Geometrik ve Topolojik Çıkarımlar: Topolojik Veri Analizi
Loading...

Date
2022
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Open Access Color
OpenAIRE Downloads
OpenAIRE Views
Abstract
Topolojik veri analizi (TDA), topoloji tekniklerini kullanarak veri kümelerinin analizine yönelik bir yaklaşımdır. Yüksek boyutlu, eksik ve gürültülü veri kümelerinden bilgi çıkarmak genellikle zordur. Yüksek boyutlu verilerin görselleştirilmesini sağlayan TDA, bu tür verileri seçilen belirli metriğe duyarlı olmayan bir şekilde analiz etmek için genel bir çerçeve sağlar. Topolojik veri analizinin (TDA), amacı verilerin topolojik ve geometrik yapısını anlamaktır. Bu amaç doğrultusunda matematiksel ve algoritmik araçlar sağlar. Günümüzde gelişmekte olan bir alandır. Verilerden çıkarılan topolojik bilgiler göz önüne alınarak matematiksel temellere odaklanılır. Böyle topolojik analizlerin, başka yollarla kolayca elde edilemeyen, veri kümeleri hakkında nitel bilgi verebileceği artık yaygın olarak kabul edilmektedir. Bu tez, bu yeni alana kısa bir giriş sağlar. Bu tezde Topolojik Veri Analizinin ana hatlarından bahsedilmiş ve R STUDIO programı vasıtasıyla Boğaziçi Üniversitesi Kandilli Rasathanesi ve Deprem Araştırma Enstitüsü (KRDAE) 'nden alınan veri seti kullanılarak bir uygulama yapılmıştır.
Topological data analysis (TDA) is an approach to the analysis of datasets using topology techniques. It is often difficult to extract information from high-dimensional, incomplete, and noisy datasets. By enabling the visualization of high-dimensional data, TDA provides a general framework for analyzing such data in a way that is insensitive to the particular metric chosen. The purpose of topological data analysis (TDA) is to understand the topological and geometric structure of data. It provides mathematical and algorithmic tools for this purpose. It is a developing field today. Considering the topological information extracted from the data, the focus is on mathematical foundations. It is now widely accepted that such topological analyzes can yield qualitative information about datasets that are not easily obtained by other means. This thesis provides a brief introduction to this new field. In this thesis, the main lines of Topological Data Analysis were mentioned and an application was made using the data set obtained from Boğaziçi University Kandilli Observatory and Earthquake Research Institute (KRDAE) through the R STUDIO program.
Topological data analysis (TDA) is an approach to the analysis of datasets using topology techniques. It is often difficult to extract information from high-dimensional, incomplete, and noisy datasets. By enabling the visualization of high-dimensional data, TDA provides a general framework for analyzing such data in a way that is insensitive to the particular metric chosen. The purpose of topological data analysis (TDA) is to understand the topological and geometric structure of data. It provides mathematical and algorithmic tools for this purpose. It is a developing field today. Considering the topological information extracted from the data, the focus is on mathematical foundations. It is now widely accepted that such topological analyzes can yield qualitative information about datasets that are not easily obtained by other means. This thesis provides a brief introduction to this new field. In this thesis, the main lines of Topological Data Analysis were mentioned and an application was made using the data set obtained from Boğaziçi University Kandilli Observatory and Earthquake Research Institute (KRDAE) through the R STUDIO program.
Description
Keywords
Matematik, Barkod, Homoloji, K-En Yakın Komşu Algoritması, Topoloji, Veri Analizi, Mathematics, Barcode, Homology, K-Nearest Neighbor Algorithm, Topology, Data Analysis
Turkish CoHE Thesis Center URL
Fields of Science
Citation
WoS Q
Scopus Q
Source
Volume
Issue
Start Page
End Page
64
