Satellite images have gained a wide popularity in the field of content-based image retrieval. A massive amount of these images are collected every year due to the high availability of satellites and computer technologies. However, extracting user-specific content from these images still remains a primary concern due to the presence of semantic gap. This limits the capabilities of CBIR. Therefore, an effective and efficient method is required for image retrieval. This paper puts forward a semantic-based image retrieval approach along with the advantages of hashing for better feature extraction and precise retrieval. Hashing accelerates the quality of similarity search among images by generating unique imagehash codes .This approach also aims to scale down the problems related to semantic gap for better retrieval results. General TermsRemote sensing, Satellites, Data sets, Content based image retrieval and Algorithms.
Privacy is one of the important issues now days as privacy is linked with multidimensional issues; security, sentiment, fear, emotions, threats etc. Protecting privacy is as much as data utilization. In this day and age, data is getting generated largely by various industries. Medical industry is one of them. Providing safe access controls and privacy preservation are the primary concerns in the development of medical applications. Medical data possess sensitive information. According to the author, privacy should be preserved at all levels; storage level, to view level to knowledge discovery level. At view level, very limited approaches are proposed to protect the privacy of the medical data. This paper implements Fuzzy C means approach to protect the sensitive data while viewing blood donor data online. In this paper, a sample blood donor records are extracted to categorize the data into high sensitive data and low sensitive data using fuzzy C means rules. Subsequently, the model teaches the underlying relations to perform categorization based on the input. This paper describes the experiment in view of privacy preserving data mining. The experiment is simulated using MATLAB and shows satisfactory result.
Privacy preserving is utmost important in medical applications. Cryptography has numerous techniques to safe guard the privacy of the data. It is practice to use private key for encryption and public key for decryption in the area of cryptography. Conventionally, without decryption, data usability is difficult. However, the complications outweigh the private and public keys. This paper presents privacy preserving model based on Homomorphic encryption technique and model evaluation using classification technique. The homomorphic model highlights usability of the data without decryption. The objective of this paper is to show how the encrypted data is preserving underlying relations through classification tree. This paper presents two parts: Part-I describes the model building on medical data using PSO optimization and filer based coefficient matrix (for encryption) to protect privacy of the data and part-II describes model evaluation using classification tree and clustering technique. The performance of the encryption is tested using predictive modelling technique (classification tree technique) and K-Means clustering technique, to assess whether the underlying relations are preserved in the encrypted data. The experimental results show that the underlying classification accuracy of encrypted data and source data (non-encrypted) is just varying by +/-5%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.