Developing Processes and Learning in a Project-based Firm

T��m��n diplomity��n tavoitteena on kuvata tiedonkulkua projektiliiketoimintaa harjoittavassa yrityksess�� sek�� analysoida kuvausta m����ritt��en mahdolliset kehityskohdat. Ty��ss��tuotetut kuvaukset ja kehityskohtien m����ritt��minen toimivat pohjana yrityksen kehitt��ess�� projektien hallintaansa tulevaisuudessa. Ty��ss�� valitaan tietojohtamisen n��k��kulma sopivaksi l��hestymistavaksi yrityksen toiminnananalysointiin. Haastatteluin ker��tyn tutkimusmateriaalin perusteella luodaan prosessikuvaukset jotka mallintavat tietovirtoja yrityksen projektien aikana tapahtuvien prosessien v��lill��. Kuvausta peilataan tiet��myksen luomisen sek�� projektien tietojohtamisen teoriaan ja m����ritet����n kehityskohteita. Kehityskohteiden m����ritt��misen lis��ksi ehdotetaan mahdollisia toimenpiteit�� tiedon ja tiet��myksen hallinnan kehitt��miseksi. Kokemusten ja opittujen asioiden sek��palautteen ker����minen projektien aikana sek�� niiden j��lkeen havaittiin t��rkeimm��ksi kehityskohdaksi. N��iden ker����misen voidaan todeta vaativan j��rjestelm��llisyytt�� jotta projektien onnistumiset sek�� niiss�� saavutetut parannukset voidaan toistaa jatkossa ja virheet sek�� ep��onnistumiset sit�� vastoin v��ltt����.

Learning Preferences with Kernel-Based Methods

Learning of preference relations has recently received significant attention in machine learning community. It is closely related to the classification and regression analysis and can be reduced to these tasks. However, preference learning involves prediction of ordering of the data points rather than prediction of a single numerical value as in case of regression or a class label as in case of classification. Therefore, studying preference relations within a separate framework facilitates not only better theoretical understanding of the problem, but also motivates development of the efficient algorithms for the task. Preference learning has many applications in domains such as information retrieval, bioinformatics, natural language processing, etc. For example, algorithms that learn to rank are frequently used in search engines for ordering documents retrieved by the query. Preference learning methods have been also applied to collaborative filtering problems for predicting individual customer choices from the vast amount of user generated feedback. In this thesis we propose several algorithms for learning preference relations. These algorithms stem from well founded and robust class of regularized least-squares methods and have many attractive computational properties. In order to improve the performance of our methods, we introduce several non-linear kernel functions. Thus, contribution of this thesis is twofold: kernel functions for structured data that are used to take advantage of various non-vectorial data representations and the preference learning algorithms that are suitable for different tasks, namely efficient learning of preference relations, learning with large amount of training data, and semi-supervised preference learning. Proposed kernel-based algorithms and kernels are applied to the parse ranking task in natural language processing, document ranking in information retrieval, and remote homology detection in bioinformatics domain. Training of kernel-based ranking algorithms can be infeasible when the size of the training set is large. This problem is addressed by proposing a preference learning algorithm whose computation complexity scales linearly with the number of training data points. We also introduce sparse approximation of the algorithm that can be efficiently trained with large amount of data. For situations when small amount of labeled data but a large amount of unlabeled data is available, we propose a co-regularized preference learning algorithm. To conclude, the methods presented in this thesis address not only the problem of the efficient training of the algorithms but also fast regularization parameter selection, multiple output prediction, and cross-validation. Furthermore, proposed algorithms lead to notably better performance in many preference learning tasks considered.

A Belief rule-based environmental responsibility assessment system for small and medium-sized enterprises

Various environmental management systems, standards and tools are being created to assist companies to become more environmental friendly. However, not all the enterprises have adopted environmental policies in the same scale and range. Additionally, there is no existing guide to help them determine their level of environmental responsibility and subsequently, provide support to enable them to move forward towards environmental responsibility excellence. This research proposes the use of a Belief Rule-Based approach to assess an enterprise���s level commitment to environmental issues. The Environmental Responsibility BRB assessment system has been developed for this research. Participating companies will have to complete a structured questionnaire. An automated analysis of their responses (using the Belief Rule-Based approach) will determine their environmental responsibility level. This is followed by a recommendation on how to progress to the next level. The recommended best practices will help promote understanding, increase awareness, and make the organization greener. BRB systems consist of two parts: Knowledge Base and Inference Engine. The knowledge base in this research is constructed after an in-depth literature review, critical analyses of existing environmental performance assessment models and primarily guided by the EU Draft Background Report on "Best Environmental Management Practice in the Telecommunications and ICT Services Sector". The reasoning algorithm of a selected Drools JBoss BRB inference engine is forward chaining, where an inference starts iteratively searching for a pattern-match of the input and if-then clause. However, the forward chaining mechanism is not equipped with uncertainty handling. Therefore, a decision is made to deploy an evidential reasoning and forward chaining with a hybrid knowledge representation inference scheme to accommodate imprecision, ambiguity and fuzzy types of uncertainties. It is believed that such a system generates well balanced, sensible and Green ICT readiness adapted results, to help enterprises focus on making improvements on more sustainable business operations.

Kernel-Based Ranking. Methods for Learning and Performance Estimation

Machine learning provides tools for automated construction of predictive models in data intensive areas of engineering and science. The family of regularized kernel methods have in the recent years become one of the mainstream approaches to machine learning, due to a number of advantages the methods share. The approach provides theoretically well-founded solutions to the problems of under- and overfitting, allows learning from structured data, and has been empirically demonstrated to yield high predictive performance on a wide range of application domains. Historically, the problems of classification and regression have gained the majority of attention in the field. In this thesis we focus on another type of learning problem, that of learning to rank. In learning to rank, the aim is from a set of past observations to learn a ranking function that can order new objects according to how well they match some underlying criterion of goodness. As an important special case of the setting, we can recover the bipartite ranking problem, corresponding to maximizing the area under the ROC curve (AUC) in binary classification. Ranking applications appear in a large variety of settings, examples encountered in this thesis include document retrieval in web search, recommender systems, information extraction and automated parsing of natural language. We consider the pairwise approach to learning to rank, where ranking models are learned by minimizing the expected probability of ranking any two randomly drawn test examples incorrectly. The development of computationally efficient kernel methods, based on this approach, has in the past proven to be challenging. Moreover, it is not clear what techniques for estimating the predictive performance of learned models are the most reliable in the ranking setting, and how the techniques can be implemented efficiently. The contributions of this thesis are as follows. First, we develop RankRLS, a computationally efficient kernel method for learning to rank, that is based on minimizing a regularized pairwise least-squares loss. In addition to training methods, we introduce a variety of algorithms for tasks such as model selection, multi-output learning, and cross-validation, based on computational shortcuts from matrix algebra. Second, we improve the fastest known training method for the linear version of the RankSVM algorithm, which is one of the most well established methods for learning to rank. Third, we study the combination of the empirical kernel map and reduced set approximation, which allows the large-scale training of kernel machines using linear solvers, and propose computationally efficient solutions to cross-validation when using the approach. Next, we explore the problem of reliable cross-validation when using AUC as a performance criterion, through an extensive simulation study. We demonstrate that the proposed leave-pair-out cross-validation approach leads to more reliable performance estimation than commonly used alternative approaches. Finally, we present a case study on applying machine learning to information extraction from biomedical literature, which combines several of the approaches considered in the thesis. The thesis is divided into two parts. Part I provides the background for the research work and summarizes the most central results, Part II consists of the five original research articles that are the main contribution of this thesis.

Biomedical Event Extraction with Machine Learning

Biomedical natural language processing (BioNLP) is a subfield of natural language processing, an area of computational linguistics concerned with developing programs that work with natural language: written texts and speech. Biomedical relation extraction concerns the detection of semantic relations such as protein-protein interactions (PPI) from scientific texts. The aim is to enhance information retrieval by detecting relations between concepts, not just individual concepts as with a keyword search. In recent years, events have been proposed as a more detailed alternative for simple pairwise PPI relations. Events provide a systematic, structural representation for annotating the content of natural language texts. Events are characterized by annotated trigger words, directed and typed arguments and the ability to nest other events. For example, the sentence ���Protein A causes protein B to bind protein C��� can be annotated with the nested event structure CAUSE(A, BIND(B, C)). Converted to such formal representations, the information of natural language texts can be used by computational applications. Biomedical event annotations were introduced by the BioInfer and GENIA corpora, and event extraction was popularized by the BioNLP'09 Shared Task on Event Extraction. In this thesis we present a method for automated event extraction, implemented as the Turku Event Extraction System (TEES). A unified graph format is defined for representing event annotations and the problem of extracting complex event structures is decomposed into a number of independent classification tasks. These classification tasks are solved using SVM and RLS classifiers, utilizing rich feature representations built from full dependency parsing. Building on earlier work on pairwise relation extraction and using a generalized graph representation, the resulting TEES system is capable of detecting binary relations as well as complex event structures. We show that this event extraction system has good performance, reaching the first place in the BioNLP'09 Shared Task on Event Extraction. Subsequently, TEES has achieved several first ranks in the BioNLP'11 and BioNLP'13 Shared Tasks, as well as shown competitive performance in the binary relation Drug-Drug Interaction Extraction 2011 and 2013 shared tasks. The Turku Event Extraction System is published as a freely available open-source project, documenting the research in detail as well as making the method available for practical applications. In particular, in this thesis we describe the application of the event extraction method to PubMed-scale text mining, showing how the developed approach not only shows good performance, but is generalizable and applicable to large-scale real-world text mining projects. Finally, we discuss related literature, summarize the contributions of the work and present some thoughts on future directions for biomedical event extraction. This thesis includes and builds on six original research publications. The first of these introduces the analysis of dependency parses that leads to development of TEES. The entries in the three BioNLP Shared Tasks, as well as in the DDIExtraction 2011 task are covered in four publications, and the sixth one demonstrates the application of the system to PubMed-scale text mining.

Quantitative refinement of reaction-based biomodels

In the field of molecular biology, scientists adopted for decades a reductionist perspective in their inquiries, being predominantly concerned with the intricate mechanistic details of subcellular regulatory systems. However, integrative thinking was still applied at a smaller scale in molecular biology to understand the underlying processes of cellular behaviour for at least half a century. It was not until the genomic revolution at the end of the previous century that we required model building to account for systemic properties of cellular activity. Our system-level understanding of cellular function is to this day hindered by drastic limitations in our capability of predicting cellular behaviour to reflect system dynamics and system structures. To this end, systems biology aims for a system-level understanding of functional intraand inter-cellular activity. Modern biology brings about a high volume of data, whose comprehension we cannot even aim for in the absence of computational support. Computational modelling, hence, bridges modern biology to computer science, enabling a number of assets, which prove to be invaluable in the analysis of complex biological systems, such as: a rigorous characterization of the system structure, simulation techniques, perturbations analysis, etc. Computational biomodels augmented in size considerably in the past years, major contributions being made towards the simulation and analysis of large-scale models, starting with signalling pathways and culminating with whole-cell models, tissue-level models, organ models and full-scale patient models. The simulation and analysis of models of such complexity very often requires, in fact, the integration of various sub-models, entwined at different levels of resolution and whose organization spans over several levels of hierarchy. This thesis revolves around the concept of quantitative model refinement in relation to the process of model building in computational systems biology. The thesis proposes a sound computational framework for the stepwise augmentation of a biomodel. One starts with an abstract, high-level representation of a biological phenomenon, which is materialised into an initial model that is validated against a set of existing data. Consequently, the model is refined to include more details regarding its species and/or reactions. The framework is employed in the development of two models, one for the heat shock response in eukaryotes and the second for the ErbB signalling pathway. The thesis spans over several formalisms used in computational systems biology, inherently quantitative: reaction-network models, rule-based models and Petri net models, as well as a recent formalism intrinsically qualitative: reaction systems. The choice of modelling formalism is, however, determined by the nature of the question the modeler aims to answer. Quantitative model refinement turns out to be not only essential in the model development cycle, but also beneficial for the compilation of large-scale models, whose development requires the integration of several sub-models across various levels of resolution and underlying formal representations.

Modelling Energy Consumption of a Switch using Fuzzy-Rule Classifier

The energy consumption of IT equipments is becoming an issue of increasing importance. In particular, network equipments such as routers and switches are major contributors to the energy consumption of internet. Therefore it is important to understand how the relationship between input parameters such as bandwidth, number of active ports, traffic-load, hibernation-mode and their impact on energy consumption of a switch. In this paper, the energy consumption of a switch is analyzed in extensive experiments. A fuzzy rule-based model of energy consumption of a switch is proposed based on the result of experiments. The model can be used to predict the energy saving when deploying new switches by controlling the parameters to achieve desired energy consumption and subsequent performance. Furthermore, the model can also be used for further researches on energy saving techniques such as energy-efficient routing protocol, dynamic link shutdown, etc.

Generative Part-Based Gabor Object Detector

Object detection is a fundamental task of computer vision that is utilized as a core part in a number of industrial and scientific applications, for example, in robotics, where objects need to be correctly detected and localized prior to being grasped and manipulated. Existing object detectors vary in (i) the amount of supervision they need for training, (ii) the type of a learning method adopted (generative or discriminative) and (iii) the amount of spatial information used in the object model (model-free, using no spatial information in the object model, or model-based, with the explicit spatial model of an object). Although some existing methods report good performance in the detection of certain objects, the results tend to be application specific and no universal method has been found that clearly outperforms all others in all areas. This work proposes a novel generative part-based object detector. The generative learning procedure of the developed method allows learning from positive examples only. The detector is based on finding semantically meaningful parts of the object (i.e. a part detector) that can provide additional information to object location, for example, pose. The object class model, i.e. the appearance of the object parts and their spatial variance, constellation, is explicitly modelled in a fully probabilistic manner. The appearance is based on bio-inspired complex-valued Gabor features that are transformed to part probabilities by an unsupervised Gaussian Mixture Model (GMM). The proposed novel randomized GMM enables learning from only a few training examples. The probabilistic spatial model of the part configurations is constructed with a mixture of 2D Gaussians. The appearance of the parts of the object is learned in an object canonical space that removes geometric variations from the part appearance model. Robustness to pose variations is achieved by object pose quantization, which is more efficient than previously used scale and orientation shifts in the Gabor feature space. Performance of the resulting generative object detector is characterized by high recall with low precision, i.e. the generative detector produces large number of false positive detections. Thus a discriminative classifier is used to prune false positive candidate detections produced by the generative detector improving its precision while keeping high recall. Using only a small number of positive examples, the developed object detector performs comparably to state-of-the-art discriminative methods.

Evaluation of Machine Learning Classifiers for Mobile Network Intrusion Detection Systems

Mobile malwares are increasing with the growing number of Mobile users. Mobile malwares can perform several operations which lead to cybersecurity threats such as, stealing financial or personal information, installing malicious applications, sending premium SMS, creating backdoors, keylogging and crypto-ransomware attacks. Knowing the fact that there are many illegitimate Applications available on the App stores, most of the mobile users remain careless about the security of their Mobile devices and become the potential victim of these threats. Previous studies have shown that not every antivirus is capable of detecting all the threats; due to the fact that Mobile malwares use advance techniques to avoid detection. A Network-based IDS at the operator side will bring an extra layer of security to the subscribers and can detect many advanced threats by analyzing their traffic patterns. Machine Learning(ML) will provide the ability to these systems to detect unknown threats for which signatures are not yet known. This research is focused on the evaluation of Machine Learning classifiers in Network-based Intrusion detection systems for Mobile Networks. In this study, different techniques of Network-based intrusion detection with their advantages, disadvantages and state of the art in Hybrid solutions are discussed. Finally, a ML based NIDS is proposed which will work as a subsystem, to Network-based IDS deployed by Mobile Operators, that can help in detecting unknown threats and reducing false positives. In this research, several ML classifiers were implemented and evaluated. This study is focused on Android-based malwares, as Android is the most popular OS among users, hence most targeted by cyber criminals. Supervised ML algorithms based classifiers were built using the dataset which contained the labeled instances of relevant features. These features were extracted from the traffic generated by samples of several malware families and benign applications. These classifiers were able to detect malicious traffic patterns with the TPR upto 99.6% during Cross-validation test. Also, several experiments were conducted to detect unknown malware traffic and to detect false positives. These classifiers were able to detect unknown threats with the Accuracy of 97.5%. These classifiers could be integrated with current NIDS', which use signatures, statistical or knowledge-based techniques to detect malicious traffic. Technique to integrate the output from ML classifier with traditional NIDS is discussed and proposed for future work.

Segmental Durations of Speech

This dissertation considers the segmental durations of speech from the viewpoint of speech technology, especially speech synthesis. The idea is that better models of segmental durations lead to higher naturalness and better intelligibility. These features are the key factors for better usability and generality of synthesized speech technology. Even though the studies are based on a Finnish corpus the approaches apply to all other languages as well. This is possibly due to the fact that most of the studies included in this dissertation are about universal effects taking place on utterance boundaries. Also the methods invented and used here are suitable for any other study of another language. This study is based on two corpora of news reading speech and sentences read aloud. The other corpus is read aloud by a 39-year-old male, whilst the other consists of several speakers in various situations. The use of two corpora is twofold: it involves a comparison of the corpora and a broader view on the matters of interest. The dissertation begins with an overview to the phonemes and the quantity system in the Finnish language. Especially, we are covering the intrinsic durations of phonemes and phoneme categories, as well as the difference of duration between short and long phonemes. The phoneme categories are presented to facilitate the problem of variability of speech segments. In this dissertation we cover the boundary-adjacent effects on segmental durations. In initial positions of utterances we find that there seems to be initial shortening in Finnish, but the result depends on the level of detail and on the individual phoneme. On the phoneme level we find that the shortening or lengthening only affects the very first ones at the beginning of an utterance. However, on average, the effect seems to shorten the whole first word on the word level. We establish the effect of final lengthening in Finnish. The effect in Finnish has been an open question for a long time, whilst Finnish has been the last missing piece for it to be a universal phenomenon. Final lengthening is studied from various angles and it is also shown that it is not a mere effect of prominence or an effect of speech corpus with high inter- and intra-speaker variation. The effect of final lengthening seems to extend from the final to the penultimate word. On a phoneme level it reaches a much wider area than the initial effect. We also present a normalization method suitable for corpus studies on segmental durations. The method uses an utterance-level normalization approach to capture the pattern of segmental durations within each utterance. This prevents the impact of various problematic variations within the corpora. The normalization is used in a study on final lengthening to show that the results on the effect are not caused by variation in the material. The dissertation shows an implementation and prowess of speech synthesis on a mobile platform. We find that the rule-based method of speech synthesis is a real-time software solution, but the signal generation process slows down the system beyond real time. Future aspects of speech synthesis on limited platforms are discussed. The dissertation considers ethical issues on the development of speech technology. The main focus is on the development of speech synthesis with high naturalness, but the problems and solutions are applicable to any other speech technology approaches.

Parallella, dynamiska representationer i gymnasiefysiken : implementering av ett interaktivt datorverktyg i didaktiska situationer och uppfattning av effektivt l��rande

The computer is a useful tool in the teaching of upper secondary school physics, and should not have a subordinate role in students' learning process. However, computers and computer-based tools are often not available when they could serve their purpose best in the ongoing teaching. Another problem is the fact that commercially available tools are not usable in the way the teacher wants. The aim of this thesis was to try out a novel teaching scenario in a complicated subject in physics, electrodynamics. The didactic engineering of the thesis consisted of developing a computer-based simulation and training material, implementing the tool in physics teaching and investigating its effectiveness in the learning process. The design-based research method, didactic engineering (Artigue, 1994), which is based on the theoryof didactical situations (Brousseau, 1997), was used as a frame of reference for the design of this type of teaching product. In designing the simulation tool a general spreadsheet program was used. The design was based on parallel, dynamic representations of the physics behind the function of an AC series circuit in both graphical and numerical form. The tool, which was furnished with possibilities to control the representations in an interactive way, was hypothesized to activate the students and promote the effectiveness of their learning. An effect variable was constructed in order to measure the students' and teachers' conceptions of learning effectiveness. The empirical study was twofold. Twelve physics students, who attended a course in electrodynamics in an upper secondary school, participated in a class experiment with the computer-based tool implemented in three modes of didactical situations: practice, concept introduction and assessment. The main goal of the didactical situations was to have students solve problems and study the function of AC series circuits, taking responsibility for theirown learning process. In the teacher study eighteen Swedish speaking physics teachers evaluated the didactic potential of the computer-based tool and the accompanying paper-based material without using them in their physics teaching. Quantitative and qualitative data were collected using questionnaires, observations and interviews. The result of the studies showed that both the group of students and the teachers had generally positive conceptions of learning effectiveness. The students' conceptions were more positive in the practice situation than in the concept introduction situation, a setting that was more explorative. However, it turned out that the students' conceptions were also positive in the more complex assessment situation. This had not been hypothesized. A deeper analysis of data from observations and interviews showed that one of the students in each pair was more active than the other, taking more initiative and more responsibilityfor the student-student and student-computer interaction. These active studentshad strong, positive conceptions of learning effectiveness in each of the threedidactical situations. The group of less active students had a weak but positive conception in the first iv two situations, but a negative conception in the assessment situation, thus corroborating the hypothesis ad hoc. The teacher study revealed that computers were seldom used in physics teaching and that computer programs were in short supply. The use of a computer was considered time-consuming. As long as physics teaching with computer-based tools has to take place in special computer rooms, the use of such tools will remain limited. The affordance is enhanced when the physical dimensions as well as the performance of the computer are optimised. As a consequence, the computer then becomes a real learning tool for each pair of students, smoothly integrated into the ongoing teaching in the same space where teaching normally takes place. With more interactive support from the teacher, the computer-based parallel, dynamic representations will be efficient in promoting the learning process of the students with focus on qualitative reasoning - an often neglected part of the learning process of the students in upper secondary school physics.

TURKU TAKING STEPS TOWARDS FUTURE - technology supports physical activity

Physical activity (PA) is an important field of healthcare research internationally and within Finland. As technology devices and services penetrate deeper levels within society, the need for studying the usefulness for PA turns vital. We started this research work by reviewing literature consisting of two hundred research journals, all of which have found technology to significantly improve an individual���s ability to get motivation and achieve officially recommended levels of physical activity, like the 10000 steps a day, being tracked with the help of pedometers. Physical activity recommendations require sustained encouragement, consistent performance in order to achieve the long term benefits. We surveyed within the city of Turku, how the motivation levels and thirty three other criterions encompassing technology awareness, adoption and usage attitudes are impacted. Our aim was to know the factors responsible for achieving consistent growth in activity levels within the individuals and focus groups, as well as to determine the causes of failures and for collecting user experience feedback. The survey results were quite interesting and contain impeccable information for this field. While the focus groups confirmed the theory established by past studies within our literature review, it also establishes our research propositions that ict tools and services have provided and can further add higher benefits and value to individuals in tracking and maintain their activity levels consistently for longer time durations. This thesis includes two new models which dictate technology and physical activity adoption patterns based on four easy to evaluate criterions, thereby helping the healthcare providers to recommend improvements and address issues with an easy rule based approach. This research work provides vital clues on technology based healthcare objectives and achievement of standard PA recommendations by people within Turku and nearby regions.

Theorizing Formal and Informal Feedback Practices in Management Accounting Through Three Dimensions

The purpose of this doctoral thesis is to widen and develop our theoretical frameworks for discussion and analyses of feedback practices in management accounting, particularly shedding light on its formal and informal aspects. The concept of feedback in management accounting has conventionally been analyzed within cybernetic control theory, in which feedback flows as a diagnostic or comparative loop between measurable outputs and pre-set goals (see e.g. Flamholtz et al. 1985; Flamholtz 1996, 1983), i.e. as a formal feedback loop. However, the everyday feedback practices in organizations are combinations of formal and informal elements. In addition to technique-driven feedback approaches (like budgets, measurement, and reward systems) we could also categorize social feedback practices that managers see relevant and effective in the pursuit of organizational control. While cybernetics or control theories successfully capture rational and measured aspects of organizational performance and offer a broad organizational context for the analysis, many individual and informal aspects remain vague and isolated. In order to discuss and make sense of the heterogeneous field of interpretations of formal and informal feedback, both in theory and practice, dichotomous approaches seem to be insufficient. Therefore, I suggest an analytical framework of formal and informal feedback with three dimensions (3D���s): source, time, and rule. Based on an abductive analysis of the theoretical and empirical findings from an interpretive case study around a business unit called Division Steelco, the 3Dframework and formal and informal feedback practices are further elaborated vis-��-vis the four thematic layers in the organizational control model by Flamholtz et al. (1985; Flamholtz 1996, 1983): core control system, organizational structure, organizational culture, and external environment. Various personal and cultural meanings given to the formal and informal feedback practices (���feedback as something���) create multidimensional interpretative contexts. Multidimensional frameworks aim to capture and better understand both the variety of interpretations and their implications to the functionality of feedback practices, important in interpretive research.

Linguistic models for decision support

Linguistic modelling is a rather new branch of mathematics that is still undergoing rapid development. It is closely related to fuzzy set theory and fuzzy logic, but knowledge and experience from other fields of mathematics, as well as other fields of science including linguistics and behavioral sciences, is also necessary to build appropriate mathematical models. This topic has received considerable attention as it provides tools for mathematical representation of the most common means of human communication - natural language. Adding a natural language level to mathematical models can provide an interface between the mathematical representation of the modelled system and the user of the model - one that is sufficiently easy to use and understand, but yet conveys all the information necessary to avoid misinterpretations. It is, however, not a trivial task and the link between the linguistic and computational level of such models has to be established and maintained properly during the whole modelling process. In this thesis, we focus on the relationship between the linguistic and the mathematical level of decision support models. We discuss several important issues concerning the mathematical representation of meaning of linguistic expressions, their transformation into the language of mathematics and the retranslation of mathematical outputs back into natural language. In the first part of the thesis, our view of the linguistic modelling for decision support is presented and the main guidelines for building linguistic models for real-life decision support that are the basis of our modeling methodology are outlined. From the theoretical point of view, the issues of representation of meaning of linguistic terms, computations with these representations and the retranslation process back into the linguistic level (linguistic approximation) are studied in this part of the thesis. We focus on the reasonability of operations with the meanings of linguistic terms, the correspondence of the linguistic and mathematical level of the models and on proper presentation of appropriate outputs. We also discuss several issues concerning the ethical aspects of decision support - particularly the loss of meaning due to the transformation of mathematical outputs into natural language and the issue or responsibility for the final decisions. In the second part several case studies of real-life problems are presented. These provide background and necessary context and motivation for the mathematical results and models presented in this part. A linguistic decision support model for disaster management is presented here ��� formulated as a fuzzy linear programming problem and a heuristic solution to it is proposed. Uncertainty of outputs, expert knowledge concerning disaster response practice and the necessity of obtaining outputs that are easy to interpret (and available in very short time) are reflected in the design of the model. Saaty���s analytic hierarchy process (AHP) is considered in two case studies - first in the context of the evaluation of works of art, where a weak consistency condition is introduced and an adaptation of AHP for large matrices of preference intensities is presented. The second AHP case-study deals with the fuzzified version of AHP and its use for evaluation purposes ��� particularly the integration of peer-review into the evaluation of R&D outputs is considered. In the context of HR management, we present a fuzzy rule based evaluation model (academic faculty evaluation is considered) constructed to provide outputs that do not require linguistic approximation and are easily transformed into graphical information. This is achieved by designing a specific form of fuzzy inference. Finally the last case study is from the area of humanities - psychological diagnostics is considered and a linguistic fuzzy model for the interpretation of outputs of multidimensional questionnaires is suggested. The issue of the quality of data in mathematical classification models is also studied here. A modification of the receiver operating characteristics (ROC) method is presented to reflect variable quality of data instances in the validation set during classifier performance assessment. Twelve publications on which the author participated are appended as a third part of this thesis. These summarize the mathematical results and provide a closer insight into the issues of the practicalapplications that are considered in the second part of the thesis.