(in English): The thesis is devoted to the comparison of a few methods of mining knowledge from data. Methods decision tree, classification rules, cluster analysis, and Naive Bayes classifier were applied to the data sample. Data about clients of a non-profit organization Association of Civil Counseling were used. It has been worked according to the technological process of knowledge mining. In the thesis was applied data description, data preparation, modeling and testing and results from interpretation. Because of using the same sample of data and similar data preparation, overlapping results are also expected. The research is focused not only on results similarity, but also differences in results. The correlation between the amount of debt of clients and other attributes was found. In the results, there really were some patterns repeating through most of all methods. It turned out the amount of debt is related to a number of creditors. The more creditors, the higher amount of debt. Clients with a higher amount of liabilities had also higher debt. The results might not be surprising, but it proves the functionality of models and comparability of results.

Sjökaptensstudenterna på Sjöfartshögskolan i Kalmar har i sin utbildningsplan tolv månaders fartygsförlagd utbildning som är fördelad över tre perioder. Praktiken erbjuder studenterna möjligheten att utöva samt utveckla den teoretiska kunskapen de lärt sig i skolan men även att få uppleva hur det verkligen är att arbeta till sjöss. Arbetsmiljön, den sociala miljön samt hur det är att vara hemifrån under en längre period är saker som studenterna får prova på. Att arbeta till sjöss har många fördelar men även sin utmaningar. Det är ett arbete med hög arbetsbelastning samt höga krav på organisationen ombord, säkerheten och miljömedvetande. Som sjöbefälsstudent på Sjöfartshögskolan i Kalmar hamnar man i denna miljö under sitt första år på utbildningen då man under termin ett åker ut på första praktikperioden. Denna studie syftar till att undersöka hur sjökaptensstudenterna upplever att sömnbrist, kontraktslängd samt arbetstiderna ombord påverkar deras kunskapsinhämtande. För att ta reda på studenternas upplevelser har en kvalitativ intervjustudie genomförts med sex sjökaptensstudenter; endast sistaårsstudenter intervjuades då de genomgått hela eller en stor del av den fartygsförlagda utbildningen och ansågs därför ha mest erfarenhet. Svaren var i de flesta fallen överensstämmande där studenterna upplevde att praktikperioderna samt arbetsdagarna var för långa, att man behövde ha minst en vilodag i veckan och att sömnbrist hade en negativ inverkan på deras kunskapsinhämtande. Samtidigt framkom det i studien vad som vore det mest optimala för sjöbefälstudenternas kunskapsinhämtande, vad gäller optimal längd på praktikperioderna samt optimalt arbetsschema för en så givande och effektiv praktik som möjligt. / The master mariner students at Kalmar Maritime Academy have twelve months of ship-based training which is a part of the education plan, and these twelve months are distributed over three periods. The internship offers the students the opportunity to practice and develop the theoretical knowledge they have gained in school, but also to experience how it really is to work at sea. The work environment, the social environment and what it can be like to be away from home for a longer period are central. Working at sea has many benefits but also its challenges. The job is associated with long periods at sea with a high workload and high demands on the organization on board, as well as safety and environmental awareness. As a master mariner student at Kalmar Maritime Academy, you end up in this environment during your first year of education when you leave school for the first internship period during semester one. This study aims to investigate how master mariner students experience that lack of sleep, contract length and working hours on board affect their knowledge acquisition. To find out the students' experiences, a qualitative interview study was conducted with six master mariner students; only senior year students were interviewed because they had completed all or a large part of the ship-based training and were therefore considered to have the most experience. The answers were in most cases consistent where the students felt that the internship periods and working days were too long, that they needed to have at least one day off a week and that lack of sleep had a negative impact on their knowledge acquisition. At the same time, the study showed what would be the optimal for the master mariner students' knowledge acquisition, in terms of optimal length of internship periods and optimal work schedule for a rewarding and effective internship as possible.

Simulation training has been implemented at a small nursing school in the eastern United States to improve the currently low content exam scores in nursing courses. With the guidance of Kolb's experiential learning theory, differences in 8 course content exam scores were investigated for students who received simulation training in the content area before the exam and students who received simulation training after the exam, using a quasi-experimental, comparative design. Archival exam scores from 424 content exams, 212 completed by students who received simulation training before the exam and 212 completed by students who received simulation training after the exam, were used in a multivariate analysis of variance. The difference of the group means was not statistically significant (p = .69) for the pediatric assessment, meningitis, respiratory deviations, and gastrointestinal nursing content exams. However, there was a significant difference, F (4, 47) = 5.192, p = .00; λ = .694; η2 = .316, for the postpartum and neonatal assessment, preeclampsia, and cardiovascular nursing content exams. The results are split, which may be due to inconsistency in the conduct of simulation training across the 8 content areas. The varied outcomes led to the development of a white paper with policy and implementation recommendations for simulation training. Positive social change may occur in the planning of simulation training to promote consistency and best practices, enhancing students' ability to perform safely and competently at the patient's bedside and thus supporting improved patient outcomes.

This work investigates the effective acquisition of lexical knowledge from the Web to perform semantic interpretation. The Web provides an unprecedented amount of natural language from which to gain knowledge useful for semantic interpretation. The knowledge acquired is described as common sense knowledge, information one uses in his or her daily life to understand language and perception. Novel approaches are presented for both the acquisition of this knowledge and use of the knowledge in semantic interpretation algorithms. The goal is to increase accuracy over other automatic semantic interpretation systems, and in turn enable stronger real world applications such as machine translation, advanced Web search, sentiment analysis, and question answering. The major contributions of this dissertation consist of two methods of acquiring lexical knowledge from the Web, namely a database of common sense knowledge and Web selectors. The first method is a framework for acquiring a database of concept relationships. To acquire this knowledge, relationships between nouns are found on the Web and analyzed over WordNet using information-theory, producing information about concepts rather than ambiguous words. For the second contribution, words called Web selectors are retrieved which take the place of an instance of a target word in its local context. The selectors serve for the system to learn the types of concepts that the sense of a target word should be similar. Web selectors are acquired dynamically as part of a semantic interpretation algorithm, while the relationships in the database are useful to iii stand-alone programs. A final contribution of this dissertation concerns a novel semantic similarity measure and an evaluation of similarity and relatedness measures on tasks of concept similarity. Such tasks are useful when applying acquired knowledge to semantic interpretation. Applications to word sense disambiguation, an aspect of semantic interpretation, are used to evaluate the contributions. Disambiguation systems which utilize semantically annotated training data are considered supervised. The algorithms of this dissertation are considered minimallysupervised; they do not require training data created by humans, though they may use humancreated data sources. In the case of evaluating a database of common sense knowledge, integrating the knowledge into an existing minimally-supervised disambiguation system significantly improved results – a 20.5% error reduction. Similarly, the Web selectors disambiguation system, which acquires knowledge directly as part of the algorithm, achieved results comparable with top minimally-supervised systems, an F-score of 80.2% on a standard noun disambiguation task. This work enables the study of many subsequent related tasks for improving semantic interpretation and its application to real-world technologies. Other aspects of semantic interpretation, such as semantic role labeling could utilize the same methods presented here for word sense disambiguation. As the Web continues to grow, the capabilities of the systems in this dissertation are expected to increase. Although the Web selectors system achieves great results, a study in this dissertation shows likely improvements from acquiring more data. Furthermore, the methods for acquiring a database of common sense knowledge could be applied in a more exhaustive fashion for other types of common sense knowledge. Finally, perhaps the greatest benefits from this work will come from the enabling of real world technologies that utilize semantic interpretation.

We describe the automatic acquisition of a semantic network in which over 7,500 of the most frequently occurring nouns in the English language are linked to their semantically related concepts in the WordNet noun ontology. Relatedness between nouns is discovered automatically from lexical co-occurrence in Wikipedia texts using a novel adaptation of an information theoretic inspired measure. Our algorithm then capitalizes on salient sense clustering among these semantic associates to automatically disambiguate them to their corresponding WordNet noun senses (i.e., concepts). The resultant concept-to-concept associations, stemming from 7,593 target nouns, with 17,104 distinct senses among them, constitute a large-scale semantic network with 208,832 undirected edges between related concepts. Our work can thus be conceived of as augmenting the WordNet noun ontology with RelatedTo links. The network, which we refer to as the Szumlanski-Gomez Network (SGN), has been subjected to a variety of evaluative measures, including manual inspection by human judges and quantitative comparison to gold standard data for semantic relatedness measurements. We have also evaluated the network’s performance in an applied setting on a word sense disambiguation (WSD) task in which the network served as a knowledge source for established graph-based spreading activation algorithms, and have shown: a) the network is competitive with WordNet when used as a stand-alone knowledge source for WSD, b) combining our network with WordNet achieves disambiguation results that exceed the performance of either resource individually, and c) our network outperforms a similar resource, WordNet++ (Ponzetto & Navigli, 2010), that has been automatically derived from annotations in the Wikipedia corpus. iii Finally, we present a study on human perceptions of relatedness. In our study, we elicited quantitative evaluations of semantic relatedness from human subjects using a variation of the classical methodology that Rubenstein and Goodenough (1965) employed to investigate human perceptions of semantic similarity. Judgments from individual subjects in our study exhibit high average correlation to the elicited relatedness means using leave-one-out sampling (r = 0.77, σ = 0.09, N = 73), although not as high as average human correlation in previous studies of similarity judgments, for which Resnik (1995) established an upper bound of r = 0.90 (σ = 0.07, N = 10). These results suggest that human perceptions of relatedness are less strictly constrained than evaluations of similarity, and establish a clearer expectation for what constitutes human-like performance by a computational measure of semantic relatedness. We also contrast the performance of a variety of similarity and relatedness measures on our dataset to their performance on similarity norms and introduce our own dataset as a supplementary evaluative standard for relatedness measures.

No description available.

Då data som transporteras över trådlösa nätverk sänds genom luften i form av radiovågor är det viktigt att säkra upp nätverkskommunikationen med nya, erkändasäkerhetsstandarder. Däremot är användningsgraden av nyare säkerhetsstandarder inom Wi-Fi, specifikt WPA3 och PMF, låg. Samtidigt finns ett behov att öka förståelsen för relevanta metoder för kunskapsinhämtning. Syftet med studien är att ge rekommendationer för hur små och medelstora företag kan öka säkerheten i trådlösa nätverk. Studien identifierar orsaker till den låga användningsgraden av nyare säkerhetsstandarder i trådlösa nätverk och även hur nätverksadministratörer håller sig uppdaterade om standarderna. En kvalitativ ansats valdes för att besvara studiens syfte, vilket genomfördes med hjälp av 23 semi-strukturerade intervjuer med nätverksadministratörer i Sverige. Studiens resultat visar på ett tydligt tema där klientbasen i nätverken är huvudanledningen till avvaktandet med att implementera nyare säkerhetsstandarder, där kompabilitet upplevs som ett problem samtidigt som det råder okunskap om standarderna. Bland respondenterna anses metoden praktiskt laborerande vara mest effektiv för kunskapsinhämtning och fortbildning, ofta i samband med läsande av teori för att bilda en grundläggande förståelse. Studien landar i rekommendationer om de nyare säkerhetsstandarderna och kunskapsinhämtning riktade mot nätverksadministratörer, företag och även myndigheter och organisationer som bidrar med riktlinjer om trådlösa nätverk. / As data transmitted over wireless networks is sent through air, in the form of radio waves, it is important to secure network communication with new, recognized security standards. However, the adoption rate of newer security standards in Wi-Fi, specifically WPA3 and PMF, is low. At the same time, there is a need to increase understanding of relevant methods for knowledge acquisition. This study’s purpose is to provide recommendations on how small and medium-sized enterprises can increase the security of wireless networks. The study identifies reasons for the low adoption rate of newer security standards in wireless networks and how network administrators stay updated on the standards. A qualitative approach was chosen to address the study's purpose, which was conducted through 23 semi-structured interviews with network administrators in Sweden. The study's results reveal a clear theme where the client base in the networks is the main reason for reservations to implement newer security standards, with compatibility being perceived as a problem alongside a lack of knowledge about the standards. Among the respondents, practical experimentation is considered the most effective method for knowledge acquisition and continuous education, often combined with reading of theory to form a fundamental understanding. The study concludes with recommendations on the newer security standards and knowledge acquisition targeted towards network administrators, companies, as well as authorities and organizations that provide guidelines on wireless networks.

Description logics in their standard setting only allow for representing and reasoning with crisp knowledge without any degree of uncertainty. Of course, this is a serious shortcoming for use cases where it is impossible to perfectly determine the truth of a statement. For resolving this expressivity restriction, probabilistic variants of description logics have been introduced. Their model-theoretic semantics is built upon so-called probabilistic interpretations, that is, families of directed graphs the vertices and edges of which are labeled and for which there exists a probability measure on this graph family. Results of scientific experiments, e.g., in medicine, psychology, or biology, that are repeated several times can induce probabilistic interpretations in a natural way. In this document, we shall develop a suitable axiomatization technique for deducing terminological knowledge from the assertional data given in such probabilistic interpretations. More specifically, we consider a probabilistic variant of the description logic EL⊥, and provide a method for constructing a set of rules, so-called concept inclusions, from probabilistic interpretations in a sound and complete manner.

For a probabilistic extension of the description logic EL⊥, we consider the task of automatic acquisition of terminological knowledge from a given probabilistic interpretation. Basically, such a probabilistic interpretation is a family of directed graphs the vertices and edges of which are labeled, and where a discrete probabilitymeasure on this graph family is present. The goal is to derive so-called concept inclusions which are expressible in the considered probabilistic description logic and which hold true in the given probabilistic interpretation. A procedure for an appropriate axiomatization of such graph families is proposed and its soundness and completeness is justified.

To be able to make accurate predictions and adapt, we sometimes need to adjust our understanding of the world, yet what incentivizes expansion of our mental world models remains poorly understood. The aim of this study was to investigate what motivates people to update their world models – here referred to as the ontological model structure, and how updating is related to uncertainty. The study is of experimental design and uses a digital game divided into two conditions (ambiguous and unambiguous) that vary the expectations for the game’s causal structure. The goal of the game was to gain points by accurately predicting on what food item a fly will land. To make accurate predictions, the participant should adjust their cognitive model when encountering new information. Data from 84 participants was collected online, using Prolific.co. It was hypothesized that initial ambiguity would affect the likelihood of information seeking by increasing the frequency of prediction errors and would result in a faster switch to an optimal cognitive model. The study found that participants in the more ambiguous condition sought information earlier, gained more prediction errors and changed to an optimal model faster than participants in the less ambiguous condition. However, both participant groups seemed equally as equipped to change models as a result of prediction errors. This might indicate that despite similar support for an initial model, it is the prediction errors and our recent history that affects our tendency to adjust our cognitive models. / För att kunna göra korrekta prediktioner och anpassa oss behöver vi ibland justera vår förståelse av världen, vad som motiverar en revidering av våra mentala modeller är dock fortfarande oklart. Studiens syfte var att undersöka vad som motiverar människor att uppdatera sina modeller – benämnd här som den ontologiska modellstrukturen, och hur uppdateringen är relaterad till osäkerhet. Studien är av experimentell design och använder ett digitalt spel uppdelat i två betingelser (tvetydig och entydig), som varierar förväntningarna på spelets ontologiska struktur. Spelets mål var att samla poäng genom att korrekt predicera på vilken matvara en fluga kommer att landa. För att kunna göra korrekta prediktioner bör deltagaren justera sin kognitiva modell när ny information fås. Data från 84 deltagare samlades in online, med hjälp av Prolific.co. Det antogs att den initiala tvetydigheten skulle påverka sannolikheten för informationssökning genom att öka frekvensen av prediktionsfel och att det skulle resultera i en snabbare övergång till en optimal kognitiv modell. Studien fann att deltagare i den mer tvetydiga betingelsen sökte information tidigare, fick fler prediktionsfel och ändrade till en optimal modell snabbare än deltagare i den mindre tvetydiga betingelsen. Däremot verkade båda deltagargrupperna lika väl utrustade att byta modell till följd av prediktionsfel. Det kan tyda på att trots liknande stöd för en initialmodell är det prediktionsfel och vår närhistoria som påverkar vår tendens att justera våra kognitiva modeller.