable to coNP in case of the data complexity, independent of which query language is used. After answering the open complexity questions, we investigate applications and relevant consequences of our results for description logics and give two generic complexity statements, respectively, for acyclic and general conjunctive query answering over description logic knowledge bases. These generic results allow for an easy determination of the complexity of this reasoning task, based on the expressivity of the considered description logic.
14
Albhbah, Atia Mahmod. "Dynamic web forms development using RuleML : building a framework using metadata driven rules to control Web forms generation and appearance." Thesis, University of Bradford, 2013. http://hdl.handle.net/10454/5719.
Full textAbstract:
Web forms development for Web based applications is often expensive, laborious, error-prone, time consuming and requires a lot of effort. Web forms are used by many different people with different backgrounds and a lot of demands. There is a very high cost associated with the need to update the Web application systems to achieve these demands. A wide range of techniques and ideas to automate the generation of Web forms exist. These techniques and ideas however, are not capable of generating the most dynamic behaviour of form elements, and make Insufficient use of database metadata to control Web forms' generation and appearance. In this thesis different techniques are proposed that use RuleML and database metadata to build rulebases to improve the automatic and dynamic generation of Web forms. First this thesis proposes the use of a RuleML format rulebase using Reaction RuleML that can be used to support the development of automated Web interfaces. Database metadata can be extracted from system catalogue tables in typical relational database systems, and used in conjunction with the rulebase to produce appropriate Web form elements. Results show that this mechanism successfully insulates application logic from code and suggests that Abstract iii the method can be extended from generic metadata rules to more domain specific rules. Second it proposes the use of common sense rules and domain specific rules rulebases using Reaction RuleML format in conjunction with database metadata rules to extend support for the development of automated Web forms. Third it proposes the use of rules that involve code to implement more semantics for Web forms. Separation between content, logic and presentation of Web applications has become an important issue for faster development and easy maintenance. Just as CSS applied on the client side to control the overall presentation of Web applications, a set of rules can give a similar consistency to the appearance and operation of any set of forms that interact with the same database. We develop rules to order Web form elements and query forms using Reaction RuleML format in conjunction with database metadata rules. The results show the potential of RuleML formats for representing database structural and active semantics. Fourth it proposes the use of a RuleML based approach to provide more support for greater semantics for example advanced domain support even when this is not a DBMS feature. The approach is to specify most of the semantics associated with data stored in RDBMS, to overcome some RDBMSs limitations. RuleML could be used to represent database metadata as an external format.
15
Albhbah, Atia M. "Dynamic web forms development using RuleML. Building a framework using metadata driven rules to control Web forms generation and appearance." Thesis, University of Bradford, 2013. http://hdl.handle.net/10454/5719.
Full textAbstract:
Web forms development for Web based applications is often expensive, laborious, error-prone, time consuming and requires a lot of effort. Web forms are used by many different people with different backgrounds and a lot of demands. There is a very high cost associated with the need to update the Web application systems to achieve these demands.
A wide range of techniques and ideas to automate the generation of Web forms exist. These techniques and ideas however, are not capable of generating the most dynamic behaviour of form elements, and make Insufficient use of database metadata to control Web forms¿ generation and appearance.
In this thesis different techniques are proposed that use RuleML and database metadata to build rulebases to improve the automatic and dynamic generation of Web forms.
First this thesis proposes the use of a RuleML format rulebase using Reaction RuleML that can be used to support the development of automated Web interfaces. Database metadata can be extracted from system catalogue tables in typical relational database systems, and used in conjunction with the rulebase to produce appropriate Web form elements. Results show that this mechanism successfully insulates application logic from code and suggests that
Abstract
iii
the method can be extended from generic metadata rules to more domain specific rules.
Second it proposes the use of common sense rules and domain specific rules rulebases using Reaction RuleML format in conjunction with database metadata rules to extend support for the development of automated Web forms.
Third it proposes the use of rules that involve code to implement more semantics for Web forms. Separation between content, logic and presentation of Web applications has become an important issue for faster development and easy maintenance. Just as CSS applied on the client side to control the overall presentation of Web applications, a set of rules can give a similar consistency to the appearance and operation of any set of forms that interact with the same database. We develop rules to order Web form elements and query forms using Reaction RuleML format in conjunction with database metadata rules. The results show the potential of RuleML formats for representing database structural and active semantics.
Fourth it proposes the use of a RuleML based approach to provide more support for greater semantics for example advanced domain support even when this is not a DBMS feature. The approach is to specify most of the semantics associated with data stored in RDBMS, to overcome some RDBMSs limitations. RuleML could be used to represent database metadata as an external format.
16
Ademi, Muhamet. "adXtractor – Automated and Adaptive Generation of Wrappers for Information Retrieval." Thesis, Malmö högskola, Fakulteten för teknik och samhälle (TS), 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:mau:diva-20071.
Full textAbstract:
The aim of this project is to investigate the feasibility of retrieving unstructured automotive listings from structured web pages on the Internet. The research has two major purposes: (1) to investigate whether it is feasible to pair information extraction algorithms and compute wrappers (2) demonstrate the results of pairing these techniques and evaluate the measurements. We merge two training sets available on the web to construct reference sets which is the basis for the information extraction. The wrappers are computed by using information extraction techniques to identify data properties with a variety of techniques such as fuzzy string matching, regular expressions and document tree analysis. The results demonstrate that it is possible to pair these techniques successfully and retrieve the majority of the listings. Additionally, the findings also suggest that many platforms utilise lazy loading to populate image resources which the algorithm is unable to capture. In conclusion, the study demonstrated that it is possible to use information extraction to compute wrappers dynamically by identifying data properties. Furthermore, the study demonstrates the ability to open non-queryable domain data through a unified service.
17
Honorato-Zimmer, Ricardo. "On a thermodynamic approach to biomolecular interaction networks." Thesis, University of Edinburgh, 2017. http://hdl.handle.net/1842/28904.
Full textAbstract:
We explore the direct and inverse problem of thermodynamics in the context of rule-based modelling. The direct problem can be concisely stated as obtaining a set of rewriting rules and their rates from the description of the energy landscape such that their asymptotic behaviour when t → ∞ coincide. To tackle this problem, we describe an energy function as a finite set of connected patterns P and an energy cost function e which associates real values to each of these energy patterns. We use a finite set of reversible graph rewriting rules G to define the qualitative dynamics by showing which transformations are possible. Given G and P, we construct a finite set of rules Gp which i) has the same qualitative transition system as G and ii) when equipped with rates according to e, defines a continuous-time Markov chain that has detailed balance with respect to the invariant probability distribution determined by the energy function. The construction relies on a technique for rule refinement described in earlier work and allows us to represent thermodynamically consistent models of biochemical interaction networks in a concise manner. The inverse problem, on the other hand, is to i) check whether a rule-based model has an energy function that describes its asymptotic behaviour and if so ii) obtain the energy function from the graph rewriting rules and their rates. Although this problem is known to be undecidable in the general case, we find two suitable subsets of Kappa, our rule-based modelling framework of choice, were this question can be answer positively and the form of their energy functions described analytically.
18
Masachis, Gelo Sara. "When mRNA folding rules gene expression : lessons from type I toxin-antitoxin systems." Thesis, Bordeaux, 2018. http://www.theses.fr/2018BORD0191/document.
Full textAbstract:
Les systèmes toxine-antitoxine (TA) sont de petits modules génétiques largement présents dans les génomes bactériens. Ils codent pour une petite protéine toxique et une antitoxine. Ils sont classés en six types en fonction de la nature et du mode d'action de l'antitoxine. Ce travail a porté sur l'étude du type I, pour lequel l'antitoxine est un ARN antisens qui cible l'ARNm de la toxine afin de réprimer son expression. Au cours de cette thèse, nous avons étudié le système aapA3/IsoA3, codé sur le chromosome du pathogène gastrique humain Helicobacter pylori. À ce jour, la plupart des systèmes TA ont été étudiés à l'aide de systèmes d'expression artificiels, qui ne permettent pas de caractériser la régulation transcriptionnelle ou post-transcriptionnelle. En utilisant la létalité induite par l’expression chromosomique de la toxine obtenue en absence d’antitoxine, nous avons développé une sélection génétique de mutants suppresseurs révélés par séquençage haut-débit. Cette approche, appelée FASTBAC-Seq, nous a permis de cartographier une myriade de déterminants de toxicité localisés dans les régions codantes et non codantes du gène de la toxine AapA3. En particulier, certaines de ces mutations ont révélé l'existence de tige-boucles ARN transitoires qui agissent de manière co-transcriptionnelle pour empêcher l'initiation de la traduction pendant la synthèse de l'ARNm codant pour la toxine. Ces structures ARN métastables fonctionnelles sont nécessaires pour découpler les processus de transcription et de traduction et permettent la présence de ces gènes toxiques sur le chromosome bactérien. Bien que les ARNm non traduits deviennent rapidement instables, nos travaux ont également révélé l'existence de deux tige-boucles protectrices situées aux deux extrémités de l'ARNm. Ces structures secondaires empêchent des activités exonucléolytiques agissant en 5' et 3'. Dans l’ensemble, notre travail met en évidence les conséquences de la forte pression de sélection pour limiter l'expression des toxines sous laquelle évoluent les systèmes TA. Cela nous a permis de mieux comprendre l’influence du repliement secondaire des ARNm, non seulement lors de la régulation posttranscriptionnelle, mais aussi co-transcriptionnelle de l’expression de cette famille particulière de gènes. Ces caractéristiques de régulation basées sur l'ARN peuvent être exploitées à l'avenir pour des applications biotechnologiques (p. ex., production accrue de protéines par stabilisation d'ARNm) ou biomédicales (p.ex., développement de stratégies antimicrobiennes alternatives pour l'activation de la synthèse de toxines)Toxin-antitoxin (TA) systems are small genetic modules widely present in bacterial genomes. They usually code for a small toxic protein and its cognate antitoxin and can be classified into six types depending on the nature and mode of action of the antitoxin. This work focuses on the study of type I, for which the antitoxin is an antisense RNA that targets the toxin mRNA to inhibit its expression. We characterized the aapA3/IsoA3 system, encoded on the chromosome of the human gastric pathogen Helicobacter pylori. To date, most TAs have been studied using artificial expression systems, which do not allow the characterization of transcriptional or post-transcriptional regulation. Taking advantage of the lethality induced by the toxin chromosomal expression in the absence of antitoxin, we developed a high-throughput genetic selection of suppressor mutations revealed by Next-Generation Sequencing. This approach, named FASTBAC-Seq, allowed us to map a myriad of toxicity determinants located in both, coding and noncoding regions, of the aapA3 toxic gene. More precisely, some suppressor mutations revealed the existence of transient RNA hairpins that act co-transcriptionally to prevent translation initiation while the toxinencoding mRNA is being made. Such functional RNA metastable structures are essential to uncouple the transcription and translation processes and allow the presence of these toxic genes on bacterial chromosomes. Although untranslated mRNAs become rapidly unstable, our work also revealed the presence of two protective stem-loops located at both mRNA ends that prevent from both, 5’ and 3’ exonucleolytic activity. Altogether, our work evidenced the consequences of the strong selection pressure to silence toxin expression under which the TAs evolve, and highlighted the key role of mRNA folding in the co- and post-transcriptional regulation of this family of genes. These RNA-based regulatory mechanisms may be exploited in the future for biotechnological (e.g., increased protein production through mRNA stabilization) or biomedical (e.g., development of alternative antimicrobial strategies aiming at the activation of toxin synthesis) applications
19
Geležis, Jonas. "Programinio kodo generavimo iš grafinių veiklos taisyklių modelių galimybių tyrimas." Master's thesis, Lithuanian Academic Libraries Network (LABT), 2009. http://vddb.library.lt/obj/LT-eLABa-0001:E.02~2009~D_20090831_153530-40477.
Full textAbstract:
Programinio kodo generavimo iš veiklos taisyklių modelių sritis iki šiol yra menkai ištirta ir tai neigiamai veikia veiklos taisyklių koncepcijos plėtrą. Nagrinėjama kodo generavimo iš grafinių IS (informacinių sistemų) reikalavimus atspindinčių modelių problema. Pristatomas modifikuotu Roso metodu grindžiamo veiklos taisyklių modeliavimo IS projektavimo stadijoje metodo tyrimas, siekiant sukurti adekvačią programinio kodo generavimo iš taisyklių diagramų metodiką.One of the reasons for a relatively slow growth of the business rules approach could be the lack of developments in the field of program code generation from the business rules models. During this work methods for code generation from IS requirements models are analysed. The focus is placed on a modified Ross method based rules modelling method aiming to create an adequate code generation methodology.
20
Dymock, Yosabeth. "Vi behandlar andra så som vi själva vill bli behandlade : En studie om att undersöka och problematisera regler inom fritidshemmet utifrån generationsmaktordningen." Thesis, Södertörns högskola, Lärarutbildningen, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:sh:diva-32590.
Full textAbstract:
Syftet med denna studie har varit att undersöka och problematisera hur regler inverkar på den överordning pedagoger har i förhållande till elever utifrån generationsmaktordningen. Som grund för resultatet ligger kvalitativa observationer från tre fritidshem och kvalitativa intervjuer med fyra pedagoger från dessa. Det empiriska materialet analyseras med hjälp av socialkonstruktivism samt ett barnistiskt perspektiv. Dessa teorier grundar sig i antaganden om att vi socialt konstruerar vår verklighet samt att man kan se orättvisor och underordning utifrån ett ålders och maktperspektiv. Resultatet visar att fritidshemmet är en komplex arena där elever förväntas navigera mellan regler som är synliga, osynliga, föränderliga och svårtolkade. Det visar sig även att regler synliggörs genom tillrättavisningar som sker i olika situationer och på olika sätt. Under intervjuerna beskrivs elevernas motstånd mot regler, men är inte helt oproblematiskt på grund av hur pedagogerna tolkar motståndet och värderar det. En slutsats är att regler, hur de skapas och hur de upprätthålls förstärker den överordning pedagoger har på ett till viss del omotiverat sätt. Men att detta är något som kan utmanas och omförhandlas.The purpose of this study has been to explore and problematize how rules affect the superiority educators have in relation to pupils, based on the generation power structure. As a basis for the result are qualitative observations from three recreation centers and qualitative interviews with four educators from these. The empirical material is analyzed with the help of social constructivism and a childish perspective. These theories are based on the assumption that we socially construct our reality as well as to see injustices and subordination based on an age and power perspective. The results show that the recreation centre is a complex arena where pupils are expected to navigate between rules that are visible, invisible, changeable and difficult to interpret. It also shows that rules are made visible through reprimands that take place in different situations and in different ways. During the interviews, pupils resistance to rules is described, but is not entirely unproblematic because of the way educators interpret the resistance and value it. One conclusion is that rules, how they are created and how they are maintained reinforce the superiority educators have in a partially unjustified manner. But that this is something that can be challenged and renegotiated.
21
Mayer, Rosirene. "A linguagem de Oscar Niemeyer." reponame:Biblioteca Digital de Teses e Dissertações da UFRGS, 2003. http://hdl.handle.net/10183/6693.
Full textAbstract:
Este trabalho tem como objetivo a descrição dos elementos que caracterizam a singularidade da linguagem arquitetônica de Oscar Niemeyer. Argumenta que a identificação de tais elementos passa pelo escrutínio de aspectos não visíveis da obra do arquiteto. A identificação foi possível a partir da análise de edifícios caracterizados pelo perfil curvilíneo e da construção de um modelo que associa os elementos compositivos utilizados por Niemeyer a uma Gramática de Formas. A utilização do modelo possibilitou revelar os princípios generativos - conjunto de regras, vocabulário e relações geométricas – que caracterizam o estilo – ou linguagem arquitetônica de Niemeyer. Ajudou ainda a demonstrar como a linguagem de Niemeyer associa de forma original, operações de transformação como rotação, reflexão, e translação a um vocabulário de curvas. A associação é parametrizada segundo um traçado regulador baseado na seção áurea. Em suas conclusões o trabalho sugere possibilidades de desenvolvimento desta gramática para todas as figuras utilizadas por Niemeyer e a aplicação de princípios generativos no ensino de arquitetura.This work aims at describing the elements that characterize Oscar Niemeyer’s singular architectural language. It argues that the identification of these elements passes for the scrutiny of non-visible aspects of his work. The identification was possible taking into consideration from the analysis of buildings characterized for curved profile and the construction of a model that associates the compositional elements utilized by Niemeyer to a Shape Grammar. The utilization of the model made it possible to reveal the generative principles - set of rules, vocabulary and geometric relations - that characterize Niemeyer’s style and architectural language. It also helped showing how Niemeyer’s language associates, in an original way, operations of transformation such as rotation, reflection, and translation to a vocabulary of curves. The association has its parameters on a drawn line which acts as a regulator based on the golden section. As its conclusion, the work suggests possibilities of development of this grammar for all the forms utilized by Niemeyer and the aplication of generative principles in the teaching of architecture.
22
D’Agnese, Daniele. "Strumenti per la generazione automatica di documentazione di profili d’uso di linguaggi standard basati su Core Components." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2011. http://amslaurea.unibo.it/2702/.
Full text
23
Lopes, Priscilla de Abreu. "Agrupamento de dados semissupervisionado na geração de regras fuzzy." Universidade Federal de São Carlos, 2010. https://repositorio.ufscar.br/handle/ufscar/7061.
Full textAbstract:
Submitted by Izabel Franco (izabel-franco@ufscar.br) on 2016-09-06T18:25:30Z
No. of bitstreams: 1
DissPAL.pdf: 2245333 bytes, checksum: 24abfad37e7d0675d6cef494f4f41d1e (MD5)Approved for entry into archive by Marina Freitas (marinapf@ufscar.br) on 2016-09-12T14:03:53Z (GMT) No. of bitstreams: 1 DissPAL.pdf: 2245333 bytes, checksum: 24abfad37e7d0675d6cef494f4f41d1e (MD5)
Approved for entry into archive by Marina Freitas (marinapf@ufscar.br) on 2016-09-12T14:04:01Z (GMT) No. of bitstreams: 1 DissPAL.pdf: 2245333 bytes, checksum: 24abfad37e7d0675d6cef494f4f41d1e (MD5)
Made available in DSpace on 2016-09-12T14:04:09Z (GMT). No. of bitstreams: 1 DissPAL.pdf: 2245333 bytes, checksum: 24abfad37e7d0675d6cef494f4f41d1e (MD5) Previous issue date: 2010-08-27
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
Inductive learning is, traditionally, categorized as supervised and unsupervised. In supervised learning, the learning method is given a labeled data set (classes of data are known). Those data sets are adequate for problems of classification and regression. In unsupervised learning, unlabeled data are analyzed in order to identify structures embedded in data sets. Typically, clustering methods do not make use of previous knowledge, such as classes labels, to execute their job. The characteristics of recently acquired data sets, great volume and mixed attribute structures, contribute to research on better solutions for machine learning jobs. The proposed research fits into this context. It is about semi-supervised fuzzy clustering applied to the generation of sets of fuzzy rules. Semi-supervised clustering does its job by embodying some previous knowledge about the data set. The clustering results are, then, useful for labeling the remaining unlabeled data in the set. Following that, come to action the supervised learning algorithms aimed at generating fuzzy rules. This document contains theoretic concepts, that will help in understanding the research proposal, and a discussion about the context wherein is the proposal. Some experiments were set up to show that this may be an interesting solution for machine learning jobs that have encountered difficulties due to lack of available information about data.
O aprendizado indutivo é, tradicionalmente, dividido em supervisionado e não supervisionado. No aprendizado supervisionado é fornecido ao método de aprendizado um conjunto de dados rotulados (dados que tem a classe conhecida). Estes dados são adequados para problemas de classificação e regressão. No aprendizado não supervisionado são analisados dados não rotulados, com o objetivo de identificar estruturas embutidas no conjunto. Tipicamente, métodos de agrupamento não se utilizam de conhecimento prévio, como rótulos de classes, para desempenhar sua tarefa. A característica de conjuntos de dados atuais, grande volume e estruturas de atributos mistas, contribui para a busca de melhores soluções para tarefas de aprendizado de máquina. É neste contexto em que se encaixa esta proposta de pesquisa. Trata-se da aplicação de métodos de agrupamento fuzzy semi-supervisionados na geração de bases de regras fuzzy. Os métodos de agrupamento semi-supervisionados realizam sua tarefa incorporando algum conhecimento prévio a respeito do conjunto de dados. O resultado do agrupamento é, então, utilizado para rotulação do restante do conjunto. Em seguida, entram em ação algoritmos de aprendizado supervisionado que tem como objetivo gerar regras fuzzy. Este documento contém conceitos teóricos para compreensão da proposta de trabalho e uma discussão a respeito do contexto onde se encaixa a proposta. Alguns experimentos foram realizados a fim de mostrar que esta pode ser uma solução interessante para tarefas de aprendizado de máquina que encontram dificuldades devido à falta de informação disponível sobre dados.
24
De, Waal Elda. "The educator-learner relationship within the South African public school system :|ban educational-juridical perspective / Elda de Waal." Thesis, Potchefstroom University for Christian Higher Education, 2000. http://hdl.handle.net/10394/8616.
Full textAbstract:
Harming the dignity of the learner; refusing to hear his side of the story; neglecting to
help him retrieve his stolen property : such are the unfortunate occurrences at many
South African schools, and such are the experiences that have led to this research.
Dedicated educators sometimes default, leaving their wronged learners out m the cold.
The questions are therefore: • What causes this conduct of educators and why does it recur? • Is it ignorance of their legal position? • Is it insensitivity to common law principles and statutory provisions? • Is it sheer carelessness? Mindful of the introduction of the South African Constitution Act 108 of 1996, wh1ch
contains the long-awaited Bill of Fundamental Rights, this study has been undertaken
to give an educational-juridical perspective of the educator-learner relationship 1n
South African public schools by means of a literature study and an elementary legal
comparative study.
Various legal terms which influence the educator-learner relationship significantly are
defined.
In conjunction with the private law status of the learner, the position of the learner
within the school system, and the fundamental rights of the learner in the context of
the administration of justice are identified and dealt with in so far as they have any
bearing on the educator-learner relationship,
Moreover, the legal determinants of the educator-learner relationship and the
educator's duty of care are pinpointed to determine their significance in an
accountable, responsive and open educator-learner relationship,
A comparative school law perspective of the sources of school law, the duties and
responsibilities of educators, the fundamental rights and legal obligations of the
learner, the educator's duty of care, discipline and legal liability in England and Wales,
Canada, Japan, and South Africa is presented in terms of similarities and differences,
Attention is paid to the necessity of informing educators and learners concerning their
respective rights and duties, in order to develop accountable, responsive and open
educator-learner relationships in South African schools,Thesis (Ph.D.)--Potchefstroom University for Christian Higher Education, 2000
25
Castro, Pablo Alberto Dalbem de. "Um paradigma baseado em algoritmos genéticos para o aprendizado de regras Fuzzy." Universidade Federal de São Carlos, 2004. https://repositorio.ufscar.br/handle/ufscar/546.
Full textAbstract:
Made available in DSpace on 2016-06-02T19:06:08Z (GMT). No. of bitstreams: 1
656.pdf: 1176051 bytes, checksum: 79408472b8b3606bcf1eb1699d034a2e (MD5)
Previous issue date: 2004-05-24Financiadora de Estudos e Projetos
The construction of the knowledge base of fuzzy systems has been beneficited intensively from automatic methods that extract the necessary knowledge from data sets which represent examples of the problem. The evolutionary computation, especially genetic algorithms, has been the focus of a great number of researches that deal with the problem of automatic generation of knowledge bases as search and optimization processes using di erent approaches. This work presents a methodology to learn fuzzy rule bases from examples by means of Genetic Algorithms using the Pittsburgh approach. The methodology is composed of 2 stages. The first one is the genetic learning of rule base and the other one is the genetic optimization of the rule base previously obtained in order to exclude redundant and unnecessary rules. The first stage uses a Self Adaptive Genetic Algorithm, that changes dynamically the crossover and mutation rates ensuring genetic diversity and avoiding the premature convergence. The membership functions are defined previously by the fuzzy clustering algorithm FC-Means and remain fixed during all learning process. The application domain is multidimensional pattern classification, where the attributes and, sometimes, the class are fuzzy, so they are represented by linguistic values. The proposed methodology performance is evaluated by computational simulations on some real-world pattern classification problems. The tests focused the accuracy of generated fuzzy rules in di erent situations. The dynamic change of algorithm parameters showed that better results can be obtained and the use of don t care conditions allowed to generate a small number of comprehensible and compact rules.
A construção da base de conhecimento de sistemas fuzzy tem sido beneficiada intensamente por métodos automáticos que extraem o conhecimento necessário a partir de conjuntos de dados que representam exemplos do problema. A computação evolutiva, em particular os algoritmos genéticos, tem sido alvo de um grande número de pesquisas que tratam, usando abordagens variadas, a questão da geração automática da base de conhecimento de sistemas fuzzy como um processo de busca e otimização. Este trabalho apresenta uma metodologia para o aprendizado de bases de regras fuzzy a partir de exemplos por meio de Algoritmos Genéticos usando a abordagem Pittsburgh. A metodologia é composta por duas etapas. A primeira é a geração genética da base de regras e a segunda é a otimização genética da base de regras previamente obtida, a fim de eliminar regras redundantes e desnecessárias. A primeira etapa utiliza um algoritmo genético auto-adaptativo, que altera dinamicamente os valores das taxas de cruzamento e mutação, a fim de garantir diversidade genética na população e evitar convergência prematura. As funções de pertinência são previamente definidas pelo algoritmo de agrupamento fuzzy FC-Means e permanecem fixas durante todo o processo de aprendizado. O domínio da aplicação é a classificação de padrões multi-dimensionais, onde os atributos e, algumas vezes, as classes são fuzzy, portanto, representados por valores lingüísticos. O desempenho da metodologia proposta é avaliado por simulações computacionais em alguns problemas de classificação do mundo real. Os testes focaram a acuidade das bases de regras geradas em diferentes situações. A alteração dinâmica dos parâmetros do algoritmo mostrou que melhores resultados podem ser obtidos e o uso da condição de don t care permitiu gerar um reduzido n´umero de regras mais compreensíveis e compactas.
26
Pimenta, Adinovam Henriques de Macedo. "Geração genética de classificador fuzzy intervalar do tipo-2." Universidade Federal de São Carlos, 2009. https://repositorio.ufscar.br/handle/ufscar/444.
Full textAbstract:
Made available in DSpace on 2016-06-02T19:05:45Z (GMT). No. of bitstreams: 1
3199.pdf: 1902769 bytes, checksum: 95b9e8c5042bd6117bd75983a58966f6 (MD5)
Previous issue date: 2009-10-30Universidade Federal de Sao Carlos
The objective of this work is to study, expand and evaluate the use of interval type-2 fuzzy sets in the knowledge representation for fuzzy inference systems, specifically for fuzzy classifiers, as well as its automatic generation form data sets, by means of genetic algorithms. This work investigates the use of such sets focussing the issue of balance between the cost addition in representation and the gains in interpretability and accuracy, both deriving from the representation and processing complexity of interval type-2 fuzzy sets. With this intent, an evolutionary model composed of three stages was proposed and implemented. In the first stage the rule base is generated, in the second stage the data base is optimized and finally, the number of rules of the rule base obtained is optimized in the third stage. The model developed was evaluated using several benchmark data sets and the results obtained were compared with two other fuzzy classifiers, being one of them generated by the same model using type-1 fuzzy sets and the other one generated by the Wang&Mendel method. Statistical methods usually applied for comparisons in similar contexts demonstrated a significant improvement in the classification rates of the intervalar type-2 fuzzy set classifier generated by the proposed model, with relation to the other methods.
O objetivo deste trabalho é estudar, expandir e avaliar o uso de conjuntos fuzzy intervalares tipo-2 na representação do conhecimento em sistemas de inferência fuzzy, mais especificamente para os classificadores fuzzy, bem como sua geração automática a partir de conjuntos de dados, por meio de algoritmos genéticos. Esse trabalho investiga o uso de tais conjuntos com enfoque na questão de balanceamento entre o acréscimo de custo da representação e os ganhos em interpretabilidade e precisão, ambos decorrentes da complexidade de representação e processamento dos conjuntos fuzzy intervalares do tipo-2. Com este intuito, foi proposto e implementado um modelo evolutivo composto por três etapas. Na primeira etapa á gerada a base de regras, na segunda é otimizada a base de dados e, por fim, na terceira etapa o número de regras da base gerada é otimizado. O modelo desenvolvido foi avaliado em diversos conjuntos de dados benchmark e os resultados obtidos foram comparados com outros dois classificadores fuzzy, sendo um deles gerados pelo mesmo modelo, porém, utilizando conjuntos fuzzy do tipo-1 e, o outro, gerado pelo método de Wang&Mendel. Métodos estatísticos de comparação usualmente aplicados em contextos semelhantes mostraram aumento significativo na taxa de classificação do classificador fuzzy intervalar do tipo-2 gerado pelo modelo em relação aos outros dois classificadores utilizados para comparação.
27
Holm, Cyril. "F. A. Hayek's Critique of Legislation." Doctoral thesis, Uppsala universitet, Juridiska institutionen, 2014. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-236890.
Full textAbstract:
The dissertation concerns F. A. Hayek’s (1899–1992) critique of legislation. The purpose of the investigation is to clarify and assess that critique. I argue that there is in Hayek’s work a critique of legislation that is distinct from his well-known critique of social planning. Further that the main claim of this critique is what I refer to as Hayek’s legislation tenet, namely that legislation that aims to achieve specific aggregate results in complex orders of society will decrease the welfare level. The legislation tenet gains support; (i) from the welfare claim – according to which there is a positive correlation between the utilization of knowledge and the welfare level in society; (ii) from the dispersal of knowledge thesis – according to which the total knowledge of society is dispersed and not available to any one agency; and (iii) from the cultural evolution thesis – according to which evolutionary rules are more favorable to the utilization of knowledge in social cooperation than are legislative rules. More specifically, I argue that these form two lines of argument in support of the legislation tenet. One line of argument is based on the conjunction of the welfare claim and the dispersal of knowledge thesis. I argue that this line of argument is true. The other line of argument is based on the conjunction of the welfare claim and the cultural evolution thesis. I argue that this line of argument is false, mainly because the empirical work of political scientist Elinor Ostrom refutes it. Because the two lines of argument support the legislation tenet independently of each other, I argue that Hayek’s critique of legislation is true. In this dissertation, I further develop a legislative policy tool as based on the welfare claim and Hayek’s conception of coercion. I also consider Hayek’s idea that rules and law are instrumental in forging rational individual action and rational social orders, and turn to review this idea in light of the work of experimental economist Vernon Smith and economic historian Avner Greif. I find that Smith and Greif support this idea of Hayek’s, and I conjecture that it contributes to our understanding of Adam Smith’s notion of the invisible hand: It is rules – not an invisible hand – that prompt subjects to align individual and aggregate rationality in social interaction. Finally, I argue that Hayek’s critique is essentially utilitarian, as it is concerned with the negative welfare consequences of certain forms of legislation. And although it may appear that the dispersal of knowledge thesis will undermine the possibility of carrying out the utilitarian calculus, due to the lack of knowledge of the consequences of one’s actions – and therefore undermine the legislation tenet itself – I argue that the distinction between utilitarianism conceived as a method of deliberation and utilitarianism conceived as a criterion of correctness may be used to save Hayek’s critique from this objection.
28
Jun-Liang, Lin Raw, and 林俊良. "Efficient Generation of Simplified Fuzzy Rules and Continuation Verification of Fuzzy Rules." Thesis, 1998. http://ndltd.ncl.edu.tw/handle/84621614252951787323.
Full textAbstract:
碩士國立臺灣科技大學
電子工程技術研究所
86
In this thesis, we propose an efficiency fuzzy neural network system for generating simplified fuzzy rules. In the proposed fuzzy neural network system, the revision algorithms are successful in analyzing the distribution of input data andgenerating perfect simplified fuzzy rules from the concepts of the Back-Propagationand the Self-Organizing Map algorithms. These generated rules are fuzzy ruleswith constant consequences, besides, it is easy to be calculated and the computational load of its inference is not heavy. Also, the simulation of experiments show that the generation of simplified fuzzy rules is effective in the classification problems.Also, we present the concept of fuzzy rule continuation for the verification of fuzzy rule-based systems. Generally, the rules in rule-based systems might be inconsistency, such as redundant, subsumed, or conflict. The inconsistent rules will decrease the performance and cause an incorrect result for rule-based system. The concept of fuzzy rule continuation is that if fuzzy rules intersect between the antecedents of them, then the consequences of them should intersect too. That is, if these fuzzy rule-based systems are discontinuous, then they might be inconsistent systems that have some discontinuous fuzzy rules. In this thesis, this concept is applied to two examples and these simulation results show that the outputs of continuous fuzzy systems are better than these of discontinuous systems.
29
Hsu, Frank, and 許智豪. "Online Generation of Association Rules in Dynamic Databases." Thesis, 2000. http://ndltd.ncl.edu.tw/handle/98474207419010644579.
Full text
30
劉家銘. "Online Generation of Association Rules by Negative Correlation." Thesis, 2001. http://ndltd.ncl.edu.tw/handle/82169915037430124598.
Full text
31
Xu, Shi-Zhun, and 許時準. "Automatic generation of fuzzy control rules using machine learning methods." Thesis, 1994. http://ndltd.ncl.edu.tw/handle/98859464359220870178.
Full text
32
Hsu, Shih-Chun, and 許時準. "Automatic Generation of Fuzzy Control Rules Using Machine Learning Methods." Thesis, 1994. http://ndltd.ncl.edu.tw/handle/92786052098993771133.
Full textAbstract:
碩士國立臺灣大學
資訊工程研究所
82
This thesis presents a method for automatic generation of fuzzy control rules. Fuzzy control rules, which compose the the kernel of a fuzzy logic controller, represent the knowledge acquired from a human operator. In a complex environment with many input variables, the output may depend on some of the inputs. Moreover, each input may have a varying degree of influence on the output value. A good controller should focus on the important parameters while ignoring irrelevant ones. The ID3 algorithm is adopted to produce the initial estimate rules because it can select the most important input variables influencing the output. In addition to prioritizing relevant input variables, the ID3 algorithm can eliminate irrelevant inputs. The resulting decision tree from ID3 algorithm can be easily converted into IF-THEN type rules automatically. After the initial estimate rules are fuzzified, the back-propagation algorithm is adopted to tune the parameters of membership functions. Using the back-propagation algorithm have the advantage that the fuzzy rules are more adaptive even when the environment is dynamic. The proposed method can be applied to a variety of domains. In this work, nonlinear system identification and mobile robot control were used in the experiments. The experiment results were satisfactory.
33
Johnson, Christopher Wayne. "Mechanical generation of concrete syntax rules for the Schütz semantic editor." Thesis, 2007. http://hdl.handle.net/10057/1141.
Full textAbstract:
Schütz is a programmer's editor designed by Dr. Rodney Bates. Through its language definition language, users may adapt Schütz to any programming language. Describing a programming language in the language definition language involves writing largely parallel rule sets in three different syntaxes—the concrete syntax, the abstract syntax, and the format syntax. In this thesis, we present a method for mechanically generating the concrete syntax rule set, given the rule sets of the other two syntaxes; we also prove that the concrete syntax rule sets thus generated are correct and unambiguous, given the same traits in the rule sets of the other two syntaxes.Thesis (M.S.)--Wichita State University, College of Liberal Arts and Sciences, Dept. of Computer Science
34
Lin, Fu-Tyan, and 林富田. "A Fuzzy Neural Network Model for Fuzzy Rules Verification, Refinement and Generation." Thesis, 1995. http://ndltd.ncl.edu.tw/handle/09568554229051504394.
Full textAbstract:
碩士國立臺灣科技大學
工程技術研究所
83
In this thesis, a fuzzy neural network, named Knowledge-Based Neural Network with Trapezoid Fuzzy inputs (KBNN/TFS), that processes trapezoid fuzzy inputs is proposed. In addition to fuzzy rules refinement, this model is capable of fuzzy rule verification and generation. The system architecture of the proposed model is based on our previous work, Knowledge-Based Fuzzy Neural Network (KBFNN). To facilitate the processing of fuzzy information, LR-fuzzy interval is employed. The proposed model provides an easy way for linking neural networks and fuzzy rules. Imperfect domain theories can be directly translated into KBNN/TFS structure. In KBNN/TFS, G-neurons are used to represent the output and intermediate fuzzy concepts, whereas S-neurons are used to perform the conjunction of the antecedents of fuzzy rules. Fuzzy weights are used to stand for the value of fuzzy variables. The imperfect fuzzy rules are revised by neural learning. A consistency checking algorithm is proposed for verifying the initial knowledge and the revised fuzzy rules. The algorithm is aimed at finding the redundant rules, conflicting rules and subsumed rules in fuzzy rule base.
35
Yang, Kung, and 楊洸. "An Approximation Reasoning Approach for Generating Fuzzy Decision Rules." Thesis, 1999. http://ndltd.ncl.edu.tw/handle/86110227192570464543.
Full textAbstract:
碩士國立臺灣師範大學
資訊教育研究所
87
Most fuzzy classification systems proposed before applied a crisp-cut approach on the fuzzy degrees of the fuzzy attributes and conclusions to generate decision rules. Although, by the crisp-cut approach, decision rules with conjunction-disjunction form can be derived from training-samples, the membership functions of the conclusions cannot be generated. In this paper, a learning method named Fuzzy Approximation Reasoning Method is proposed. Two requirements can be satisfied by the method：(1)deriving fuzzy decision rules with conjunction-disjunction form from training-samples, and (2)generating the membership functions for the conclusions. In Fuzzy Approximation Reasoning Method, the dependency-degree function is designed for estimating the relationship between a conclusion and the fuzzy attributes. For the fuzzy attributes related to the conclusion, their membership functions will be combined to construct the membership function of the conclusion such that the associated fuzzy decision rule is derived. Moreover, the Fuzzy Approximation Reasoning Method also can be used to mine fuzzy association rules. In this paper, the Approximation Inducing Method is proposed to demonstrate how to mine fuzzy association rules by applying the Fuzzy Approximation Reasoning Method.
36
Chang, Chi-Hao, and 張志豪. "New Methods for Generating Fuzzy Rules from Numerical Data." Thesis, 2001. http://ndltd.ncl.edu.tw/handle/62727720069770369894.
Full textAbstract:
碩士國立臺灣科技大學
電子工程系
89
The fuzzy classification system is an important application of the fuzzy set theory. Fuzzy classification systems can deal with perceptual uncertainties in classification problems. In order to design a fuzzy classification system, it is an important task to construct the membership function for each attribute and generate fuzzy rules from training instances for handling a specific classification problem. There are two approaches to construct the membership function for each attribute and generate fuzzy rules from training instances. One approach is based on human experts’ assistance, and the other approach is by applying machine learning techniques, such that the fuzzy classification system can construct membership functions and generate fuzzy rules from the training instances automatically. In recent years, many researchers have proposed different methods to construct membership functions and to generate fuzzy rules for handling fuzzy classification problems. However, there are some drawbacks in the existing methods: (1) Some existing methods need human experts to predefine initial membership functions, i.e., these methods can not construct membership functions from the training data set fully automatically. (2) Some existing methods are too complicated and need a lot of computation time. (3) Some existing methods generate too many fuzzy rules. In this thesis, we proposed two methods to construct the membership function for each attribute and to generate fuzzy rules automatically from training instances for handling fuzzy classification problems. The first method is based on the exclusion of attribute terms that can achieve a higher average classification accuracy rate and generate less fuzzy rules than the existing methods. The second method generates weighted fuzzy rules from training instances that can construct membership functions automatically without any human experts’ interaction and can generate less fuzzy rules than the existing methods.
37
Wu, Pei-Yun, and 吳珮芸. "An Efficient Generation of Candidate Itemsets and Count Algorithm for Mining Association Rules." Thesis, 2004. http://ndltd.ncl.edu.tw/handle/39905924144178640330.
Full textAbstract:
碩士國立高雄應用科技大學
電子與資訊工程研究所碩士班
92
Mining association rules from transaction databases is one of important techniques in data mining. Applications of association rules extend to discovering frequent patterns in consumer behavior, marketing analysis, electronic commerce and education, and other areas. In this thesis, we developed EGC, is an efficient algorithm for mining association rules. The main improvements are EGC uses an innovative method for generating candidate itemsets by checking the numbers of the preceding frequent itemsets before joining procedure. And EGC uses the simple tree data structure for storing the candidate itemsets and counting their supports. In addition, EGC uses the database global pruning method of DCP for efficiently reducing the size of the database. The experiments show that the performance of EGC is better than Apriori and DHP,IHPwoTTP, and IHPwTTP. The execution time and memory required of EGC are less than Apriori, DHP, IHPwoTTP, and IHPwTTP. In other applications, EGC can efficiently mine interesting information from investor databases to provide the optimal portfolio for each investor of the brokerage securities firm.
38
Yung-Chou and 陳勇洲. "New Methods for Generating Fuzzy Rules for Fuzzy Classification Systems." Thesis, 2001. http://ndltd.ncl.edu.tw/handle/59759052097981521421.
Full textAbstract:
碩士國立臺灣科技大學
電子工程系
89
The fuzzy classification system is an important application of the fuzzy set theory. The most important task to design fuzzy classification systems is to find a set of fuzzy rules from training data to deal with a specific classification problem. There are two main approaches to obtain the fuzzy rules of fuzzy classification systems. One of them is given by experts; the other is through an automatic learning process. In recent years, there are many method have been proposed to generate fuzzy rules from training instances for fuzzy classification systems. In this thesis, we proposed two new algorithms for generating fuzzy rules from training instances. We propose a new algorithm to generate weighted fuzzy rules from training data to deal with classification problems. Firstly, we convert the training data to fuzzy rules, and then we merge those fuzzy rules in order to reduce the number of fuzzy rules. Then, we calculate the weight of each input variable appearing in the generated fuzzy rules by the relationships of input variables. Then, we proposed another new algorithm to generate fuzzy rules using the genetic algorithm. Firstly, we divide the training data into several clusters and generate a fuzzy rule for each cluster. Then, we tune the membership functions of fuzzy rules by genetic algorithms. The proposed algorithms can get a higher average classification accuracy rate and generate less fuzzy rules than existing methods.
39
Li, Sin-Da, and 李信達. "A Bottom Up Algorithm for Mining Cross-Level Association Patterns without Redundant Rules Generation." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/65s577.
Full textAbstract:
碩士國立東華大學
資訊工程學系
95
Mining multilevel association rules is an interesting domain in data mining. However, the great parts of previous studies are devoted to mine at same level. By the way, many efficient associations will omit or the mined rules not perceive through the senses directly. Only a few works focus on mining cross level associations, and existing works still generate amount of redundant rules. In this thesis, we propose a bottom-up algorithm for mining cross-level association rules at multiple concept levels in large transaction database. Our algorithm, named ML-BottomUp, generates useful rules with high quality and none redundancy. Moreover, the similar rules are also been combined for generating efficient ones. A set of experiments is also performing to show the benefit of our approach.
40
Yeh, Ming-Shiow, and 葉明繡. "Generating Fuzzy Rules from Relational Database Systems for Fuzzy Information Retrieval." Thesis, 1995. http://ndltd.ncl.edu.tw/handle/17850078135325377817.
Full textAbstract:
碩士國立交通大學
資訊科學學系
83
In this thesis, we present a fuzzy concept learning system algorithm (FCLS) to construct fuzzy decision trees from relational database systems and to generate fuzzy rules from the constructed fuzzy decision trees. The completeness of the constructed fuzzy decision tree is alsodiscussed in details. Based on the generated fuzzy rules, we also present a method to forecast null values in relational database systems. Furthermore,we also made an experiment to compare the proposed FCLS algorithm with the existing methods for analyzing the ability of approximation ofreal-valued functions. The experiment result shows that the overall result of approximation of the FCLS algorithm is better than the existing methods,especially when f(x)=x/2. Furthermore, we also present a new clustering algorithm to deal with fuzzy query processing for database systems. Theproposed algorithm is more flexible and more efficient than the existing method due to the fact that the proposed algorithm has the following good features: (1) The number of clusters does not need to be predefined. (2) The ranges of fuzzy terms can dynamically be changed. (3) It does not need to perform complicated membership function calculations. (4) The speed of fuzzy query processing can be much faster.
41
余筱薇. "The SCORM Sequencing Rules Generation System and Multimedia Curricular Construction Using Template Based Authoring System." Thesis, 2006. http://ndltd.ncl.edu.tw/handle/93631764085995803291.
Full textAbstract:
碩士國立交通大學
資訊科學與工程研究所
94
In recent years, the multimedia presentation curriculums applying to teaching are getting widely available. To create interactive multimedia presentation documents, content creators such as school teachers who can use some multimedia authoring tools. However, to ensure the correctness of the multimedia presentations and interaction, teachers need to know some logic of programming. In other words, creating a multimedia curriculum requires a great deal of time and good computer literacy for teachers. Unfortunately, not every teacher has the background of programming. Undoubtedly, it is a hard job for most teachers to construct perfect multimedia curriculums. Due to the highly demand for multimedia curriculums, a wide variety of multimedia authoring tools are springing up one after another. However, multimedia curriculums made by different authoring tools have different standards, which results in reducing the interoperability of curriculums. For this reason, the American organization ADL (Advanced Distributed Learning) exerts a structured adaptive effort to develop the standards, tools and learning content for the learning environment. The standard is named SCORM (Sharable Course Object Reference Model) which provides a comprehensive suite of e-learning capabilities to enhance the interoperability, accessibility and reusability of learning content. Still, the rules of SCORM are very complex. There is a very high threshold for content creators to construct a multimedia curriculum conforming to SCORM. In this thesis, the two difficulties described above are solved. Our goals are to decrease the effort needed to create multimedia curriculums and to make the curriculums conform SCORM standard easily. Therefore, this thesis proposes the concept of "Multimedia Curriculum Template" for content creators. This topic is discussed in two main dimensions: "Multimedia Curriculum Template Construction" and "Multimedia Curriculum Template Imitating". This thesis analyzes the process of constructing multimedia curriculums, abstracts the repetition in the operation to form multimedia curriculum templates, and gives definitions of different classifications of these templates. According to the structure of multimedia curriculum, several levels of multimedia curriculum template's imitating are discussed, such as scene level, SCO level, and content organization level imitating. These different levels of templates enable content creators to compose a multimedia curriculum much more easily and efficiently. In order to reach the goal of improving the interoperability of learning content, this thesis discusses the definition of learning strategy based on SCORM sequencing rules and proposes the template of content organization and learning strategy. Without the need to know the detailed standard of SCORM, content creators will have no troubles using the templates to edit the learning strategy of multimedia curriculums and make the multimedia curriculum meet SCORM 100%.
42
Lin, Hao-Lin, and 林皓琳. "Generating Weighted Fuzzy Rules from Training Data for Handling Fuzzy Classification Problems." Thesis, 2001. http://ndltd.ncl.edu.tw/handle/22523933145504773247.
Full textAbstract:
碩士國立臺灣科技大學
電子工程系
89
In recent years, many methods have been proposed to generate fuzzy rules from training data. In this thesis, we present a new algorithm (FRG) to generate weighted fuzzy rules from a set of training data, where the attributes appearing in the antecedent parts of the generated fuzzy rules may have different weights. We apply the generated weighted fuzzy rules to deal with the “Saturday Morning Problem”, where the proposed FRG algorithm can get a higher average classification accuracy rate and generate less fuzzy rules than the existing methods. Then, based on the genetic algorithm, we propose a new method consists of the FRG algorithm to tune the weights of the attributes appearing in the generated fuzzy rules for generating weighted fuzzy rules. We also apply the generated weighted fuzzy rules to deal with the Iris data classification problem. The proposed method can obtain a higher average classification accuracy rate and generate less fuzzy rules than the existing methods.
43
林育賢. "Auto generating fuzzy rules and membership function with evolvable hardware image filter." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/83786918209197576207.
Full textAbstract:
碩士國立高雄大學
電機工程學系碩博士班
105
Evolvable hardware (EHW), which is a combination of reconfigurable hardware and evolutionary algorithm, is an emerging research topic.Recent studies show that the integration of fuzzy theory and EHW demonstrates effectiveness on digital image filtering.However, in these studies fuzzy rules and membership functions are defined heuristically. Their performance on filtering a variety of types of image noise is limited. %% In this study, similarity and divergence of image pixels are analyzed and used for clustering.Each cluster is defined as a fuzzy classification rule.The belongingness of pixels to a cluster describes a model of fuzzy membership function in terms of similarity and divergence. %% A clustering-based incremental algorithm is developed for generating fuzzy rules and membership functions from a given set of image pixels.With each fuzzy classification rule, an EHW-based image filter is learned and used for filtering the pixels classified by the fuzzy rule.Because fuzzy rules are learned from image pixels, not defined statically, our proposed method can have better performance on processing noisy pixels with the correct circuits. %% In this study, the performance of our proposed method is compared with other ones.The experimental results show that our proposed method outperforms traditional methods on image filtering.\\
44
HU, DA-WEI, and 胡大偉. "A retargetable code generator using pattern-matching rules derived from peephole optimization." Thesis, 1991. http://ndltd.ncl.edu.tw/handle/35305201659476132042.
Full text
45
Tsai, Fu-Ming, and 蔡富名. "New Methods for Constructing Membership Functions and Generating Fuzzy Rules from Training Instances." Thesis, 2003. http://ndltd.ncl.edu.tw/handle/24396568981428727510.
Full textAbstract:
碩士國立臺灣科技大學
電子工程系
91
In recent years, many researchers construct fuzzy classification systems to deal with fuzzy classification problems. A fuzzy classification system uses the knowledge base consist of many fuzzy rules to deal with fuzzy classification problem. The most important task when developing a fuzzy classification system is to construct a knowledge base containing fuzzy rules. There are two approaches to obtain fuzzy rules in fuzzy classification systems. One of them is given directly by domain experts; the other is obtained through a machine learning process. In this thesis, we proposed two methods for constructing membership functions and generating fuzzy rules from training instances for handling fuzzy classification problems. The first method chooses important attribute terms and based on the attribute threshold value, the classification threshold value, and the level threshold to construct membership functions and generate fuzzy rule. This method can get a higher average classification accuracy rate than the existing methods. The second method chooses important attribute terms, constructs membership functions and generates fuzzy rules by using maximum attribute value, minimum attribute value, and average attribute value of each attribute of the training instance. This method can generate fewer fuzzy rules than the existing methods.
46
Kao, Cheng-Hsuan, and 高正烜. "A New Method for Generating Fuzzy Rules and Constructing Membership Functions from Training Data Containing Noise." Thesis, 2000. http://ndltd.ncl.edu.tw/handle/56120466495488481798.
Full textAbstract:
碩士國立臺灣科技大學
電子工程系
88
The Fuzzy classification system is an important application of fuzzy logic. In a fuzzy classification system, objects can be classified properly by a fuzzy rule base. Fuzzy rules have been used as a tool to express knowledge in fuzzy logic, and they are more advantagous than the traditional IF-THEN rules. Fuzzy classification systems can properly deal with uncertainties and vagueness of the data involved in classification problems. One of important tasks in a fuzzy system is to find out a set of rules to deal with a specific classification problem. Usually we have two ways to do this task. One of them is to get knowledge from experts and to transfer it to fuzzy rules. However, the disadvantage of this way is that it is more difficult and needs more time for knowledge acquisition and validation. The other way is to use machine-learning methods, where fuzzy rules are generated from training data automatically. In recent years, there are many researchers focused on the research topic of generating fuzzy rules from training data for handling classification problems. In this thesis, we present a new algorithm to generate fuzzy rules from training data containing noise to deal with classification problems. The proposed algorithm can get a higher classification accuracy rate and generate less fuzzy rules and less input attributes in the antecedent portions of the generated fuzzy rules.
47
De, Kock Erika. "Decentralising the codification of rules in a decision support expert knowledge base." Diss., 2004. http://hdl.handle.net/2263/22959.
Full textAbstract:
The paradigm of Decision Support Systems (DSS) is to support decision-making, while an Expert System’s (ES) major objective is to provide expert advice in specialised situations. Knowledge-Based DSS (KB-DSS), also called Intelligent Decision Support Systems (IDSS), integrate traditional DSS with the advances of ES. A KB-DSS’ knowledge base usually contains knowledge expressed by an expert and captured by a knowledge engineer. The indirect transfer between the domain expert and the knowledge base through a knowledge engineer may lead to a long and inefficient knowledge acquisition process. This thesis compares 11 DSS packages in search of a (KB-) DSS generator where domain experts can specify and maintain a Specific Decision Support System (SDSS) to assist users in making decisions. The proposed (KB-) DSS-generator is tested with a university and study-program prototype. Since course and study plan programs change intermittently, the (KB-) DSS’ knowledge base enables domain experts to set and maintain their course and study plan rules without the assistance of a knowledge engineer. Criteria are set to govern the (KB-) DSS generator search process. Example knowledge base rules are inspected to determine if domain experts will be able to maintain a set of production rules used in a student registration advice system. By developing a prototype and inspecting knowledge base rules, it was found that domain experts would be able to maintain their knowledge in the decentralised knowledge base, on condition that the objects and attributes used in the rule base were first specified by a builder/programmer.Dissertation (MSc Computer Science)--University of Pretoria, 2005.
Computer Science
unrestricted
48
Pereira, Carlos António Senra. "Modelação e prototipagem de ChatBots." Master's thesis, 2018. http://hdl.handle.net/1822/65020.
Full textAbstract:
Relatório de estágio de mestrado em Matemática e ComputaçãoGenericamente, ChatBots são programas que interagem com utilizadores humanos através de linguagens naturais. Os ChatBots podem ser criados com objetivos muito diversos, como por exemplo manter uma conversa “inteligente” com um humano, ou prestar serviços em algum domínio concreto, como seja atender chamadas num call-center, reencaminhado-as para um operador. Dada a heterogeneidade dos ChatBots, é importante identificar os seus princípios gerais de organização e de funcionamento. Neste trabalho foi desenvolvida uma proposta original de modelação de ChatBots, que procura identificar estes princípios gerais. Na modelação que desenvolvemos, os ChatBots são organizados em três componentes principais: a interface com o utilizador, o núcleo e o estado do ChatBot. O núcleo é a peça central do funcionamento do Chatbot, pois ele é responsável por processar as interações recebidas do utilizador, gerando reações em resposta. O núcleo contém um conjunto de regras que associam funções de reação a padrões linguísticos que, juntamente com o estado do ChatBot, determinam a escolha da reação a uma dada interação do utilizador. Para a modelação de padrões linguísticos, desenvolvemos aquilo que designamos por expressões regulares linguísticas (ERL). As ERL baseiam-se em expressões regulares, envolvendo etiquetas gramaticais, e incluem um mecanismo para extração das palavras-chave de um padrão linguístico, e deram origem a uma Domain Specific Language. A modelação que desenvolvemos permite a criação de um motor geral para a construção de ChatBots. Para uma prova de conceito, foi criado o Diabrete: um motor geral, open-source, escrito em Python, versão 3, com a base de dados em MySQL, que permite a criação de ChatBots que seguem a modelação desenvolvida neste trabalho. Na implementação do Diabrete recorremos a algumas ferramentas opensource, para levar a cabo as tarefas da análise sintática das frases dos utilizadores (biblioteca FreeLing) e para a construção de um classificador baseado em técnicas de machine learning para a escolha da reação a apresentar a uma dada interação do utilizador (biblioteca NLTK).
ChatBots are programs that interact with human users through natural languages. ChatBots can be created for very different purposes, such as maintaining an ”inteligent”conversation with a human, or providing services in a specific domain, such as answering calls in a call-center, and forward them to an operator. Given the heterogeneity of ChatBots, it becomes important to identify their general principles of organization and operation. In this work, we identify some of these general principles, and develop a new proposal for the modeling of ChatBots. In the developed model, ChatBots are organized into three main components: the user interface, the core of the ChatBot, and the state of the ChatBot. The core is the centerpiece of Chatbot’s operation, as it is responsible for processing the interactions received from the user, generating reactions in response. The core contains a set of rules that associates reaction functions with linguistic patterns that, together with the state of the ChatBot, determine the choice of reaction to a given user interaction. For modeling linguistic patterns, we develop what we call regular linguistic expressions (ERL). ERLs are based on regular expressions involving grammatical tags, include a mechanism for extracting the keywords from a linguistic standard, and have given rise to a Domain Specific Language. The model that we developed allows the design of a general generator for the construction of ChatBots. For a proof of concept, the Diabrete was created. Diabrete is a general, open-source generator, written in Python, version 3, with the database in MySQL, which allows the construction of ChatBots that follow the modeling developed in this work. In the implementation of Diabrete, we used some opensource tools to perform the tasks of the user-generated sentences (library FreeLing) and to construct a classifier based on machine learning techniques for the choice of reaction to be presented to a given user interaction (library NLTK).