Browsing Department of Computational and Data Sciences (CDS) by thesis submitted date"2022"
Now showing items 1-20 of 22
-
Accelerating Estimation of Perfusion Maps in Contrast X-ray Computed Tomography using Many-core CPUs and GPUs
X-ray Computed Tomography (CT) perfusion imaging is a non-invasive medical imaging modality that has been established as a fast and economical method for diagnosing cerebrovascular diseases such as acute ischemia, sub-arachnoid ... -
Augmenting Hyperspectral Image Unmixing Models Using Spatial Correlation, Spectral Variability, And Sparsity
Hyperspectral imaging sensors sample sunlight reflected from different targets on Earth's surface by utilising a series of contiguous narrow spectral channels. The higher spectral resolution of hyperspectral images (HSIs) ... -
Communication Overlapping Krylov Subspace Methods for Distributed Memory Systems
Many high performance computing applications in computational fluid dynamics, electromagnetics etc. need to solve a linear system of equations $Ax=b$. For linear systems where $A$ is generally large and sparse, Krylov ... -
Data-efficient Deep Learning Algorithms for Computer Vision Applications
The performance of any deep learning model depends heavily on the quantity and quality of the available training data. The generalization of the trained deep models improves with the availability of a large number of ... -
Deep Convolutional and Generative Networks for Ocean Synoptic Feature Extraction and Super Resolution from Remotely Sensed Images
Accurate extraction of Synoptic Ocean Features and Downscaling of Ocean Features is crucial for climate studies and the operational forecasting of ocean systems. With the advancement of space and sensor technologies, the ... -
Deep Learning in Computer Vision: Studies in Neuro-image Segmentation and Satellite Image Super-resolution
Single image super-resolution (SR) has been a topic of great interest in the computer vision and deep learning community and has found applications in many areas including quality enhancement of satellite images. As the ... -
Development of Novel Deep Learning Methods for Fast-MRI: Anatomical Image Reconstruction to Quantitative Imaging
In medical imaging, the task of estimating interpretable anatomical images from raw scanner data - based on underlying physical principles - is known as an "inverse problem". The solution to such inverse problems can be ... -
Epistasis Detection and Phenotype Prediction in GWAS Using Machine Learning Methods
Genome-wide association studies (GWAS) are used to find the association between genetic variants, Single Nucleotide Polymorphisms (SNPs), and phenotypic traits or diseases in a population. The number of GWAS has increased ... -
INTERPIN: identifying INtrinsic transcription TERminators, hairPINs in bacteria
The conversion of DNA to RNA through transcription is an important step in the life cycle of every organism. It ensures that the genetic information in DNA is converted through RNA into instructions/blueprints for the ... -
Landmark Estimation and Image Synthesis Guidance using Self-Supervised Networks
The exponential rise in the availability of data over the past decade has fuelled research in deep learning. While supervised deep learning models achieve near-human performance using annotated data, it comes with an ... -
Learning to Perceive Humans From Appearance and Pose
Analyzing humans and their activities takes a central role in computer vision. This requires machine learning models to encapsulate both the diverse poses and appearances exhibited by humans. Estimating the 3D poses of ... -
Methods for Improving Data-efficiency and Trustworthiness using Natural Language Supervision
Traditional strategies to build machine learning based classification systems employ discrete labels as targets. This limits the usefulness of such systems in two ways. First, the generalizability of these systems is limited ... -
Mitigating Domain Shift via Self-training in Single and Multi-target Unsupervised Domain Adaptation
Though deep learning has achieved significant successes in many computer vision tasks, the state-of-the-art approaches rely on the availability of a large amount of labeled data for supervision, collection of which is ... -
Novel Neural Architectures based on Recurrent Connections and Symmetric Filters for Visual Processing
Artificial Neural Networks (ANN) have been very successful due to their ability to extract meaningful information without any need for pre-processing raw data. First artificial neural networks were created in essence to ... -
Numerical simulations of hydrogen flames in reheat gas turbine combustor: effect of pressure scaling and fuel blending
With a goal toward a net-zero energy supply, hydrogen, hydrogen-enriched natural gas, and biofuels, which reduce the carbon footprint, are actively being considered for firing stationary gas turbine engines. In this regard, ... -
Optimizing the Interval-centric Distributed Computing Model for Temporal Graph Algorithms
Graphs with temporal characteristics are increasingly becoming prominent. Their vertices, edges and attributes are annotated with a lifespan, allowing one to add or remove vertices and edges. Such graphs can grow to millions ... -
Prediction of Dynamical Systems by Constraining the Dynamics on the Observational Manifold
Evolution models of dynamical systems posed as differential equations generally do not include all the factors affecting the system. This leads to a mismatch between the model prediction and the observations. In this work, ... -
Relating Representations in Deep Learning and the Brain
Deep Neural Networks (DNN) inspired by the human brain have redefined the state-of-the-art performance in AI during the past decade. Much of the research is still trying to understand and explain the function of these ... -
Scalable Asynchrony-Tolerant PDE Solver for Multi-GPU Systems
Partial differential equations (PDEs) are used to model various natural phenomena and engineered systems. At conditions of practical interest, these equations are highly non-linear and demand massive computations. Current ... -
Self-Supervised Domain Adaptation Frameworks for Computer Vision Tasks
There is a strong incentive to build intelligent machines that can understand and adapt to changes in the visual world without human supervision. While humans and animals learn to perceive the world on their own, almost ...