This thesis investigates new clustering paradigms and algorithms based on the principle of the shared nearest-neighbors (SNN. As most other graph-based clustering approaches, SNN methods are actually well suited to overcome data complexity, heterogeneity and high-dimensionality.The first contribution of the thesis is to revisit existing shared neighbors methods in two points. We first introduce a new SNN formalism based on the theory of a contrario decision. This allows us to derive more reliable connectivity scores of candidate clusters and a more intuitive interpretation of locally optimum neighborhoods. We also propose a new factorization algorithm for speeding-up the intensive computation of the required sharedneighbors matrices.The second contribution of the thesis is a generalization of the SNN clustering approach to the multi-source case. Whereas SNN methods appear to be ideally suited to sets of heterogeneous information sources, this multi-source problem was surprisingly not addressed in the literature beforehand. The main originality of our approach is that we introduce an information source selection step in the computation of candidate cluster scores. As shown in the experiments, this source selection step makes our approach widely robust to the presence of locally outlier sources. This new method is applied to a wide range of problems including multimodal structuring of image collections and subspace-based clustering based on random projections. The third contribution of the thesis is an attempt to extend SNN methods to the context of bipartite k-nn graphs. We introduce new SNN relevance measures revisited for this asymmetric context and show that they can be used to select locally optimal bi-partite clusters. Accordingly, we propose a new bipartite SNN clustering algorithm that is applied to visual object's discovery based on a randomly precomputed matching graph. Experiments show that this new method outperformed state-of-the-art object mining results on OxfordBuilding dataset. Based on the discovered objects, we also introduce a new visual search paradigm, i.e. object-based visual query suggestion.

Diss. (sammanfattning) Stockholm : Karol. inst., 2002. / Härtill 5 uppsatser.

This study examined psychoanalytic, physiological, and social learning models of depression in terms of etiology and symptomatology. Emphasis was placed on social learning theories of depression. First, Beck's cognitive approach stated that the root of depression was a negative cognitive set. Depressive episodes might be externally precipitated, but it was the individual's perception and appraisal of the event that rendered it depression inducing. Secondly, Seligman's learned helplessness model explained reactive depression in terms of a belief in one's own helplessness. Specifically, Seligman stated belief in the uncontrollability of outcomes resulted in depression, irrespective of the correspondence of such beliefs to objective circumstances. Additionally, depression resulted from noncontingent aversive stimulation and noncontingent positive reinforcement. Thirdly, Lewinsohn's model was based on these assumptions: a low rate of response-contingent positive reinforcement which acted as an eliciting stimulus for depressive behaviors. This low rate of response-contingent positive reinforcement constituted an explanation for the low rate of behaviors observed in the depressive. Total amount of response—contingent positive reinforcement is a function of a number of events reinforcing for the individual, availability of reinforcement in the environment, and social skills of the individual that are necessary to elicit reinforcement.

This Master’s Thesis aimed to assess and propose improvements for initial learnability in Sectra AB’s Picture Archiving Communication System (PACS) by integrating usability engineering and agile software development. Assessing initial learnability and re-designing complex systems is difficult as they have a high skill cap and take longer time to learn in comparison to simpler ones. Further, companies that use agile methodologies often focus on completing small items which might hide the overarching vision of a product that can lead to usability problems. While there are several methods for assessing usability, no research has specifically focused on assessing initial learnability in complex systems. This study however investigates how this may be achieved by combining current methodologies for measuring learnability with usability engineering and agile software development. Initial learnability issues and needs were assessed after evaluating Sectra PACS using 5 participants and analysed using impact mapping as well as conducting a focus group within the organisation that owns the product.

The present diploma thesis deals with new optimization suggestions and their introduction to the logistics distribution chain of the online shop administered by the Lilien Czech Jewelry s.r.o. company. The thesis is comprised of two interconnected parts. The first, theoretical part, is dedicated to the description of key terms which are necessary for the general understanding of the importance of logistics chains in the efficiency of a company, as well as for the understaning of the practical part which follows. The second, practical part, deals with the company in question itself. The aim of the thesis is to provide an evaluation of the logistics chain of the given company as well as its resources. This includes an overview of the state of things before and after innovations proposed and carried out based on a previous bachelor's thesis. Further, the thesis treats the topic of new optimization suggestions regarding the processes involved in the flow of goods to the customer. This concerns specifically suggestions affecting the international distribution of delivery and storage within the company. Other phases of the chain are, however, not omitted.

This thesis deals with issues of debt forgiveness of natural persons on theoretical and practical basis. First part of thesis describes clarification of procedure of insolvency and explains key concepts. Practical part of the thesis is dedicated to analysis of debtors who went successfully through the procces of debt forgiveness since the beggining (insolvency suggestion) till the end (resolution of satisfaction of debt forgiveness). The goal of thesis is to clarify debt forgiveness in the context of whole process of insolvency procedure on the theoretical basis and to make detailed structured analysis of debtors who fulfiled all conditions of debt forgiveness by law.

The aim of the diploma thesis is to point out the connections between the moral life of a person and his state of health. This is a current topic of applied ethics, which deals with the relationship between ethical behavior and its consequences in health and disease therapy. The work deals with the life and work of Ctibor Bezděk, who is considered by the professional public to be the founder of ethics therapy. The diploma thesis introduces the concepts of ethics therapy and tries to bring the meaning of his work to the present day with an understandable approach. The diploma thesis also points out the importance of moral balance in various areas of our lives, the role of faith in God and the trust we place in him in the dynamics of health and disease. The method used in the diploma thesis is the analysis of Ctibor Bezděk's texts, the systematic arrangement into the topic of the thesis and the updating of his legacy. Key words: ethics, ethicotherapy, prayer, morality, illness, suggestion, healing, evil

The master’s thesis is focused on a functional suggestion of a data infrastructure in a company with more branches. It analyses the present condition of the data infrastructure and it is based on an analysis and there is an own solution implemented. The solution must be functional, and it must match the requirements discussed with the investor.

The thesis deals with technologies of goods protection. It is focused on electronic technologies of goods protection, which call EAS (electronic article surveillance) in foreign literature. The goal of this thesis is support for instruction in electronic surveillance of goods. This document systematically describes principle and technical solution recent electronic technologies of goods protection. There are mentioned advantages and disadvantages too. The other chapter deals with basic operating mode and configuration parameters of loop systems, acoustic-magnetic system and radio system. On the basis of this was suggested laboratory task. This task is use for better understanding of principles electronic surveillance of goods. Some possible attacks of electronic surveillance of goods are described at the last chapter of this thesis. This attacks was also realized.

This diploma thesis deals with the information system in organization AIESEC Slovakia. Through appropriate methods and analysis, the current state of the IS will be assessed. Based on results of these analyzes, there will be proposed changes that will lead ultimately to higher efficiency of the organization and improvement of quality of services provided.