Spectral Analysis of Symmetric and Anti-Symmetric Pairwise Kernels

This work investigates theoretical properties of symmetric and anti-symmetric kernels. First chapters give an overview of the theory of kernels used in supervised machine learning. Central focus is on the regularized least squares algorithm, which is motivated as a problem of function reconstruction through an abstract inverse problem. Brief review of reproducing kernel Hilbert spaces shows how kernels define an implicit hypothesis space with multiple equivalent characterizations and how this space may be modified by incorporating prior knowledge. Mathematical results of the abstract inverse problem, in particular spectral properties, pseudoinverse and regularization are recollected and then specialized to kernels. Symmetric and anti-symmetric kernels are applied in relation learning problems which incorporate prior knowledge that the relation is symmetric or anti-symmetric, respectively. Theoretical properties of these kernels are proved in a draft this thesis is based on and comprehensively referenced here. These proofs show that these kernels can be guaranteed to learn only symmetric or anti-symmetric relations, and they can learn any relations relative to the original kernel modified to learn only symmetric or anti-symmetric parts. Further results prove spectral properties of these kernels, central result being a simple inequality for the the trace of the estimator, also called the effective dimension. This quantity is used in learning bounds to guarantee smaller variance.

A substantive theory of the realization of stroke patients’ dignity in hospital care

Dignity is seen important in health care context but considered as a controversial and complex concept. In health care context, it is described as being influenced by for example autonomy, respect, communication, privacy and hospital environment. Patient dignity is related to satisfaction with care, reduced stress, better confidence in health services, enhanced patient outcomes and shorter stay in a hospital. Stroke patients may struggle for dignity as being dependent on other people has impact on the patients’ self-image. In all, stroke patients are very specific patient group and considered vulnerable from emotional aspect. Therefore study findings from other patient groups in the area of ethical problems cannot be transferred to the stroke patients. This master’s thesis consists of two parts. The first part is the literature review of patients’ dignity in hospital care. The literature defined dignity and described factors promoting and reducing it. The results were ambiguous and thus a clear understanding was not able to create. That was the basis for the second part of the master’s thesis, the empirical study. This part aimed to develop theoretical construction to explore the realization of stroke patients’ dignity in hospital care. The data of the second part was collected by interviewing 16 stroke patients and analyzed using the constant comparison of Grounded Theory. The result was ‘The Theory of Realization of Stroke Patients’ Dignity in Hospital Care’ which is described not only in this master’s thesis but also as a scientific article. The theory consists of the core category, four generic elements and five specific types on realization. The core category emerged as ‘dignity in a new situation’. After a stroke, dignity is defined in a new way which is influenced by the generic elements: life history, health history, individuality and a stroke. Stroke patient’s dignity is realized through five specific types on realization: person related dignity type, control related dignity type, independence related dignity type, social related dignity type and care related dignity type. The theory points out possible special characteristics of stroke patients’ dignity in control related dignity type and independence related dignity type. Before implementing the theory, the relation between the core category, generic elements and specific types on realization needs to be studied further.