Search

Traditional watermarking methods can remove a watermark from an image, making it possible to see the copyright information about the image owner or to estimate similarities using techniques such as bit error rate and normalized correlation. Deep learning is another examination field in AI, and is utilized to develop a deep network to extract objective elements and afterwards distinguish the general environment. To assure the robustness and security of computerized image watermarking, we propose a novel algorithm using convolutional generative adversarial neural networks. This research proposed a novel technique in digital watermarking, with data hiding based on segmentation and classification, using deep learning techniques. The used input images are medical images, including Magnetic Resonance Images (MRI) and Computed Tomography (CT) images, which have been processed for noise removal, smoothening and normalization. The processed image has been watermarked using the Singular Value Decomposition-based discrete wavelet transform quantization model, being segmented and classified using convolutional generative adversarial neural networks. The experimental analysis has been carried out in terms of bit error rate, Structural Similarity Index Measure (SSIM), Normalized Cross-Correlation (NCC), training accuracy, and validation accuracy. This achieved an attained bit error rate of 71%, an SSIM of 56%, a Normalized Cross-Correlation of 71%, a training accuracy of 98%, and a validation accuracy of 95%. [ABSTRACT FROM AUTHOR]

Nowadays, there is a growing demand for information security and security rules all across the world. Intrusion detection (ID) is a critical technique for detecting dangers in a network during data transmission. Artificial Intelligence (AI) methods support the Internet of Things (IoT) and smart cities by creating gadgets replicating intelligent behavior and enabling decision making with little or no human intervention. This research proposes novel technique for secure data transmission and detecting an intruder in a biometric authentication system by feature extraction with classification. Here, an intruder is detected by collecting the biometric database of the smart building based on the IoT. These biometric data are processed for noise removal, smoothening, and normalization. The processed data features are extracted using the kernel-based principal component analysis (KPCA). Then, the processed features are classified using the convolutional VGG−16 Net architecture. Then, the entire network is secured using a deterministic trust transfer protocol (DTTP). The suggested technique's performance was calculated utilizing several measures, such as the accuracy, f-score, precision, recall, and RMSE. The simulation results revealed that the proposed method provides better intrusion detection outcomes. [ABSTRACT FROM AUTHOR]

The present study aims to measure the contributions of Prof. Anurag Kumar, who served as the Director at the Indian Institute of Science (IISc) in Bengaluru between August 2014 to July 2020. He has contributed 181 publications during his 36 years of career. He has published his majority of publications 171 (94.48%) in collaboration; most active collaborators with Prof. Anurag Kumar are Altman E. with (17) publications, Kuri Joy (15), Anand (14), and Singh (12). His highest Collaboration Coefficient found is 0.73 in 2013, and the highest Modified Collaboration Coefficient is 1.33 in the year 2018. The highest degree of collaboration observed for Prof. Anurag Kumar was 1.00. The highest Collaborative Index of Prof. Anurag found is 4.75 in the year 2016. His publications received 2595 citations so far, with 14.3 citations for each publication and an average citation of 72.08 per year. He has produced most of his publications in the field of computer science (45.9%). He preferred conference papers as his communication channel, where he published 100 (55.24%) papers out of 181. Prof. Anurag Kumar has contributed the highest (62) publication between 2005-2010, and he has published his first publication at the age of 30. [ABSTRACT FROM AUTHOR]