Abstract This paper suggests a revolutionary deep learning method using a dynamic deep auto-encoder for improving the performance of indexing the feature vectors of images by centroid updation. Feature vectors such as color, semantic, and spatial local binary pattern are extracted from the images for content-based image retrieval. The owner encrypts the images for protection using elliptic curve cryptography before uploading them to the cloud. A black hole entropic fuzzy clustering with Tversky indexing is used to retrieve similar information. When the new training image is matched with any of the centroid then the centroid gets updated by using dynamic deep auto-encoder. During the auto-encoder phase, the conflicted data points are dedicated to reconstruction and the reliable data points are helpful to centroid updation. The suggested BHE fuzzy clustering with dynamic deep auto-encoder approach fared better than the current methods, achieving the best accuracy of 97.605%, the highest $\boldsymbol{F_{1}}$ score of 90.210%, better precision of 90.001%, and the highest recall of 95.149%.

Abstract In this paper, initially, message intensities are used to create two encoding tables: an index and a code sequence. The table is then updated with $n$ secret data encoded into it. If the code sequence of the second encoding table matches the code sequence of the preceding or succeeding half of the two encoding tables, the second encoding table is folded. The folding is done when maximum intensity occurs in the utmost succeeding part of the two encoding tables. Finally, using the combination orientation approach, the encoded indices are embedded in the stego images. In the extraction phase, using the two stego images and the encoding with the combination orientation method, the encoded indices are obtained. The decoding is performed to extract the secret message as well as the cover image and there is no occurrence of overflow and underflow problems. It has a high visual quality and a high embedding capacity. The proposed technique achieved a maximum $\mathrm{PSNR}$ of $49.49$dB and a $648\ 242$-bit embedding capacity. When compared to traditional techniques, the experimental results show that the proposed method outperforms them.

Abstract The face recognition (FR) process identifies or confirms a person with the help of images and videos. The traditional aging FR (AFR) method encounters numerous issues as a result of age-related biological transformation. An adaptive fully recurrent deep neural learning (AFRDNL) technique is presented in this research to improve FR accuracy (FRA) with minimal time complexity (TC). Feature extraction and classification are two processes included in the proposed technique. The AFRDNL technique gathers facial images from the database and trains the face images with three layers. To learn the facial features, three hidden layers are employed in the AFRDNL technique. Finally, the AFRDNL technique utilizes the Gaussian activation function for matching extracted testing features with earlier saved training features. This process is repeated until a minimal training error with a higher FRA is achieved. Experimental evaluation is carried out with three image datasets like Face and Gesture Recognition Research Network, MORPH and Cross-Age Labeled faces in the Wild (CALFW) datasets using different metrics, such as FRA, false-positive rate (FPR), TC and F1score. The experimental results confirm that the AFRDNL technique effectively increases the FRA and F1score and minimizes the FPR and TC more effectively than the state-of-the-art methods.

Personal health record (PHR) system has become the most important platform to exchange health information, in which the patients can share and manage personal health information more effectively in cloud storage. However, the cloud server is unreliable, and the secure data of users may be disclosed. Therefore, a secure data sharing mechanism is developed in this research using the proposed session password, data access key, and circular interpolation (SKC)-based data-sharing approach for the secure sharing of PHR in the cloud. The proposed SKC-based data sharing approach provides high efficiency and high-security guarantee. It effectively satisfies various security properties, such as tamper resistance, openness, and decentralization. The proposed SKC-based data sharing approach is the reliable mechanism created for the doctors to share the PHR and to access the patient historical data while meeting the privacy preservation.