Vikas Singh
YOU?
Author Swipe
View article: Attenuation of malignant phenotype of glioblastoma following a short course of the pro-oxidant combination of Resveratrol and Copper
Attenuation of malignant phenotype of glioblastoma following a short course of the pro-oxidant combination of Resveratrol and Copper Open
View article: FedAlign: Federated Domain Generalization with Cross-Client Feature Alignment
FedAlign: Federated Domain Generalization with Cross-Client Feature Alignment Open
Federated Learning (FL) offers a decentralized paradigm for collaborative model training without direct data sharing, yet it poses unique challenges for Domain Generalization (DG), including strict privacy constraints, non-i.i.d. local dat…
View article: Studies on varietal performance of Morus on growth and economic parameters of mulberry silkworm Bombyx mori Linn
Studies on varietal performance of Morus on growth and economic parameters of mulberry silkworm Bombyx mori Linn Open
View article: A Modified Point-Estimate-Based Probabilistic Load Flow Approach for Improving Tail Accuracy in Wind-Integrated Power Systems
A Modified Point-Estimate-Based Probabilistic Load Flow Approach for Improving Tail Accuracy in Wind-Integrated Power Systems Open
View article: AT-2FF: Adaptive Type-2 Fuzzy Filter for De-noising Images Corrupted with Salt-and-Pepper
AT-2FF: Adaptive Type-2 Fuzzy Filter for De-noising Images Corrupted with Salt-and-Pepper Open
Noise is inevitably common in digital images, leading to visual image deterioration. Therefore, a suitable filtering method is required to lessen the noise while preserving the image features (edges, corners, etc.). This paper presents the…
View article: INCIDENCE OF SINO NASAL MUCORMYCOSIS IN ACTIVE & POST COVID- 19 PATIENTS AT A DISTRICT LEVEL HOSPITAL – A PROSPECTIVE STUDY
INCIDENCE OF SINO NASAL MUCORMYCOSIS IN ACTIVE & POST COVID- 19 PATIENTS AT A DISTRICT LEVEL HOSPITAL – A PROSPECTIVE STUDY Open
Objective: To study the incidence of sinonasal mucormycosis in active and post COVID-19 patients in a district-level hospital in India. Study Design: A prospective, interventional cohort study conducted from April 2021 to January 2022. Set…
View article: Patterns of care in of craniopharyngioma: outcomes following multimodality approach of surgery and radiation therapy
Patterns of care in of craniopharyngioma: outcomes following multimodality approach of surgery and radiation therapy Open
View article: An Online Riemannian PCA for Stochastic Canonical Correlation Analysis.
An Online Riemannian PCA for Stochastic Canonical Correlation Analysis. Open
We present an efficient stochastic algorithm (RSG+) for canonical correlation analysis (CCA) using a reparametrization of the projection matrices. We show how this reparametrization (into structured matrices), simple in hindsight, directly…
View article: Neural TMDlayer: Modeling Instantaneous flow of features via SDE Generators
Neural TMDlayer: Modeling Instantaneous flow of features via SDE Generators Open
We study how stochastic differential equation (SDE) based ideas can inspire new modifications to existing algorithms for a set of problems in computer vision. Loosely speaking, our formulation is related to both explicit and implicit strat…
View article: An Online Riemannian PCA for Stochastic Canonical Correlation Analysis
An Online Riemannian PCA for Stochastic Canonical Correlation Analysis Open
We present an efficient stochastic algorithm (RSG+) for canonical correlation analysis (CCA) using a reparametrization of the projection matrices. We show how this reparametrization (into structured matrices), simple in hindsight, directly…
View article: Deep learning based optimum fault diagnosis of electrical and mechanical faults in induction motor
Deep learning based optimum fault diagnosis of electrical and mechanical faults in induction motor Open
Among all the motors Induction motor (IM) plays a vital role in industry and the demand for their reliability and safe operation is increasing day by day. They are reliable but they do wear out if not maintained timely which in turn will l…
View article: Connecting What to Say With Where to Look by Modeling Human Attention Traces
Connecting What to Say With Where to Look by Modeling Human Attention Traces Open
We introduce a unified framework to jointly model images, text, and human attention traces. Our work is built on top of the recent Localized Narratives annotation framework [30], where each word of a given caption is paired with a mouse tr…
View article: Graph Neural Networks to Predict Customer Satisfaction Following Interactions with a Corporate Call Center
Graph Neural Networks to Predict Customer Satisfaction Following Interactions with a Corporate Call Center Open
Customer satisfaction is an important factor in creating and maintaining long-term relationships with customers. Near real-time identification of potentially dissatisfied customers following phone calls can provide organizations the opport…
View article: Dimension constraints improve hypothesis testing for large-scale, graph-associated, brain-image data
Dimension constraints improve hypothesis testing for large-scale, graph-associated, brain-image data Open
Summary For large-scale testing with graph-associated data, we present an empirical Bayes mixture technique to score local false-discovery rates (FDRs). Compared to procedures that ignore the graph, the proposed Graph-based Mixture Model (…
View article: Intelligent Condition-Based Monitoring Techniques for Bearing Fault Diagnosis
Intelligent Condition-Based Monitoring Techniques for Bearing Fault Diagnosis Open
In recent years, intelligent condition-based monitor-ing of rotary machinery systems has become a major researchfocus of machine fault diagnosis. In condition-based monitoring,it is challenging to form a large-scale well-annotated datasetd…
View article: A Bayesian Approach with Type-2 Student-tMembership Function for T-S Model Identification
A Bayesian Approach with Type-2 Student-tMembership Function for T-S Model Identification Open
Clustering techniques have been proved highly suc-cessful for Takagi-Sugeno (T-S) fuzzy model identification. Inparticular, fuzzyc-regression clustering based on type-2 fuzzyset has been shown the remarkable results on non-sparse databut t…
View article: Improved Adaptive Type-2 Fuzzy Filter with Exclusively Two Fuzzy Membership Function for Filtering Salt and Pepper Noise
Improved Adaptive Type-2 Fuzzy Filter with Exclusively Two Fuzzy Membership Function for Filtering Salt and Pepper Noise Open
Image denoising is one of the preliminary steps in image processing methods in which the presence of noise can deteriorate the image quality. To overcome this limitation, in this paper a improved two-stage fuzzy filter is proposed for filt…
View article: BIDEAL: A Toolbox for Bicluster Analysis -- Generation, Visualization and Validation
BIDEAL: A Toolbox for Bicluster Analysis -- Generation, Visualization and Validation Open
This paper introduces a novel toolbox named BIDEAL for the generation of biclusters, their analysis, visualization, and validation. The objective is to facilitate researchers to use forefront biclustering algorithms embedded on a single pl…
View article: MobileDets: Searching for Object Detection Architectures for Mobile Accelerators
MobileDets: Searching for Object Detection Architectures for Mobile Accelerators Open
Inverted bottleneck layers, which are built upon depthwise convolutions, have been the predominant building blocks in state-of-the-art object detection models on mobile devices. In this work, we investigate the optimality of this design pa…
View article: Cluster Detection through Model Based Clustering Approach
Cluster Detection through Model Based Clustering Approach Open
Cluster analysis is an important technique for creating homogeneous group of objects, items. These groupings are sometimes essential for the proper analysis of data. Therefore, the technique of clustering is very useful in data analysis, e…
View article: Variable feature weighted fuzzy k-means algorithm for high dimensional data
Variable feature weighted fuzzy k-means algorithm for high dimensional data Open
This paper presents a new fuzzy k-means algorithm for the clustering of high-dimensional data in various subspaces. Since high-dimensional data, some features might be irrelevant and relevant but may have different significance in the clus…
View article: mRMR-DNN with Transfer Learning for IntelligentFault Diagnosis of Rotating Machines.
mRMR-DNN with Transfer Learning for IntelligentFault Diagnosis of Rotating Machines. Open
In recent years, intelligent condition-based monitoring of rotary machinery systems has become a major research focus of machine fault diagnosis. In condition-based monitoring, it is challenging to form a large-scale well-annotated dataset…
View article: Intelligent Condition Based Monitoring Techniques for Bearing Fault\n Diagnosis
Intelligent Condition Based Monitoring Techniques for Bearing Fault\n Diagnosis Open
In recent years, intelligent condition-based monitor-ing of rotary machinery\nsystems has become a major researchfocus of machine fault diagnosis. In\ncondition-based monitoring,it is challenging to form a large-scale\nwell-annotated datas…
View article: DUAL-GLOW: Conditional Flow-Based Generative Model for Modality Transfer
DUAL-GLOW: Conditional Flow-Based Generative Model for Modality Transfer Open
Positron emission tomography (PET) imaging is an imaging modality for diagnosing a number of neurological diseases. In contrast to Magnetic Resonance Imaging (MRI), PET is costly and involves injecting a radioactive substance into the pati…
View article: Dimension constraints improve hypothesis testing for large-scale,\n graph-associated, brain-image data
Dimension constraints improve hypothesis testing for large-scale,\n graph-associated, brain-image data Open
For large-scale testing with graph-associated data, we present an empirical\nBayes mixture technique to score local false discovery rates. Compared to\nempirical Bayes procedures that ignore the graph, the proposed method gains\npower in s…
View article: Resource Constrained Neural Network Architecture Search: Will a Submodularity Assumption Help?
Resource Constrained Neural Network Architecture Search: Will a Submodularity Assumption Help? Open
The design of neural network architectures is frequently either based on human expertise using trial/error and empirical feedback or tackled via large scale reinforcement learning strategies performed over distinct discrete architecture ch…
View article: A Rare Case of Arteriovenous Malformation of Mandible: A Case Report
A Rare Case of Arteriovenous Malformation of Mandible: A Case Report Open
View article: Clinico-epidemiological profile of trauma victims in a tertiary care hospital in rural setting of Central Uttar Pradesh
Clinico-epidemiological profile of trauma victims in a tertiary care hospital in rural setting of Central Uttar Pradesh Open
Background: In the present scenario of unprecedented population growth and development in India, we are also facing tremendous increase in cases of trauma victims and this burden is not only in economic terms, but also has significant phys…
View article: Finding Differentially Covarying Needles in a Temporally Evolving\n Haystack: A Scan Statistics Perspective
Finding Differentially Covarying Needles in a Temporally Evolving\n Haystack: A Scan Statistics Perspective Open
Recent results in coupled or temporal graphical models offer schemes for\nestimating the relationship structure between features when the data come from\nrelated (but distinct) longitudinal sources. A novel application of these ideas\nis f…
View article: When can Multi-Site Datasets be Pooled for Regression? Hypothesis Tests,\n $\\ell_2$-consistency and Neuroscience Applications
When can Multi-Site Datasets be Pooled for Regression? Hypothesis Tests,\n $\\ell_2$-consistency and Neuroscience Applications Open
Many studies in biomedical and health sciences involve small sample sizes due\nto logistic or financial constraints. Often, identifying weak (but\nscientifically interesting) associations between a set of predictors and a\nresponse necessi…