The main aim of this diploma thesis was to explore the topic of malaria preventive measures. Concretely, to study which preventive measures are useful and to see how they are distributed around the world. For international organizations, this is very important as they need to know whether funds allocated for malaria aid are distributed effectively. This study is using manually compounded data from the World Health Organization for all countries threatened by malaria mostly from 2001 to 2018. For this purpose, panel data regression methods using robust standard errors, bootstrapping and cluster analysis were used. The results showed that generally, the most useful preventive measures are indoor-residual sprayings, a combination of sprayings and insecticide-treated nets and rapid diagnostic tests. Furthermore, the effect of the population living in rural areas is significant. Besides, gross domestic product is a very important factor for African countries. The stability analysis - bootstrapping - confirmed our results. However, we examined that insecticide-treated nets are still the most distributed measures. Doing the cluster analysis, we observed that countries on the same continent should not be treated similarly and we emphasized countries that should receive higher attention. Overall, the...

Den senaste finanskrisen har visat att det finns ett behov av ökad övervakning av aktörerna på den finansiella marknaden. Ett sätt att förbättra övervakningen är genom att öka förståelsen för företagens affärsmodeller. Syftet med detta examensarbete är att hitta likheter i affärsmodellerna hos svenska kreditinstitut och hos svenska filialer av utländska banker. Mer specifikt syftar denna studie till att hitta grupper av företag, i denna rapport kallat kluster, med liknande affärsmodell och till att identifiera existerande affärsmodeller på den svenska bankmarknaden. Informationen som användes i studien är från årsredovisningar som rapporterades till Finansinspektionen för åren 2000, 2005, 2010 och 2013.  För att möjliggöra en jämförelse mellan olika aktörers data har kvoter skapats utifrån deras balans- och resultaträkningar. För att reducera mängden data och för att få ett fåtal okorrelerade variabler användes principalkomponentanalys. Metoden som användes för att hitta klustren är en hierarkisk agglomerativ metod kallad Wards metod. Antalet kluster bestämdes genom att använda Calinski- Harabasz-index. Bootstrapping användes för att testa stabiliteten hos de identifierade klustren.  Denna studie visar att mönster existerar på den svenska bankmarknaden och att det är möjligt att hitta kluster av företag med liknande affärsmodell. Svenska filialer av utländska banker och svenska kreditinstitut har studerats separat. För svenska kreditinstitut hittades sex kluster och för att beskriva affärsmodellerna kallas de: Universalbanker, Sparbanker, Leasingföretag, Icke inlåningsfinansierade kreditinstitut, Servicefokuserade kreditinstitut och Övriga kreditinstitut. De mest stabila klustren, det vill säga de med högst likhet, är Sparbanker och Leasingföretag. Klustret med lägst likhet är Universalbanker och detta bör ses som ett mönster i använd data snarare än ett kluster. För de svenska filialerna av utländska banker hittades tre kluster och dessa kallas: Banker, Servicefokuserade kreditinstitut och Övriga kreditinstitut. Dessa kluster är stabila. / The recent financial crisis has emphasized the need for improved supervision of the actors on the financial market. One way to improve supervision is through better understanding of business models. The aim with this thesis is to find similarities in business models for Swedish credit institutions and for Swedish branches of foreign banks. More specific this study aims to find groups of companies, in this paper called clusters, with similar business models and identify existing business models in the banking market. The data used in this study are financial statements reported to the Swedish Financial Supervisory Authority for the years 2000, 2005, 2010 and 2013. In order to compare the companies’ data, ratios from the income statements and balance sheets have been created. To reduce the amount of data and arrive at a smaller set of uncorrelated variables, principal component analysis was used. The method used for finding the clusters was a hierarchical agglomerative clustering method called Ward’s method. The number of clusters was determined using Calinski-Harabasz index. Bootstrapping was used in order to test cluster stability. This study shows that patterns in the Swedish banking sector exist and that it is possible to find clusters of companies with similar business models. Swedish branches of foreign banks have been treated separately from Swedish credit institutions. For Swedish credit institutions a division into six clusters was found to be most suitable and in order to describe the business model the clusters are named: Universal banks, Savings banks, Leasing companies, Non-deposit funded credit institutions, Service-focused credit institutions and Other credit institutions. The most stable clusters, that are the clusters with highest similarity, are Savings banks and Leasing companies. The cluster with lowest stability is Universal banks and it could be considered as a pattern in the data rather than a cluster. For Swedish branches of foreign banks, three clusters were found to be most suitable and the clusters are named: Banks, Service-focused credit institutions and Other credit institutions. These clusters are stable.

In this thesis we consider graph partition of a particular kind of complex networks referred to as power law graphs. In particular, we focus our analysis on the market graph, constructed from time series of price return on the American stock market. Two different methods originating from clustering analysis in social networks and image segmentation are applied to obtain graph partitions and the results are evaluated in terms of the structure and quality of the partition. Along with the market graph, power law graphs from three different theoretical graph models are considered. This study highlights topological features common in many power law graphs as well as their differences and limitations. Our results show that the market graph possess a clear clustered structure only for higher correlation thresholds. By studying the internal structure of the graph clusters we found that they could serve as an alternative to traditional sector classification of the market. Finally, partitions for different time series was considered to study the dynamics and stability in the partition structure. Even though the results from this part were not conclusive we think this could be an interesting topic for future research. / I denna uppsats studeras graf partition av en typ av komplexa nätverk som kallas power law grafer. Specifikt fokuserar vi på marknadengrafen, konstruerad av tidsserier av aktiepriser på den amerikanska aktiemarknaden. Två olika metoder, initialt utvecklade för klusteranalys i sociala nätverk samt för bildanalys appliceras för att få graf-partitioner och resultaten utvärderas utifrån strukturen och kvaliten på partitionen. Utöver marknadsgrafen studeras aven power law grafer från tre olika teoretiska grafmodeller. Denna studie belyser topologiska egenskaper vanligt förekommande i många power law grafer samt modellerns olikheter och begränsningar. Våra resultat visar att marknadsgrafen endast uppvisar en tydlig klustrad struktur för högre korrelation-trösklar. Genom att studera den interna strukturen hos varje kluster fann vi att kluster kan vara ett alternativ till traditionell marknadsindelning med industriella sektorer. Slutligen studerades partitioner för olika tidsserier för att undersöka dynamiken och stabiliteten i partitionsstrukturen. Trots att resultaten från denna del inte var entydiga tror vi att detta kan vara ett intressant spår för framtida studier.

In today's society, companies are trying to find ways to utilize all the data they have, which considers valuable information and insights to make better decisions. This includes data used to keeping track of timber that flows between forest and industry. The growth of Artificial Intelligence (AI) and Machine Learning (ML) has enabled the development of ML modes to automate the measurements of timber on timber trucks, based on images. However, to improve the results there is a need to be able to get information from unlabeled images in order to decide weather and lighting conditions. The objective of this study is to perform an extensive for classifying unlabeled images in the categories, daylight, darkness, and snow on the load. A comparative study between partitional clustering and competitive learning is conducted to investigate which method gives the best results in terms of different clustering performance metrics. It also examines how dimensionality reduction affects the outcome. The algorithms K-means and Kohonen Self-Organizing Map (SOM) are selected for the clustering. Each model is investigated according to the number of clusters, size of dataset, clustering time, clustering performance, and manual samples from each cluster. The results indicate a noticeable clustering performance discrepancy between the algorithms concerning the number of clusters, dataset size, and manual samples. The use of dimensionality reduction led to shorter clustering time but slightly worse clustering performance. The evaluation results further show that the clustering time of Kohonen SOM is significantly higher than that of K-means.

Dans la vie actuelle, les données directionnelles sont présentes dans la majorité des domaines, sous plusieurs formes, différents aspects et de grandes tailles/dimensions, d'où le besoin de méthodes d'étude efficaces des problématiques posées dans ce domaine. Pour aborder le problème de la classification automatique, l'approche probabiliste est devenue une approche classique, reposant sur l'idée simple : étant donné que les g classes sont différentes entre elles, on suppose que chacune suit une loi de probabilité connue, dont les paramètres sont en général différents d'une classe à une autre; on parle alors de modèle de mélange de lois de probabilités. Sous cette hypothèse, les données initiales sont considérées comme un échantillon d'une variable aléatoire d-dimensionnelle dont la densité est un mélange de g distributions de probabilités spécifiques à chaque classe. Dans cette thèse nous nous sommes intéressés à la classification automatique de données directionnelles, en utilisant des méthodes de classification les mieux adaptées sous deux approches: géométrique et probabiliste. Dans la première, en explorant et comparant des algorithmes de type kmeans; dans la seconde, en s'attaquant directement à l'estimation des paramètres à partir desquels se déduit une partition à travers la maximisation de la log-vraisemblance, représentée par l'algorithme EM. Pour cette dernière approche, nous avons repris le modèle de mélange de distributions de von Mises-Fisher, nous avons proposé des variantes de l'algorithme EMvMF, soit CEMvMF, le SEMvMF et le SAEMvMF, dans le même contexte, nous avons traité le problème de recherche du nombre de composants et le choix du modèle de mélange, ceci en utilisant quelques critères d'information : Bic, Aic, Aic3, Aic4, Aicc, Aicu, Caic, Clc, Icl-Bic, Ll, Icl, Awe. Nous terminons notre étude par une comparaison du modèle vMF avec un modèle exponentiel plus simple ; à l'origine ce modèle part du principe que l'ensemble des données est distribué sur une hypersphère de rayon ρ prédéfini, supérieur ou égal à un. Nous proposons une amélioration du modèle exponentiel qui sera basé sur une étape estimation du rayon ρ au cours de l'algorithme NEM. Ceci nous a permis dans la plupart de nos applications de trouver de meilleurs résultats; en proposant de nouvelles variantes de l'algorithme NEM qui sont le NEMρ , NCEMρ et le NSEMρ. L'expérimentation des algorithmes proposés dans ce travail a été faite sur une variété de données textuelles, de données génétiques et de données simulées suivant le modèle de von Mises-Fisher (vMF). Ces applications nous ont permis une meilleure compréhension des différentes approches étudiées le long de cette thèse. / In contemporary life directional data are present in most areas, in several forms, aspects and large sizes / dimensions; hence the need for effective methods of studying the existing problems in these fields. To solve the problem of clustering, the probabilistic approach has become a classic approach, based on the simple idea: since the g classes are different from each other, it is assumed that each class follows a distribution of probability, whose parameters are generally different from one class to another. We are concerned here with mixture modelling. Under this assumption, the initial data are considered as a sample of a d-dimensional random variable whose density is a mixture of g distributions of probability where each one is specific to a class. In this thesis we are interested in the clustering of directional data that has been treated using known classification methods which are the most appropriate for this case. In which both approaches the geometric and the probabilistic one have been considered. In the first, some kmeans like algorithms have been explored and considered. In the second, by directly handling the estimation of parameters from which is deduced the partition maximizing the log-likelihood, this approach is represented by the EM algorithm. For the latter approach, model mixtures of distributions of von Mises-Fisher have been used, proposing variants of the EM algorithm: EMvMF, the CEMvMF, the SEMvMF and the SAEMvMF. In the same context, the problem of finding the number of the components in the mixture and the choice of the model, using some information criteria {Bic, Aic, Aic3, Aic4, AICC, AICU, CAIC, Clc, Icl-Bic, LI, Icl, Awe} have been discussed. The study concludes with a comparison of the used vMF model with a simpler exponential model. In the latter, it is assumed that all data are distributed on a hypersphere of a predetermined radius greater than one, instead of a unit hypersphere in the case of the vMF model. An improvement of this method based on the estimation step of the radius in the algorithm NEMρ has been proposed: this allowed us in most of our applications to find the best partitions; we have developed also the NCEMρ and NSEMρ algorithms. The algorithms proposed in this work were performed on a variety of textual data, genetic data and simulated data according to the vMF model; these applications gave us a better understanding of the different studied approaches throughout this thesis.

This work presents the topic of data mining on the web. It is focused on clustering. The aim of this project was to study the field of clustering and to implement clustering through the k-means algorithm. Then, the algorithm was tested on a dataset of text documents and on data extracted from web. This clustering method was implemented by means of Java technologies.

Aim of this project is to evaluate effectivity of various texture features within the context of image processing, particulary the task of texture recognition and classification. My work focuses on comparing and discussion of usage and efficiency of texture features based on local binary patterns and co- ccurence matrices. As classification algorithm is concerned, cluster analysis was choosen.

In der betriebswirtschaftlichen Forschung gewinnt die KMU- und Entrepreneurshipforschung zunehmend mehr Aufmerksamkeit. In den letzten Jahren wurden zahlreiche Konzepte aus der Forschung für große Unternehmen auf den Entre­preneur­ship- und KMU-Bereich übertragen und dort angewendet, ohne ihre Eignung für Klein- und Kleinstunternehmen zu überprüfen. Eine (empirische) Überprüfung, inwieweit die zugrundeliegenden Modelle und Annahmen auch im Bereich der KMU allgemein zutreffen, ist daher sicherlich angebracht. Eines dieser Werkzeuge, das in letzter Zeit immer mehr in den Blickpunkt der Forschung rückt, ist Entrepreneurial Orientation. Mit Entrepreneurial Orientation steht ein Werkzeug zur Verfügung, dass den gesamten Lebenszyklus eines Unternehmens abbilden kann und Elemente sowohl der Entrepreneurship- als auch der Organisations- und Strategieforschung integriert. Inwieweit Kombinationen von Entrepreneurial Orientation bei Konfigurationen von Unternehmens­eigenschaften für kleine und mittlere Unternehmen einen Erkenntnisbeitrag leisten können, wird in diesem Buch theoretisch und empirisch untersucht. / Recently, a major focus in economical research is on small- and medium-sized enterprises and entrepreneurship. As part of this development, many concepts have been transferred and adapted to the Entrepreneurship and SME sector from large corporation research, without being tested for their fit to this area. An (empirical) examination how the underlying models and assumptions transferred apply also to the field of SMEs in general seems to be necessary. One of the tools that gain more attention every year is the concept of Entrepreneurial Orientation. Entrepreneurial Orientation provides a tool that can model the entire lifecycle of an enterprise and integrates elements of entrepreneurship as well as organizational and strategy research. This book does provide a theoretical and empirical evaluation of how Entrepreneurial Orientation may be useful by designing configurations of small and medium-sized enterprises.

No description available.

Accurate and reliable traffic state estimation is essential for the identification of congested areas and bottleneck locations. It enables the quantification of congestion characteristics, such as intensity, duration, reliability, and spreading which are indispensable for the deployment of appropriate traffic management plans that can efficiently ameliorate congestion problems. Similarly, it is important to categorize known congestion patterns throughout a long period of time, so that corresponding traffic simulation models can be built for the investigation of the performance of different traffic management plans. This study conducts cluster analysis to identify days with similar travel conditions and congestion patterns. To this end, travel, traffic and weather data from the Smart Mobility Living Lab of Thessaloniki, Greece is used. Representative days per cluster are determined to facilitate the development of traffic simulation models that typify average traffic conditions within each cluster. Moreover, spatio-temporal matrices are developed to illustrate time-varying traffic conditions along different routes for the representative days. Results indicate that the proposed clustering technique can produce valid classification of days in groups with common characteristics, and that spatio-temporal matrices enable the development of traffic management plans which encompass routing information for competing routes in the city of Thessaloniki.