A multi-pretraining U-Net architecture for semantic segmentation by Cagla Copurkaya (22502042)

“…In this research, we propose and evaluate a modified version of a deep learning algorithm called U-Net architecture for partitioning histopathological images. …”

Machine Learning-based X-Ray Projection Interpolation for Improved 4D-CBCT Reconstruction by Ramesh, Jayroop

Get full text

CNN and HEVC Video Coding Features for Static Video Summarization by Issa, Obada

“…During coding, 64 proposed features were generated from the coder for each frame. Additionally, we converted the original YUVs of the raw videos into RGB images and fed them into pretrained CNN networks for feature extraction. …”
Get full text

From Collatz Conjecture to chaos and hash function by Masrat Rasool (17807813)

“…<p>The non-linear property of Chaos is a promising approach to information security, and many accomplishments have been made by combining Chaos with several sub-security domains, including chaos-based stream ciphers, block ciphers, image encryption, and hash functions. Most Chaos-based hash functions are insecure or inefficient due to their dependence on complex, attacked multi-dimensional maps or uncertain, weak one-dimensional maps like logistic and tent. …”