Department

Sort by: Order: Results:

  • Automatic Assignment of Medical Codes 
    SAMANTA, MRITYUNJAY (2021-06)
    Natural Language Processing (NLP) is one of the most challenging and rapidly growing fields in artificial intelligence. It is all about deciphering human languages and deriving meaning from them. Some of the commonly ...
  • Applications of Deep Learning: Sequence Modelling in Industrial Sound Analytics 
    CHOUDHARY, ABHISHEK (2021-06)
    In today's world of data and information, deep learning has proven to be the ace in data science applications. While we hear much of deep learning concerning computer vision, NLP (Natural Language Processing), audio analysis ...
  • Applications of Convolutional-Recurrent Neural Networks in Weather Forecasting 
    SAMANTA, ARYA (2021-06)
    In this thesis, we use convolutional long short-term memory based neural network archi- tectures to predict certain basic dynamics of weather variables. First, rainfall dynamics are studied across direct and iterative ...
  • Machine Learning in Sound Analytic 
    MOHAN, ANIKET (2021-07)
    In this project we focus on different deep Learning algorithms for noisy audio enhancement where traditional Digital signal Processing (DSP) techniques fail to enhance noisy audio clips, we also worked on the classification ...
  • Medical Report Generation Model 
    GUPTA, PAWAN (2021-07)
    After recovery, many Covid Patients have a post-corona effect, and the most common is a lung infection (Pneumonia) in treatment response of this the first things that are done are taking X-rays and creating Reports. ...
  • Privacy-Preserving Distributed learning in the Healthcare sector 
    MADAAN, HARSHIT (2021-07)
    In this thesis, we compare three privacy-preserving distributed learning techniques: federated learning, split learning, and SplitFed. We use these techniques to develop binary classification models for detecting tuberculosis ...
  • Working with Small Datasets 
    SETH, JITESH (2021-07)
    Deep learning semantic segmentation algorithms can localise abnormalities or opacities from chest radiographs. However, collecting and annotating training data is expensive and requires expertise which remains a bottleneck ...
  • Application of Convolutional Recurrent Neural Network in Precipitation Forecasting 
    ABHISHEK, NAMIT (2021-08)
    In this work, we use convolutional recurrent neural network-based architectures involving ConvLSTM and ConvGRU for precipitation forecasting over the Indian region. We first compare direct and iterative approach for ...
  • A universal framework for detecting cis-regulatory diversity in DNA regions 
    BISWAS, ANUSHUA; NARLIKAR, LEELAVATI (Cold Spring Harbor Laboratory Press, 2021-09)
    High-throughput sequencing-based assays measure different biochemical activities pertaining to gene regulation, genome-wide. These activities include transcription factor (TF)–DNA binding, enhancer activity, open chromatin, ...
  • Reducing Labelled Data Requirement for Pneumonia Segmentation Using Image Augmentations 
    SETH, JITESH; Lokwani, Rohit; Kulkarni, Viraj; Pant, Aniruddha; Kharat, Amit (Springer Nature, 2022-01)
    Home ICT Systems and Sustainability Conference paper Reducing Labelled Data Requirement for Pneumonia Segmentation Using Image Augmentations Jitesh Seth, Rohit Lokwani, Viraj Kulkarni, Aniruddha Pant & Amit Kharat ...
  • From Complexity to Simplicity and Back 
    APTE, AMIT (Indian Academy of Sciences, 2022-02)
    The Nobel Prize of 2021 highlighted the importance of understanding the complex dynamical processes that govern the evolution of Earth’s climate. Two of the Nobel laureates, Syukuro Manabe and Klaus Hasselmann pioneered ...
  • Graph Neural Networks for Multivariate Time Series Forecasting 
    ., AJAY (2022-04)
    Stock market analysis is a hot topic with a very active research community working on it. Stock price prediction is of particular interest owing to the high stakes it offers. It is actually a multivariate time series ...
  • Text Analytics to Assist Financial Research 
    M P, RAHMATHULLA (2022-05)
    The amount of data is increasing in the financial domain as in every field. It is humanly impossible to analyse all these data efficiently, so we need optimised computational techniques to achieve this. In this work, We ...
  • Object Detection in Indian Food Platters using Transfer Learning with YOLOv4 
    Pandey, Deepanshu; PARMAR, PURVA; Toshniwal, Gauri; Goel, Mansi; Agrawal, Vishesh; Dhiman, Shivangi; Gupta, Lavanya; Bagler, Ganesh (IEEE, 2022-05)
    Object detection is a well-known problem in computer vision. Despite this, its usage and pervasiveness in the traditional Indian food dishes has been limited. Particularly, recognizing Indian food dishes present in a single ...
  • Investigation of Mixed Layer Depth through the lens of Artificial Intelligence 
    BHASKAR, ANKIT (2022-12)
    Predicting the various oceanic parameters responsible for air-sea coupling is crucial to understanding how the climate and weather systems can affect the ecosphere. One of the most important among these oceanic parameters ...
  • Effects of equatorially-confined shear flow on MRG and Rossby waves 
    Raghav, Mukesh Singh; Jose, Sharath; APTE, AMIT; Govindarajan, Rama (Elsevier B.V., 2022-12)
    Linear modal stability analysis of a mean zonal shear flow is carried out in the framework of rotating shallow water equations (RSWE), both under the -plane approximation and in the full spherical coordinate system. Two ...
  • Semantic Search and Question-Answering Systems 
    PARMAR, PURVA (2023-05)
    Keyword Search Systems have been in wide use since the availability of computers themselves. Keyword search returns the relevant results which contain the exact keywords used in a search query. But in today’s world of ...
  • Continual Domain Incremental Learning during Test-time 
    CHAKRABARTY, GOIRIK (2023-05)
    This thesis focuses on the problem of continual test time domain adaptation in deep learning, where a trained model needs to adapt to new and changing environments during deployment. The first contribution of this work ...
  • Meteorological Variables Nowcasting using Machine Learning and Deep Learning Techniques 
    HARAL, HRISHIKESH (2023-05)
    In this work, we address two nowcasting problem statements. The first is the PM2.5 concentration temporal nowcasting over Delhi NCR. It has been observed that the high levels of PM2.5 concentrations in Delhi, particularly ...
  • Data-driven Prediction of Crop Yield Over Germany 
    PRAMANICK, PRANTIK (2023-05)
    This research aims to create a system that predicts agricultural yields using an all-encompassing system that integrates Numerical Weather Prediction (NWP) with machine learning. We want to know if combining NWP and ML ...