Loading

Dimensionality Reduction on Cloud Images Based on Various Climate Zones
L. Gowri1, K. R. Manjula2 

1L. Gowri, School of Computing SASTRA Deemed University, Thanjavur, (Tamil Nadu), India.
2Dr. K. R. Manjula, School of Computing SASTRA Deemed University, Thanjavur, (Tamil Nadu), India.

Manuscript received on 03 March 2019 | Revised Manuscript received on 09 March 2019 | Manuscript published on 30 July 2019 | PP: 3288-3292 | Volume-8 Issue-2, July 2019 | Retrieval Number: B3043078219/19©BEIESP | DOI: 10.35940/ijrte.B3043.078219
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: In recent decades, cloud image classification has become a research hotspot in the field of weather forecasting. Initially, cloud images that fall on various climate zones are categorized based on their regions. Dimensionality reduction is performed in the cloud images by applying Principal Components Analysis (PCA) to enhance the classification accuracy of cloud images. The proposed system uses the training set to learn the features of cloud images and classifies the test case images into low, medium and high. The experimental results are obtained by implementing the INSAT weather image data set using MATLAB tool. The proposed methodology can be used in various applications like Rainfall Prediction, Oceanography and Cyclone Forecasting.
Keywords: INSAT Weather Satellite Images, PCA, Principle Features,

Scope of the Article: Cloud Computing