Algoritmalar kullanılarak kirlilik ve petrol tüketimi arasındaki korelasyon ilişkisinin analizi (spektral kümeleme ve K-ortalaması)

Clustering can be considered the most significant unsupervised learning methods that reveal similar behaviors (sets) on large sets of data. Clustering is the process of organizing objects into groups that are similar in some way to their members. Spectral clustering data points as nodes of a connected graph and clusters are found by partitioning this graph, based on its spectral decomposition, into subgraphs. K - means assembly: Divide objects into k groups so that some measurements are minimized relative to the middle points of the clusters. In this thesis, we have applied both of algorithms (spectral clustering and k-mean) on data from the life process and these data are statistical data. The field of data is the quantities of pollution and petroleum consumption. The spectral clustering algorithm was applied several times and k-mean was applied several times and the best result was compared and the best classification was also obtained. Keywords: Clustering ,Spectral Clustering ,K-mean ,pollution, petroleum