No abstract

Cloud-based computation is known as the source architecture of the upcoming generation of IT enterprise. In context to up-coming trade solutions, the Information Technology sections are established under logical, personnel, and physical control, it transfers application software and large database to appropriate data centers, where security and management of database with services are not trustworthy fully. So this process may face many challenges towards society and organizations and that not been well understood over a while duration. This becomes one of the major challenges days today. So in this research, it focuses on security-based data storage using cloud, which plays one of the important aspects bases on qualities of services. To assure user data correctness in the cloud system, a flexible and effective distributed technique with two different salient features was examined by utilizing the token called homomorphic with erasure-coded data for distributed verification, based on this technique it achieved error data localization and integration of storage correctness. Also, it identifies server misbehaving, efficient, and security-based dynamic operations on data blocking such as data append, delete, and update methods. Performance analysis and security show the proposed method is more effective resilient and efficient against Byzantine failure, even server colluding attacks and malicious data modification attacks.

Background: Researchers have developed various algorithms to identify the occurrence of an oil spill in these oceans. However, knowing the type of oil that is spilled in the ocean is important to assess and plan the restoration process. To predict the type of oil that is spilled in the ocean by using machine learning techniques. Fifty satellite images of three types of an oil spill, namely petroleum, crude oil, and diesel were examined to identify the type of oil spill over the affected area. The oil spills were initially identified from the images using K-Nearest Neighbor algorithm. Color-based, Statistical, Textural and Geographical features are extracted after applying various types of wavelets to obtain the features relevant to the physical parameters and type of oil in the ocean. The features were then trained and classified using K-Nearest Neighbor algorithm to identifying the type of oil. Methods: For wavelet analysis (Daubechies analysis db1, db2, db3, db4, db5, db6, db7, db8, db9, db10) and machine learning (k-nearest neighbor algorithm) applied to optimize the oil spill feature sets. Features included color-based, statistical, texture and geological features. This experiment was conducted on SAR images. The features were classified using a k-nearest neighbor algorithm. Seventy percent of features used for training and thirty percent for testing. Results: The results show that oil spill classification achieved by wavelet transforms and machine learning algorithms outperformed very well with similar parameter settings, especially with 70% training data and 30% testing data using confusion matrix. It also represents 99% accuracy for petrol oil using Daubechies 5 analysis which indicates better characterization of oil spills. Results denote oil spill detection using Synthetic Aperture Radar (SAR) remote sensing which provides an excellent tool in oil spill characterization various features can be extracted from SAR data set.

No abstract

No abstract