The aim of this dissertation is to study two problems of distributed nearest neighbor classification (DiNN) systematically. The first one compares two DiNN classifiers based on different schemes: majority voting and weighted voting. The second one is an extension of the DiNN method to the crowdsourcing application, which allows each worker data has a different size and noisy labels due to low worker quality. Both statistical guarantees and numerical comparisons are studied in depth.<br><div><br></div><div><div>The first part of the dissertation focuses on the distributed nearest neighbor classification in big data. The sheer volume and spatial/temporal disparity of big data may prohibit centrally processing and storing the data. This has imposed a considerable hurdle for nearest neighbor predictions since the entire training data must be memorized. One effective way to overcome this issue is the distributed learning framework. Through majority voting, the distributed nearest neighbor classifier achieves the same rate of convergence as its oracle version in terms of the regret, up to a multiplicative constant that depends solely on the data dimension. The multiplicative difference can be eliminated by replacing majority voting with the weighted voting scheme. In addition, we provide sharp theoretical upper bounds of the number of subsamples in order for the distributed nearest neighbor classifier to reach the optimal convergence rate. It is interesting to note that the weighted voting scheme allows a larger number of subsamples than the majority voting one.</div></div><div><br></div><div>The second part of the dissertation extends the DiNN methods to the application in crowdsourcing. The noisy labels in crowdsourcing data and different sizes of worker data will deteriorate the performance of DiNN methods. We propose an enhanced nearest neighbor classifier (ENN) to overcome this issue. Our proposed method achieves the same regret as its oracle version on the expert data with the same size. We also propose two algorithms to estimate the worker quality if it is unknown in practice. One method constructs the estimators for worker quality based on the denoised worker labels through applying kNN classifier on expert data. Unlike previous worker quality estimation methods, which have no statistical guarantee, it achieves the same regret as the ENN with observed worker quality. The other method estimates the worker quality iteratively based on ENN, and it works well without expert data required by most previous methods.<br></div>

The Masters thesis deals with the psychosocial needs of seniors in residential care. The theoretical part characterizes the old age phenomenon as a natural part of human life. It describes the attitude of society to senior citizens and the status of the senior in the family system. The thesis focuses on the saturation of psychosocial needs of seniors within institutional care. Impact is placed on the role of a social worker in providing social help to these people. The research part detects through semi-structured interviews how the users of social services perceive the quality of their life in the retirement home. The results of the research are compared with the opinions of experts dealing with senior issues.

This diploma thesis deals with support of quality increasing process at social service provider in Domov pro seniory, Zahradní Město in Prague. The theoretical part intercepts a development of social services in context of social and legislative changes, theoretically deals with spheres which relate with change management process i.e. quality of social services, organizational culture and conflicts. With use of qualitative and quantitative methods was followed process of main aim filling of thesis i.e. quality increasing of provided social service. By focus group method was verified successfulness of planned process in praxis of social service provider. Final part of thesis contains my reflection of process from process participant view and from managerial practice view. I also give out my vision of further organization progress shortly. Considering to results of research evaluative phase it is possible to say that main aim of thesis i.e. quality increasing process of provided social service was fulfilled. It is possible to note that partial aims of diploma thesis were successfully fulfilled too i.e. describe action research process, define process pillars and barriers. KEY WORDS Quality Increasing Process, Change, Key Worker, Quality, Social Service Provider, Action Research, Organizational Culture.

The thesis discusses the conditions of admission assessment of the applicants to a social service home for the elderly . This work compares how 35 selected services home for the elderly provided by the selection of new user requirements with respect to their procedure. The thesis explains the sub concepts such as old age, quality of life, the role of the family in relation to the elderly, social work with the elderly , social service home for the elderly , the role of social worker. The research part consists of an analysis of requests for provision of social services , their attachments and general legislative documents relating to the provision of social services and the selection of a new applicant. Work also focuses on the registration of social services . Last but not least is about ethical aspects related to the selection of a new user.