Browsing by Author "Muhammad Umer"

Now showing 1 - 3 of 3

Atomistic simulation of silica-based glasses using molecular dynamics
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2017) Muhammad Umer; CIIT/FA15-RPH-026/LHR; Dr. Abdul Sattar; LHR TP 6842
Silica based glasses are being utilized ubiquitously in different disciplines of everyday life. Addition of modifiers in silica based glasses varies their physical and chemical properties. In this dissertation the preparation of silica based ternary glasses SiO2 CaO-ZrO2 using molecular dynamic simulation has been done. The structures of different silica based glasses with compositions 70SiO2-(30-x)CaO-xZrO2 (x=0,5,10,15,20,25,30) were generated using MD simulations following melt quench method. Pedone‟s potential is used to meet the requirement of molecular dynamics simulations. The radial distribution function analysis suggests that the clustering of the silica tetrahedral glass network increases with the concentration of calcium. The different concentrations of CaO and ZrO2 noticeably change the glass transition temperature of different compositions of glasses. The structural analysis of our ternary glasses equips us with the information of oxygen-silicon coordination number and the Qn species found in the prepared glasses. The appearance of different ratios of Qn species in our glasses is because of the changing concentration of CaO and ZrO2 in the composition.
Exploring Patterns and Relations in Knot Theory by Using Machine Learning
(Library Information Services, CUI Lahore, 2023) Muhammad Umer; CIIT/FA21-RMT-105/LHR; Dr. Abdul Jawad
. Machine learning is a sub-domain of AI which has manifested impressive applicability in various scientific domains, and provides different techniques that could be used to identify relations or patterns in the data. Machine learning could be used in multiple ways in analyzing and exploring knot theory. In this thesis, we will discuss how machine learning techniques could be used to find relations in knot theory, particularly, how it could be used to discover relations in different knot invariants. Briefly, given a training set {x
ULIE: Underwater Low-Light Image Enhancement Using Deep Learning
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2025) Muhammad Umer; CIIT/SP24-RCS-018/LHR; Dr. Muhammad Aksam Iftikhar Associate Professor, 55P; LHR TP 10040
Among the Underwater images captured in low-light conditions are usually suffer from severe quality degradation related to insufficient illumination, wavelength-dependent colour attenuation, scattering and noise amplification, while strongly affecting the applicability in underwater vision applications. Correcting these problems while preserving computational efficiency is critical in real-time systems and systems with limited resources underwater. This thesis introduces an efficient deep learning based approach for underwater low-light image enhancement to focus on image improvement in terms of illuminating effect, structural details preservation and color fidelity restoration. This thesis presents light-weight enhancement approach to ensure low computational complexity and a composite loss function is designed to help guide the reconstruction in terms of pixel-level reconstruction, structural similarity, perceptual consistency and color-correction. The proposed method is end-to-end trained and tested on the EUVP Dark dataset by using quantitative and qualitative evaluations. Experimental results show that the proposed approach is able to get significant improvement in illumination recovery and reconstruction accuracy, and the corresponding PSNR value of 28.52, SSIM value of 0.8433 and UIQM value of 2.79. Qualitative analysis also shows increased visibility, balanced color restoration and increased detail clarity in severely degraded underwater images. These results indicate that combining an efficient network design and a task-specific formulation of loss is a good solution for underwater low-light image enhancement, especially for real-time deployment scenarios.