Use of proximal sensor for soil classes separation applying Principal Component Analysis (PCA)

The spectrally active components of the soil allow the realization of integrative analyzes of soil aspects such as their classification. The purpose of this study was to evaluate the separation of soil classes from spectral reflectance data using principal components analysis (PCA). The study was carried out in the Aiuaba Experimental Basin located in the municipality of Aiuaba, Ceará, Brazil. Soil samples were collected in Ustalfs, Ustults and Ustorthents profiles. The samples were submitted to spectral analysis by a spectroradiometer and, subsequently, to PCA. Principal components were used to identify which of them contribute more significantly to the separation of the soil classes analyzed, based on their relationship with the soil attributes using a two-dimensional graphical analysis. From the examination of spectral behavior data of the different soil classes, the use of PCA allowed the separation of the classes Ustorthents, Ustalfs and Ustults from each other.

Study of the Clustering Algorithms for Hyper Spectral Remote Sensing Images

The data taken from the hyperspectral images are discrete and hard to classify because they are arranged in the contiguous spectral bands. We can easily detect and classify the data from the spectral images if the number of attributes in the images is very little. But it is very difficult to segregate the data from the images if the numbers of classes are more. To make the segregation easy we implement the procedure that utilizes a clustering algorithm. This paper comprises of two sections, firstly to perform unsupervised learning using different types of clustering algorithms and secondly, to compare the efficiency of the resultant clustering of these different methods to prove that which clustering method is best suitable in reading the hyperspectral imaging data. For this I have used these clustering algorithms, they are DBSCAN, MiniBatch K-Means, K-Means. By comparing these techniques I surmised that the K-Means is better for using the HyperSpectral Imaging data. To perform these calculations I used the Matlab data set from the Computational Intelligence Group.