Dissertations - M Tech (CS): Recent submissions

  • Image caption generation using Deep Q-learning framework 
    Rana, Dipen Ganpat (Indian Statistical Institute, Kolkata, 2021-07)
    With the convolution neural network getting more and more popular in the last decade or so, thanks to the easy and a ordable access to high computation power, it has been easy to process huge amount of data through ...
  • Author Identification and Analysis of Bollywood Song Lyrics 
    Pai, Deepesh (Indian Statistical Institute, Kolkata, 2021-07)
    Research in Natural Language Processing is expanding in multiple domains and applications. With every advancement, the variety of text that are processed is growing. One such domain is lyrics processing. Songs are vital ...
  • Sarcasm Detection using Deep Learning 
    Jaiswal, Amit Kumar (Indian Statistical Institute, Kolkata., 2021-07)
    Sentiment analysis is often used in NLP to understand people’s subjective opinions. However, the analysis results may be biased if people use sarcasm in their statements. In order to correctly understand people’s true ...
  • Chords in a Longest Cycle of a 3-Connected Graph 
    Chaudhary, Deepak (2021-07)
    In 1976, Carsten Thomassen conjectured that no longest cycle in a 3-connected graph can be a chordless cycle. Although this conjecture was later proved for some special classes of graphs, the general case remains open. ...
  • Detecting Anemia from retinal images using Deep Learning 
    Agrawal, Akhil (Indian Statistical Institute, Kolkata., 2021-07)
    Anemia is the condition which formed when there is not enough healthy red blood cells present in body. This ultimately result in the lack of reduced oxygen flow in the body. This causes the fatigue, dizziness, shortness ...
  • Facets of Quantum Computation { Practice and Theory 
    Mukherjee, Chandra Sekhar (Indian Statistical Institute, Kolkata, 2021-07)
    Quantum computation has seen rapid development both in theory as well as hardware and implementation in the past three decades. Against this backdrop we study both the implementational and theoretical aspects of quantum ...
  • An approach to Multi View Deep Continuous Clustering using Subspace Projection 
    Mazumder, Agnip (Indian Statistical Institute, Kolkata, 2021-07)
    As we know Clustering is an unsupervised machine learning algorithm, where in a collection of unlabelled data similar data items are grouped under same class and dissimilar data goes to di erent class. One common algorithm ...
  • Gender bias in Hindi word embedding 
    Bharti, Barkha (Indian Statistical Institute, Kolkata, 2021-07)
    The purpose of this paper is to present a study on gender bias in word embeddings in the context of the Hindi Language. It has been shown that word embeddings capture human biases (such as gender bias) present in the ...
  • Video Frame Prediction using Deep Learning 
    Kola, Bala Murali Krishna (Indian Statistical Institute, Kolkata, 2021-07)
    Advances in Deep Learning helped in developing exiting applications in the past few years like Style Transfer, Image Generation. It has helped us achieving super human performance and state-of-the-art results in various ...
  • Discriminative Dictionary Learning by Exploiting Inter-Class Similarity for HEp-2 Cell Classi cation 
    Panda, Aditya (Indian Statistical Institute,Kolkata, 2019-07)
    In this literature we present an algorithm for automatic classi cation of IIF images of HEp-2 cells into relevant classes. Our algorithm is majorly based on the \Dictionary Learning" algorithm and we have rede ned it's ...
  • BlockV: A Blockchain Enabled Peer-Peer Ride Sharing Service 
    Pal, Panchalika (Indian Statistical Institute,Kolkata, 2019-07)
    Today's ride sharing is a centralized trust based system where users trust the service providers for the ride set up, tracking, cancellation, fare calculation etc. Any malicious activity in the centralized server based ...
  • Recognition of Strokes in Tennis Videos Using Deep Learning 
    Singanporia, Kushal (Indian Statistical Institute,Kolkata, 2019-07)
    Prior introduction of neural nets to domain of computer vision, action recognition requires specific domain knowledge. Still domain knowledge is useful in action recognition but with availability of huge data and ...
  • Classi cation of Micro-Blog Texts 
    Sen, Bihan (Indian Statistical Institute,Kolkata, 2019-07)
    Classi cation of micro-blog texts is a very common task for sentiment analysis, user opinion mining, product review analysis, crisis managements, identifying ofensive and hate speech propagation across social media, ...
  • On Testing of Samplers and Related Problems 
    Chakraborty, Shayak (Indian Statistical Institute,Kolkata, 2019-07)
    The last decade has seen an unprecedented adoption of Arti cial Intelligence and Machine Learning Algorithms in various engineering applications such as medical imaging, autonomous vehicles, web services, etc. Probabilistic ...
  • Event Timeline Generation and Summarization using PageRank 
    Das, Pabani (Indian Statistical Institute,Kolkata, 2019-07)
    Given a search query our system retrieves most significant events related to the query and display them in user friendly timeline. We are using graph structure to compute relative importance of events. We are representing ...
  • Feature Extraction And Detection of Malicious URLs Using Deep Learning Approach 
    Kushwaha, Rajni (Indian Statistical Institute,Kolkata, 2019-07)
    Phishing Attack is one of the cyber bullying activity over the internet. Most of the phishing websites try to look similar to legitimate websites, their web content and URL features memic the legitimate URL. Due to ...
  • A Novel Approach to Automated Coal Petrography Using Deep Neural Networks Souptik 
    Mukhopadhyay, Souptik (Indian Statistical Institute,Kolkata, 2019-07)
    This research work is industry sponsored and carried out in collaboration with Tata Steel, India. Its objective is to alleviate a bottleneck in the steel manufacturing pipeline by the application of automated coal ...
  • Computational Learning Theory aspects of Piecewise Polynomial and Sigmoidal Neural Networks 
    Das, Soumya Kanti (Indian Statistical Institute,Kolkata, 2019-07)
    VC (Vapnik Chervonenkis) Dimension is a useful tool for measuring the power of a neural network or some other types of classi ers. In the eld of learning theory VC dimension represents the generalized power of a neural ...
  • Unsupervised Machine Translation For Indian Languages Using Monolingual Corpora 
    Choudhary, Sudeep (Indian Statistical Institute,Kolkata, 2019-07)
    Machine translation has traditionally relied on parallel data but the amount of parallel data available for Indian languages is very less . The parallel data for Hindi-Marathi translation is around 50000 sentences which ...
  • Deep Clustering For Screening Diabetic Retinopathy 
    Jaiswal, Sangeet (Indian Statistical Institute,Kolkata, 2019-07)
    Deep neural networks have been investigated in learning latent representations of medical images, yet most of the studies limit their approach using supervised convolutional neural network (CNN), which usually rely heavily ...

Search DSpace


Advanced Search

Browse

My Account