‘If-then’ rule sets are one of the most expressive and human-readable knowledge representations. This thesis deals with optimization and analysis of decision and inhibitory rules for decision tables with many-valued decisions. The most important areas of applications are knowledge extraction and representation. The benefit of considering inhibitory rules is connected with the fact that in some situations they can describe more knowledge than the decision ones. Decision tables with many-valued decisions arise in combinatorial optimization, computational geometry, fault diagnosis, and especially under the processing of data sets. In this thesis, various examples of real-life problems are considered which help to understand the motivation of the investigation. We extend relatively simple results obtained earlier for decision rules over decision tables with many-valued decisions to the case of inhibitory rules. The behavior of Shannon functions (which characterize complexity of rule systems) is studied for finite and infinite information systems, for global and local approaches, and for decision and inhibitory rules. The extensions of dynamic programming for the study of decision rules over decision tables with single-valued decisions are generalized to the case of decision tables with many-valued decisions. These results are also extended to the case of inhibitory rules. As a result, we have algorithms (i) for multi-stage optimization of rules relative to such criteria as length or coverage, (ii) for counting the number of optimal rules, (iii) for construction of Pareto optimal points for bi-criteria optimization problems, (iv) for construction of graphs describing relationships between two cost functions, and (v) for construction of graphs describing relationships between cost and accuracy of rules. The applications of created tools include comparison (based on information about Pareto optimal points) of greedy heuristics for bi-criteria optimization of rules, and construction (based on multi-stage optimization of rules) of relatively short systems of rules that can be used for knowledge representation.

Hydro power producers are faced with the task of releasing water from the reservoirs in the right time. To do this there are tools using stochastic optimization that aims at maximizing the income of that producer. The existing methods have a high computing time and grow exponentially with the size of the problem. A new approach that uses linear decision rules is investigated in this thesis to see if it is possible to maintain the same quality of the solutions and in the same time decrease run times. With this method the hydro power producer receives policies as an affine function of the realization of the uncertainty variables in inflow and price. This thesis presents a deterministic model and then converts it into an linear decision rules, LDR, model. It also presents a way to model the uncertainty in both inflow to the reservoir and the spot price. The result is that the LDR approach generates reasonable policies with low run times but loses a lot of optimality compared to solutions that are used today. Therefore it is concluded that this approach needs further development before commercial use. The work described in this thesis has been done in cooperation with three master students at NTNU. The approach of using linear decision rules are the same in the two projects but the differences are the models evaluated.

Na Inferência Estatística, é comum, após a realização de um experimento, testar simultaneamente um conjunto de diferentes hipóteses de interesse acerca de um parâmetro desconhecido. Assim, para cada hipótese, realiza-se um teste de hipótese e, a partir disto, conclui-se algo sobre os parâmetros de interesse. O objetivo deste trabalho é avaliar a (falta de) concordância lógica entre as conclusões obtidas a partir dos testes realizados após a observação de um único experimento. Neste estudo, é apresentada uma definição de classe de testes de hipóteses, uma função que para cada hipótese de interesse associa uma função de teste. São então avaliadas algumas propriedades que refletem como gostaríamos que testes para diferentes hipóteses se comportassem em termos de coerência lógica. Tais propriedades são exemplificadas através de classes de testes que as satisfazem. A seguir, consideram-se conjuntos de axiomas para classes. Estes axiomas são baseados nas propriedades mencionadas. Classes de testes usuais são investigadas com relação aos conjuntos de axiomas propostos. São também estudadas propriedades advindas de tais conjuntos de axiomas. Por fim, estuda-se um resultado que estabelece uma espécie de conexão entre testes de hipóteses e estimação pontual. / In Statistical Inference, it is usual, after an experiment is performed, to test simultaneously a set of hypotheses of interest concerning an unknown parameter. Therefore, to each hypothesis, a statistical test is performed and a conclusion about the parameter is drawn based on it. The objective of this work is to evaluate the (lack of) logical coherence among conclusions obtained from tests conducted after the observation of a single experiment. In this study, a definition of class of hypotheses tests, a function that associates a test function to each hypothesis of interest, is presented. Some properties that reflect what one could expect (in terms of logical coherence) from tests to different hypotheses are then evaluated. These properties are exemplified by classes of hypotheses tests that respect them. Then, sets of axioms based on the properties studied are proposed to classes of hypotheses tests. Usual classes of hypotheses tests are investigated with respect to these sets of axioms. Some properties related to these sets of axioms are then analyzed. At last, a result which seems to connect hypotheses testing and point estimation is stated.

Clinical decision rules improve health care fidelity, benefit patients, physicians and healthcare systems, without reducing patient safety or satisfaction, while promoting cost-effective practice standards. It is critical to appropriately and consistently apply clinical decision rules to realize these benefits. The objective of this thesis was to understand how physicians use the Ottawa Ankle Rules to guide radiography decision-making. The study employed a clinical judgment survey targeting members of the Canadian Association of Emergency Physicians. Statistical analyses were informed by the Brunswik Lens Model and Social Judgment Analysis. Physicians’ overall agreement with the ankle rule was high, but can be improved. Physicians placed greatest value on rule-based cues, while considering non-rule-based cues as moderately important. There is room to improve physician agreement with the ankle rule and use of rule-based cues through knowledge translation interventions. Further development of this Lens Modeling technique could lend itself to a valuable cognitive behavioral intervention.

Clinical decision rules improve health care fidelity, benefit patients, physicians and healthcare systems, without reducing patient safety or satisfaction, while promoting cost-effective practice standards. It is critical to appropriately and consistently apply clinical decision rules to realize these benefits. The objective of this thesis was to understand how physicians use the Ottawa Ankle Rules to guide radiography decision-making. The study employed a clinical judgment survey targeting members of the Canadian Association of Emergency Physicians. Statistical analyses were informed by the Brunswik Lens Model and Social Judgment Analysis. Physicians’ overall agreement with the ankle rule was high, but can be improved. Physicians placed greatest value on rule-based cues, while considering non-rule-based cues as moderately important. There is room to improve physician agreement with the ankle rule and use of rule-based cues through knowledge translation interventions. Further development of this Lens Modeling technique could lend itself to a valuable cognitive behavioral intervention.

Clinical decision rules improve health care fidelity, benefit patients, physicians and healthcare systems, without reducing patient safety or satisfaction, while promoting cost-effective practice standards. It is critical to appropriately and consistently apply clinical decision rules to realize these benefits. The objective of this thesis was to understand how physicians use the Ottawa Ankle Rules to guide radiography decision-making. The study employed a clinical judgment survey targeting members of the Canadian Association of Emergency Physicians. Statistical analyses were informed by the Brunswik Lens Model and Social Judgment Analysis. Physicians’ overall agreement with the ankle rule was high, but can be improved. Physicians placed greatest value on rule-based cues, while considering non-rule-based cues as moderately important. There is room to improve physician agreement with the ankle rule and use of rule-based cues through knowledge translation interventions. Further development of this Lens Modeling technique could lend itself to a valuable cognitive behavioral intervention.

Na Inferência Estatística, é comum, após a realização de um experimento, testar simultaneamente um conjunto de diferentes hipóteses de interesse acerca de um parâmetro desconhecido. Assim, para cada hipótese, realiza-se um teste de hipótese e, a partir disto, conclui-se algo sobre os parâmetros de interesse. O objetivo deste trabalho é avaliar a (falta de) concordância lógica entre as conclusões obtidas a partir dos testes realizados após a observação de um único experimento. Neste estudo, é apresentada uma definição de classe de testes de hipóteses, uma função que para cada hipótese de interesse associa uma função de teste. São então avaliadas algumas propriedades que refletem como gostaríamos que testes para diferentes hipóteses se comportassem em termos de coerência lógica. Tais propriedades são exemplificadas através de classes de testes que as satisfazem. A seguir, consideram-se conjuntos de axiomas para classes. Estes axiomas são baseados nas propriedades mencionadas. Classes de testes usuais são investigadas com relação aos conjuntos de axiomas propostos. São também estudadas propriedades advindas de tais conjuntos de axiomas. Por fim, estuda-se um resultado que estabelece uma espécie de conexão entre testes de hipóteses e estimação pontual. / In Statistical Inference, it is usual, after an experiment is performed, to test simultaneously a set of hypotheses of interest concerning an unknown parameter. Therefore, to each hypothesis, a statistical test is performed and a conclusion about the parameter is drawn based on it. The objective of this work is to evaluate the (lack of) logical coherence among conclusions obtained from tests conducted after the observation of a single experiment. In this study, a definition of class of hypotheses tests, a function that associates a test function to each hypothesis of interest, is presented. Some properties that reflect what one could expect (in terms of logical coherence) from tests to different hypotheses are then evaluated. These properties are exemplified by classes of hypotheses tests that respect them. Then, sets of axioms based on the properties studied are proposed to classes of hypotheses tests. Usual classes of hypotheses tests are investigated with respect to these sets of axioms. Some properties related to these sets of axioms are then analyzed. At last, a result which seems to connect hypotheses testing and point estimation is stated.

This thesis applies the data mining method of decision rules on data from Consulting centre for Metabolism disorders from University hospital Pilsen. As a tool is used the system LISp-Miner, developed at University of Economics, Prague. Decision rules found are evaluated by a specialist. The main parts of this thesis are followings: an overview on main data mining methods and results evalutation methods, description of the data mining method application on data and description and evaluation of results.

Background: Diagnosis of acute coronary syndromes (ACS) in the Emergency Department (ED) is a topical and contentious issue. Current diagnostic techniques rely on hospital admission for troponin testing. Only a minority of those admitted prove to have ACS while unacceptable proportions of those discharged have unrecognised ACS. Aims: We aimed to evaluate the diagnostic and prognostic value of individual clinical findings and novel biomarkers in ED patients with suspected cardiac chest pain. We then aimed to derive a clinical decision rule (CDR) to potentially enable safe, immediate discharge of a proportion of patients from the ED while risk stratifying others to facilitate triage to an appropriate level of in-patient care. Methods: We recruited patients who presented to the ED with suspected cardiac chest pain. Variables that have previously been shown to predict diagnosis of acute myocardial infarction (AMI) or to predict outcome were prospectively recorded. Blood was drawn at presentation for levels of eight biomarkers. Patients underwent 12-hour troponin testing and were followed up for the composite primary outcome of AMI, death or urgent coronary revascularisation for six months. Variables that were univariate predictors (p<0.05) of outcome were entered into a multivariate analysis using recursive partitioning. Results: While many clinical findings and levels of all eight novel biomarkers were found to be significant predictors of outcome, none could be used individually to confirm or exclude ACS in the ED. We derived a nine-point CDR that combined clinical findings with biomarker levels to effectively stratify patients into four risk groups. 14.2% of patients were identified as being at ‘no risk’ and had a 0.0% outcome rate. The rule performed significantly better than two commonly used risk scores and may improve on triage decisions made in actual clinical practice. Conclusion: ACS remains a difficult diagnosis to confidently confirm or refute in the ED. Our CDR may help to avoid unnecessary hospital admissions while improving on triage decisions made for the remaining in-patients. Prospective validation of our findings is warranted.

Sammanfattning   Björk kan ge ett bra virke och med undantag för sämre fukttålighet finns endast formella restriktioner i virkets användning i relation till tall och gran. Trots detta och trots att det finns gott om björkråvara i landet är den sågade och använda björkvolymen påfallande liten. Björken utgör därför en underskattad skoglig och industriell resurs vars utnyttjande skulle kunna öka kraftigt.   Björken har varit ett lågprioriterat virke vilket sannolikt på grund av dålig skötsel påverkat kvalitén på våra nuvarande björkskogar och plantmaterialet. Det har också lett till att vi saknar tradition i vid mening att arbeta med björken. Forskning och utbildning fokuserar på barrvirke varför lövets, och då särskilt björkens möjligheter inte tillvaratas.   Björken kräver andra skötselmetoder än barrträden men utnyttjas dessa finns förutsättningar att skapa bra produktionsskogar både med avseende på volym och kvalitet. Mer forskning behövs dock i frågan om betesskador och hur dessa kan reduceras. Bra björktimmer kan pris- och lönsamhetsmässigt vara intressantare för skogsägaren än motsvarande barrtimmer. Dessa kunskaper måste nå ut till skogsägarna för att de skall förstå att det finns attraktiva alternativ till att slentrianmässigt anlägga nya tall- eller granskogar efter en föryngringsavverkning. Utöver det goda arbetet som Skogsstyrelsen gör med allmänna skötselråd gällande björkskogen borde de mer aktivt arbeta med skogsägarna för att stimulera till ett mer kommersiellt utnyttjande av björken. Denna uppmaning gäller även andra berörda parter vilket inkluderar skogsägarens alla rådgivare.   Den helt dominerande volymen av avverkad björk går i dagsläget till massabruken. Det finns flera skäl till detta. Ett kan vara att kvaliteten inte alltid svarar mot sågverkens krav men andra skäl är hanterings- och logistikproblem med att hantera små volymer sågtimmer och bristande kunskaper både hos skördarföraren och hos skogsägaren. Hade skogsägaren haft de goda förtjänstmöjligheterna på björktimmer klar för sig vid avverkningen hade han kunnat ge noggrannare instruktioner om hur björkvirket skulle hanteras.   Sågverken som hanterar björk är få och relativt små. För en verklig volymproduktion av björktimmer behövs en resurs- och teknikutbyggnad. Vissa satsningar görs men mer behövs. Dessa satsningar måste göras utifrån ett verkligt marknadsmässigt perspektiv. Vem skall svara för nödvändiga investeringar? Var finns industrin, riskkapitalisterna och investerarna som är beredda att satsa på en fabrik för svensk björkplywood eller byggsystem som inkluderar björk? Lönsamheten är inget att skryta med och branschen utövar ingen stor lockelse för nya entreprenörer. Även här kommer marknadsaspekterna in. Det behövs industriell efterfrågan på stora volymer sågad björk för att konstituera en verklig marknad. För att skapa denna räcker det inte med en satsning på snickeriindustrin utan björk måste även i Sverige användas som ett naturligt virke i byggsammanhang. Boverket har här en nyckelroll och måste anpassa svenska normer till motsvarande europeiska så att det blir möjligt att interiört bygga också med björk. Vem driver den frågan? Vem stimulerar arkitekter och byggnadskonstruktörer till att bygga med björk? På samma sätt som det sätts upp priser för bästa trähus kunde det möjligen också skapas ett pris för bästa anläggning byggd i björk. Hur kan man skapa intresse hos en kommun, ett företag eller organisation att genomföra ett profilbygge i björk? Sveriges Träbyggnadskansli är en lämplig mottagare av detta budskap men det borde finnas fler.   I takt med att skogens miljömål accentueras blir lövskogen än viktigare. Lika viktigt är då att alla parter samverkar för att skogsägaren som sköter sin lövskog på ett bra sätt skall få avsättning för sitt virke till acceptabla villkor. Skogsstyrelsen måste också ha en positiv syn på lövavverkningen och inte av miljöskäl i en framtid stoppa denna när den blir aktuell. Blotta misstanken hos skogsägaren att så kan bli fallet kommer att leda till ett minskat intresse för lövskogen.   Lövträ är inget homogent begrepp och egenskaperna skiljer sig märkbart mellan t.ex. al, alm, ask, lönn å ena sidan och björk å den andra. Det finns ingen anledning att i detta sammanhang tala om björk i allmänna ordalag som ett lövträd utan björk är björk och inget annat och skall så behandlas.   Sammanfattningsvis har vi gott om björk vars virke kan användas på mångahanda sätt. Att så inte sker kan inte förklaras av någon enstaka faktor. För att få en ändring till stånd krävs i första hand ett renodlat marknadsmässigt tänkesätt med ökad information och kunskap i alla led. Det talas om att skogsnäringen måste marknadsorientera sig i sin verksamhet. Detta gäller hela kedjan från skogsägaren till slutkonsumenten av skogsprodukten. / Summary in English   Sweden is a forest country with a standing wood balance of more than 3 000 million m3sk. Pine and spruce are dominating species but there is also a wood balance of some 420 million m3sk of birch. Birch is offering excellent timber properties and is well matching both pine and spruce with the exception of its sensitivity to moisture. Despite of this, quite small quantities of birch timber are being used in Sweden. Most birch wood being cut is used for the production of paper and pulp (95%). Although the birch tree is an old species in Sweden it was during the 2000th century until the end of the 1970s treated as a weed and was struggled with by means of herbicides. Subsequently Sweden lost knowledge and experience in how to deal with this wood which in turn leads to a poor quality of now existing clumps of birch trees. Compared to coniferous trees little research has been done of broadleaf trees but it’s anyhow known that the clearing and thinning of birch trees have to be stricter than that of softwood. Birch trees have an interesting potential with a shorter production cycle than pine and spruce. Used for timber the yield for the forest owner could be quite interesting. Broadleaf trees are also playing an important role to improve the overall environment.   To increase the use of birch wood more information about this specific timber has to be spread to all parties concerned. That involves owners of forest land, silviculture, sawmills, industry and distributors. Activities along the chain of actors have to be market oriented and include economic incentives for parties concerned. To be able to increase the volume of birch timber used new areas of deployment have to be found outside the traditional production of furniture etc. An interesting area is then the building industry.