Anurag Kumar

Optimizing logistics resilience through strategic trade-offs: a BWM–goal programming approach

Anurag Kumar, Shraddha Mishra

in (code pays fourni par la source)

Robust sigmoidal cost logarithmic controller for power quality enhancement in PV-integrated grid systems

Anurag Kumar, Ankita Arora, Madhusudan Singh

in (code pays fourni par la source)

Leveraging Data and Voice Interfaces for Accessible Mobile Telehealth

Nitin Saksena, Vishnu Ramineni, Prema Kumar Veerapaneni, Akash Kumar Agarwal et autres

us (code pays fourni par la source)

Diagnostic Performance of ANCA Testing Across Three Platforms with and without Coexisting ANA Positivity: Experience from a Tertiary Healthcare Centre in India

Neha Rai, Shamshad Ahmad, Saurabh Karmakar, Divendu Bhushan et autres

Background: Indirect immunofluorescence (IIF) is a useful diagnostic modality for anti-neutrophilic cytoplasmic antibody (ANCA) detection in ANCA associated with vasculitis and diseases beyond vasculitis. As per latest guidelines, the IIF has been replaced by enzyme-linked immunosorbent assay (ELISA) as first line of …

in (code pays fourni par la source)

A framework for server performance analysis in cloud datacenter: A systematic study using memoryless open queuing system

Atul Sharma, Anurag Kumar, Manoj Kumar

Theoretical computer science has always played a crucial role in research and innovation in all fields of computer science and information technology. Queuing system has always assisted researchers in having a deep dive in ocean of theories and priciples of studying systems …

AI-ML Based Intelligent De-Smoking/De-Hazing Algorithm

Anurag Kumar, Mohammed Kaif, S. K. Darshan, Vishal Vaibhav et autres

This paper introduces an AI-ML-based de-smoking and de-hazing intelligent algorithm for real-time visibility improvement in haze- and smoke-contaminated environments. Utilizing a Convolutional Neural Network (CNN) structure, namely ResNet-50, the introduced model successfully identifies and deletes haze and smoke by learning intricate visual …

B-Ezy - A Booking Web Application

Shweta Chaku, Shivam Kumar Jha, Shiladitya Raj, Shriya Sharma et autres

The digital era demands seamless integration of online booking systems across sectors like healthcare, transportation, and hospitality. B-Ezy emerges as a unified web application designed to consolidate fragmented service bookings—flights, hotels, taxis, and car rentals—into a single platform. Built with a modular …

Optimizing Solar Photovoltaic Power Injection Using Machine Learning: Minimizing Harmonic Distortion Under Inertia Constraints

Anurag Kumar

This paper elaborates on a machine learningbased technique for enhancing the Space Vector Pulse Width Modulation (SVPWM) for minimizing Total Harmonic Distortion (THD) in solar photovoltaic (PV) systems under a limitation of power system inertia. Since solar PV systems have become more …

in (code pays fourni par la source)

Smart Video Monitoring: Advanced Deep Learning for Activity and Object Recognition

Dandinashivara Revanna Shashikumar, N Tejashwini, K N Pushpalatha, Anurag Kumar et autres

This study explores the integration of Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks for the real-time recognition of human activities in video data. By harnessing the advantages of these two approaches, the system achieves high accuracy in detecting complex …

Reexamining the Efficacy of MetricGAN for Speech Enhancement

Haibin Wu, Ali Aroudi, Buye Xu, Ashutosh Kumar Pandey et autres

MetricGAN, a notable generative approach, provides an effective framework to train speech enhancement models to produce high metric scores. However, we identify two key limitations of current MetricGAN-family models, i.e. neglecting certain mainstream metrics during evaluation and conducting evaluation exclusively at high …

tw, us (code pays fourni par la source)

SEAL: Speaker Error Correction using Acoustic-conditioned Large Language Models

Anurag Kumar, Rohit Paturi, Amber Afshan, Sundararajan Srinivasan

Speaker Diarization (SD) is a crucial component of modern end-to-end ASR pipelines. Traditional SD systems, which are typically audio-based and operate independently of ASR, often introduce speaker errors, particularly during speaker transitions and overlapping speech. Recently, language models including fine-tuned large language …

us (code pays fourni par la source)

A Comparison of Scheduling Algorithms for Packet Voice in a 5G Cellular System and Their Impact on Full Buffer eMBB Flows

Writtik Majumder, Anurag Kumar, Rajesh Sundaresan

Since the radio channel between the base-station and a User Equipment (UE) is stochastic, semi-persistent scheduling (SPS), commonly used for Voice over New Radio (VoNR), may be suboptimal in the utilisation of time-frequency resources, thus providing lower residual bit-rates for enhanced mobile …

in (code pays fourni par la source)