Department of Computational and Data Sciences (CDS)
Recent Submissions
-
Intelligent Methods for Cloud Workload Orchestration in Data Centers
Cloud workload orchestration plays a pivotal role in optimizing the performance, resource utilization, and cost effectiveness of applications in data centers. As modern businesses and IT operations are migrating their ... -
An importance sampling in N Sphere Monte Carlo and its performance analysis for high dimensional integration
Statistical methods for estimating integrals are indispensable when the number of dimensions (parameters) become greater than ~ 10, where numerical methods are unviable in general. Well-known statistical methods like ... -
A co-kurtosis tensor based featurization of chemistry for scalable combustion simulations
For turbulent reacting flow systems, identification of low-dimensional representations of the thermo-chemical state space is vitally important, primarily to significantly reduce the computational cost of device-scale ... -
An arbitrary lagrangian eulerian volume of fluid method for floating body dynamics simulation
The floating body dynamics is treated as a Fluid-Structure Interaction (FSI) problem. A FSI problem is where the forces from the fluid move/deform the interacting structure, and the movement of the structure, in turn, ... -
Sparsification of Reaction-Diffusion Dynamical Systems on Complex Networks
Graph sparsification is an area of interest in computer science and applied mathematics. Spar- sification of a graph, in general, aims to reduce the number of edges in the network while preserving specific properties of ... -
End-to-end Resiliency Analysis Framework for Cloud Storage Services
Cloud storage service brought the idea of a global scale storage system available on-demand and accessible from anywhere. Despite the benefits, resiliency remains one of the key issues that hinder the wide adaptation of ... -
Development of Novel Deep Learning Models with Improved Generalizability for Medical Image Analysis
Medical imaging is a process of visualization of disease/tissue in a non-invasive manner. Several imaging techniques like computed tomography (CT), magnetic resonance imaging (MRI), optical coherence tomography (OCT), and ... -
Abstractions and Optimizations for Data-driven Applications Across Edge and Cloud
Modern data driven applications have a novel set of requirements. Advances in deep neural networks (DNN) and computer vision (CV) algorithms have made it feasible to extract meaningful insights from large-scale deployments ... -
Constrained Stochastic Differential Equations on Smooth Manifolds.
Dynamical systems with uncertain fluctuations are usually modelled using Stochastic Differential Equations (SDEs). Due to operation and performance related conditions, these equations may also need to satisfy the constraint ... -
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 ... -
Data Driven Stabilization Schemes for Singularly Perturbed Differential Equations
This thesis presents a novel way of leveraging Artificial Neural Network (ANN) to aid conventional numerical techniques for solving Singularly Perturbed Differential Equation (SPDE). SPDEs are challenging to solve with ... -
Leveraging KG Embeddings for Knowledge Graph Question Answering
Knowledge graphs (KG) are multi-relational graphs consisting of entities as nodes and relations among them as typed edges. The goal of knowledge graph question answering (KGQA) is to answer natural language queries posed ... -
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) ... -
Assessing protein contribution to phenotypic change using short, coarse grained molecular dynamics simulations
Understanding the functional mapping between genotype and phenotype is an important problem that has ramifications for various diseases. Various existing computational methods can infer these disease-related functional ... -
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 ... -
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 ... -
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 ... -
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 ... -
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 ... -
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 ...