This dissertation proposes a novel theoretical framework for the data partitioning problem in computer vision and machine learning. The framework is based on level set methods that are derived from variational calculus and involve a curve-based objective function which integrates both boundary and region based information in a generic form. The proposed approaches within the framework provide original solutions to two important problems in variational methods, namely parameter tuning and information fusion, collectively termed Learning Level Sets in this thesis. Moreover, a novel pattern classification algorithm, namely Level Learning Sets, is proposed to classify any general dataset, including sparse and non sparse data. It is based on the same optimisation process of the objective function directly related to the curve propagation theory used in level set theory. The proposed approach learns the knowledge required for parameter tuning and information fusion in level set methods using machine learning techniques. It uses acquired knowledge to automatically perform parameter tuning and information fusion in level set methods. In the case of pattern classification, variational methods using level set theory optimise decision boundary construction in feature space. Consequently, the optimised values of the objective level set function over the feature space represent the model for pattern classification. The proposed automatic parameter tuning and information fusion method embedded in the level set method framework has been employed to provide original solutions to image segmentation and object extraction in computer vision. On the other hand, the Level Learning Set has been extended and applied to a variety of pattern classification problems". Several experimental results for each of the above methods are provided, demonstrating the effectiveness of the proposed solutions and indicating the potential of the automatic and dynamic tuning and fusion approaches as well as the Level Learning Set model.

Выпускная квалификационная работа “ Cравнительный анализ учебной и профессиональной мотивации российских и китайских студентов” в форме магистерской диссертации выполнена на 107 листах (формат А4, шрифт Times New Roman, размер шрифта 14, интервал между строками 1,5). Количество таблиц – 0 (без учета вложений). Количество рисунков – 66 (без учета вложений). Ключевые термины: мотивация к обучению; профессиональная мотивация; уровень обучения; поведение при обучении; образовательный подход; культурные различия; планирование карьеры; и курсы планирования карьеры. Представленная магистерская диссертация состоит из введения, трех глав, заключения, библиографического списка и приложений. Во введении описывается актуальность темы магистерской диссертации, рассматриваются цель и основные задачи исследования, определяются объект и предмет исследования, формируется гипотеза исследования, а также устанавливается перечень методов, участвующих в исследовании. В первой главе диссертации будут рассмотрены теоретические основы учебной и профессиональной мотивации современных студентов вузов и связь между ними; влияние различных культурных традиций и образовательных подходов на студентов. Во второй главе определяются цель и методология исследования, а также подробное описание выборки для исследования. В третьей главе результаты представлены в виде графиков и диаграмм в последовательном порядке, а результаты анализируются индивидуально, с личными мнениями и рекомендациями. В заключение рассмотрена существующая система образования и профессиональной подготовки университета, и предложены решения для улучшения, а также решения проблем в контексте текущей ситуации. / Final qualifying work “Comparative characteristics of learning and professional motivation of Russian and Chinese students” in the form of Master thesis is performed on 107 sheets (A4 format, font Times New Roman, font size 14, 1,5 line spacing), excluding attachments. Number of tables – 0 (excluding attachments). The number of figures – 66 (excluding attachments). Key terms: learning motivation; professional motivation; learning level; learning behavior; educational approach; cultural differences; career planning; and career planning courses. The submitted master's thesis consists of an introduction, three chapters, a conclusion, a bibliographical list, and appendices. The introduction describes the relevance of the topic of the master's thesis, considers the purpose and main objectives of the research, defines the object and subject of the research, forms the hypothesis of the research, as well as establishes a list of methods involved in the research. In the first chapter of the dissertation, the theoretical foundations of learning and professional motivation of modern university students and the connection between them; the influence of different cultural backgrounds and educational approaches on students will be considered. In the second chapter, the purpose and methodology of the study are determined, as well as a detailed description of the sample for the study. In the third chapter, the findings are produced in the form of graphs and charts in a sequential manner, and the results are analyzed individually with personal opinions and recommendations. In the conclusion, the existing education and the training system of the university as well as the vocational training system are considered, and solutions for improvement as well as solutions to the problems also are proposed in the context of the current situation.