The Web turns out to be a collection of services that interoperate through the Internet. As the number of services increase, it is getting more and more diffucult for users to find, filter and integrate these services depending on their requirements. Automatic techniques are being developed to fulfill these tasks. The first step toward automatic composition is the discovery of services needed. UDDI which is one of the accepted web standards, provides a registry of web services. However representation capabilities of UDDI are insufficient to search for services on the basis of what they provide. Semantic web initiatives like OWL and OWL-S are promising for locating exact services based on their capabilities. In this thesis, a new semantic service discovery mechanism is implemented based on OWL-S service profiles. The service profiles of an advertisement and a request are matched based on OWL ontologies describing them. In contrast to previous work on the subject, the ontologies of the advertisement and the request are not assumed to be same. In case they are different, schema matching algorithms are applied. Schema matching algorithms find the mappings between the given schema models. A hybrid combination of semantic, syntactic and structural schema matching algorithms are applied to match ontologies

Peculiar data are regarded as patterns which are significantly distinguishable from other records, relatively few in number and they are accepted as to be one of the most striking aspects of the interestingness concept. In clinical domain, peculiar records are probably signals for malignancy or disorder to be intervened immediately. The investigation of the rules and mechanisms which lie behind these records will be a meaningful contribution for improved clinical decision support systems. In order to discover the most interesting records and patterns, many peculiarity oriented interestingness measures, each fulfilling a specific requirement, have been developed. In this thesis well-known peculiarity oriented interestingness measures, Local Outlier Factor (LOF), Cluster Based Local Outlier Factor (CBLOF) and Record Peculiar Factor (RPF) are compared. The insights derived from the theoretical infrastructures of the algorithms were evaluated by using experiments on synthetic and real world medical data. The results are discussed based on the interestingness perspective and some departure points for building a more developed methodology for knowledge discovery in databases are proposed.

Since the initial genome sequencing projects along with the recent advances on technology, molecular biology and large scale transcriptome analysis result in data accumulation at a large scale. These data have been provided in different platforms and come from different laboratories therefore, there is a need for compilation and comprehensive analysis. In this thesis, we addressed the automatization of biological data acquisition and integration from these non-uniform data using machine learning techniques. We focused on two different mining studies in the scope of this thesis. In the first study, we worked on characterizing expression patterns of housekeeping genes. We described methodologies to compare measures of housekeeping genes with non-housekeeping genes. In the second study, we proposed a novel framework, bi-k-bi clustering, for finding association rules of gene pairs that can easily operate on large scale and multiple heterogeneous data sets. Results in both studies showed consistency and relatedness with the available literature. Furthermore, our results provided some novel insights waiting to be experimented by the biologists.

The managing of complex business processes, which are changed due to globalization, calls for the development of powerful information systems that offer generic process modeling and process execution capabilities. Even though contemporary information systems are more and more utilized in enterprises, their actual impact in automatizing complex business process is still limited by the difficulties encountered in design phase. Actually this design phase is time consuming, often subjective and incomplete. In the scope of this study, a reverse approach is followed. Instead of starting with process design, the method of discovering interesting patterns from the navigation traces is taken as basis and a new data analysis methodology named &ldquo / From-to Chart Based Process Discovery&rdquo / is proposed. In this hybrid methodology &ldquo / from-to chart&rdquo / , which is fundamentally dedicated to material handling issues on production floor, is used as the front-end to monitor the transitions among activities of a realistic event log and convert these raw relations into optimum activity sequence. Then a revised version of process mining, which is the back-end of this methodology, upgrades optimum activity sequence into process model.

Multi Relational Data Mining has become popular due to the limitations of propositional problem definition in structured domains and the tendency of storing data in relational databases. However, as patterns involve multiple relations, the search space of possible hypothesis becomes intractably complex. In order to cope with this problem, several relational knowledge discovery systems have been developed employing various search strategies, heuristics and language pattern limitations. In this thesis, Inductive Logic Programming (ILP) based concept discovery is studied and two systems based on a hybrid methodology employing ILP and APRIORI, namely Confidence-based Concept Discovery and Concept Rule Induction System, are proposed. In Confidence-based Concept Discovery and Concept Rule Induction System, the main aim is to relax the strong declarative biases and user-defined specifications. Moreover, this new method directly works on relational databases. In addition to this, the traditional definition of confidence from relational database perspective is modified to express Closed World Assumption in first-order logic. A new confidence-based pruning method based on the improved definition is applied in the APRIORI lattice. Moreover, a new hypothesis evaluation criterion is used for expressing the quality of patterns in the search space. In addition to this, in Concept Rule Induction System, the constructed rule quality is further improved by using an improved generalization metod. Finally, a set of experiments are conducted on real-world problems to evaluate the performance of the proposed method with similar systems in terms of support and confidence.

Web Service technology is one of the most rapidly developing contemporary technologies. Nowadays, Web Services are being used by a large number of projects and academic studies all over the world. As the use of Web service technology is increasing, it becomes harder to find the most suitable web service which meets the Quality of Service (QoS) as well as functional requirements of the user. In addition, quality of the web services (QoS) that take part in the software system becomes very important. In this thesis, we develop a method to track the QoS primitives of Web Services and an algorithm to automatically calculate QoS values for Web Services. The proposed method is realized within a domain specific web service discovery system, namely DSWSD-S, Domain Specific Web Service Discovery with Semantics. This system searches the Internet and finds web services that are related to a domain and calculates QoS values through some parameters. When a web service is queried, our system returns suitable web services with their QoS values. How to calculate, keep track of and store QoS values constitute the main part of this study.

GWAS mainly aim to identify variations associated with certain phenotypes or diseases. Recently the combined p-value approach is described as the next step after GWAS to map the significant SNPs to genes and pathways to evaluate SNP-gene-disease associations. Major bottleneck of standard GWAS approaches is the prioritization of statistically significant results. The connection between statistical analysis and biological relevance should be established to understand the underlying molecular mechanisms of diseases. There are few tools offered for SNP prioritization but these are mainly based on user-defined subjective parameters, which are hard to standardize. Our group has recently developed a novel AHP based SNP prioritization algorithm. Beside statistical association AHP based SNP prioritization algorithm scores SNPs according to their biological relevance in terms of genomic location, functional consequence, evolutionary conservation, and gene-disease association. This allows researchers to evaluate the significantly associated SNPs quickly and objectively. Here, we have investigated the performance of the AHP based prioritization as the next step in the utilization of the algorithm in comparison to the other available tools for SNP prioritization. The user-defined parameters for AHP based prioritization have been investigated and our suggestion on how to use these parameters are presented. Additionally, the GWAS results from the analysis of two different sets of Alzheimer Disease Genotyping data with the newly proposed AHP based prioritization and the integrated software, METU-SNP, it was implemented, is reported and our new findings on the association of SNPs and genes with AD based on this analysis is discussed.

Unique column combinations of a relational database table are sets of columns that contain only unique values. Discovering such combinations is a fundamental research problem and has many different data management and knowledge discovery applications. Existing discovery algorithms are either brute force or have a high memory load and can thus be applied only to small datasets or samples. In this paper, the wellknown GORDIAN algorithm and "Apriori-based" algorithms are compared and analyzed for further optimization. We greatly improve the Apriori algorithms through efficient candidate generation and statistics-based pruning methods. A hybrid solution HCAGORDIAN combines the advantages of GORDIAN and our new algorithm HCA, and it significantly outperforms all previous work in many situations. / Unique-Spaltenkombinationen sind Spaltenkombinationen einer Datenbanktabelle, die nur einzigartige Werte beinhalten. Das Finden von Unique-Spaltenkombinationen spielt sowohl eine wichtige Rolle im Bereich der Grundlagenforschung von Informationssystemen als auch in Anwendungsgebieten wie dem Datenmanagement und der Erkenntnisgewinnung aus Datenbeständen. Vorhandene Algorithmen, die dieses Problem angehen, sind entweder Brute-Force oder benötigen zu viel Hauptspeicher. Deshalb können diese Algorithmen nur auf kleine Datenmengen angewendet werden. In dieser Arbeit werden der bekannte GORDIAN-Algorithmus und Apriori-basierte Algorithmen zum Zwecke weiterer Optimierung analysiert. Wir verbessern die Apriori Algorithmen durch eine effiziente Kandidatengenerierung und Heuristikbasierten Kandidatenfilter. Eine Hybride Lösung, HCA-GORDIAN, kombiniert die Vorteile von GORDIAN und unserem neuen Algorithmus HCA, welche die bisherigen Algorithmen hinsichtlich der Effizienz in vielen Situationen übertrifft.

Syftet med denna studie är att undersöka specialpedagogers tankar kring hur förskolans arbetssätt kan anpassas för att ge stöd till barn som far illa och underlätta tidig upptäckt. Som metod har semistrukturerad intervju använts. Sex specialpedagoger med grundutbildning som förskollärare deltog. Som hjälpmedel användes fallbeskrivningar att reflektera kring och resonera om. Studien visar att specialpedagogerna i undersökningen anser att förskolan spelar en viktig roll för barn som far illa och deras utveckling. Personalens förhållningssätt till barnen och deras föräldrar är avgörande för att skapa goda relationer. Studien visar även att anmälningsfrekvensen i förskolan när det gäller barn som far illa är låg. Vanliga anledningar till detta är obehagskänsla och bristande kunskap hos personalen. Förskolepersonal har stora möjligheter att upptäcka barn som far illa och de har anmälningsskyldighet. Från specialpedagogers och övrig förskolepersonals sida finns ofta ett missnöje med samverkan med socialtjänsten, och man önskar att denna skulle kunna förbättras. Samverkan ökar kunskap och underlättar för arbete med barn och familj. / The aim of this study is to investigate special educators’ thoughts about how the work of preschool can be adjusted to give support to mistreated children and facilitate early discovery. A semi-structured interview has been used as method. Six special educators with preschool teaching as a basic education participated. Case reports to reflect and reason around were used as tools. The study shows that the special educators consider that the preschool plays a big part for mistreated children and their development. The staffs´ approach to children and their parents is essential to create good relations.

One type of instruction that is of particular interest in STEM education is instruction that actively engages students in inquiry and discovery. The author develops an operational definition of instruction for discovery learning (IDL) that adopts some of the fundamental commonalities among many reform-oriented instructional frameworks such as inquiry-based and project-based instruction. Four teachers—who received their bachelor’s degree in mathematics and teacher certification from the same undergraduate teacher-preparation program—and their Algebra I classes were observed with the focus on how particular features of IDL were being implemented in their classrooms. To gain further perspective on classroom practices and interactions, student surveys were administered to a total of 142 students and each teacher was interviewed. The student surveys focused on student orientations toward IDL, attitudes toward mathematics, and their perspective of IDL implementation in their class. Student survey data was analyzed through ANOVA, post hoc tests were used to identify significant pair-wise differences between teachers for which the ANOVA identified significance, and a factor analysis was used to evaluate the component loadings for the survey questions. The surveys revealed significant differences between perceived activities in the classes (p<0.05), but did not show very significant differences between student orientations toward IDL. All four teachers expressed familiarity with and commitment to reform-oriented frameworks such as inquiry-based and project-based instruction, and certainly experienced inquiry-based learning as students themselves in their undergraduate program. However, only one teacher—the one teaching in a New Tech high school that was structured on the framework of project-based instruction (PBI)—showed consistent differences in both student perspectives of IDL and observed implementation of IDL. The author discusses the levels at which these teachers implemented IDL, the differences among student perceptions across the classes, teacher orientations toward mathematics and learning, and the importance of a supportive school culture and administration in order to fully implement IDL and influence both student and teacher orientations toward reform-oriented pedagogy. / text