Shamanth R Nayak K

Shamanth R Nayak K

Grdauate Student at Concordia University

Publications

Generating Query Focused Summaries without Fine-tuning the Transformer-based Pre-trained Models

Published in arXiv, 2023

Deen Abdullah, Shamanth Nayak, Gandharv Suri, Yllias Chali

Fine-tuning the Natural Language Processing (NLP) models for each new data set requires higher computational time associated with increased carbon footprint and cost. However, fine-tuning helps the pre-trained models adapt to the latest data sets; what if we avoid the fine-tuning steps and attempt to generate summaries using just the pre-trained models to reduce computational time and cost. In this paper, we tried to omit the fine-tuning steps and investigate whether the Marginal Maximum Relevance (MMR)-based approach can help the pre-trained models to obtain query-focused summaries directly from a new data set that was not used to pre-train the models.
Read more

Download here

Traffic flow prediction models – A review of deep learning techniques

Published in Cogent Engineering, Volume 9, 2022 - Issue 1, 2022

Anirudh Ameya Kashyap, Shravan Raviraj, Ananya Devarakonda, Shamanth R Nayak K, Santhosh KV, Soumya J Bhat

In our paper, we review some of the latest works in deep learning for traffic flow prediction. Many deep learning architectures include Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Restricted Boltzmann Machines (RBM), and Stacked Auto Encoder (SAE).
Read more

Download here

Secure Sharing of Text Based Data Using Hybrid Encryption Algorithms in a Client-Server Model

Published in ICECCT 2021, 2021

Swadhin Routray, Dhruv Raipure, Shamanth R Nayak K, Nisha P Shetty

This paper proposes a system to secure text-based data sharing between users using a hybrid encryption methodology. On the other hand, encryption algorithms consume a significant amount of time for computation. This paper provides an evaluation of 6 different algorithmic combinations: AES+RSA, DES+RSA, 3DES+RSA, RC4+RSA, Blowfish+RSA and Rabbit+RSA. A comparison study has been conducted for the different combinations by using files with different file sizes to determine which algorithmic combination is best for the proposed system. The simulation results have been published to demonstrate the effectiveness of the algorithmic combinations and suitability for the proposed system.
Read more

Download here

IS-CAM: Integrated Score-CAM for axiomatic-based explanations

Published in RCV, CVPR 2020 (Poster), 2020

Rakshit Naidu, Ankita Ghosh, Yash Maurya, Shamanth R Nayak K, Soumya Snigdha Kundu

Convolutional Neural Networks have been known as black-box models as humans cannot interpret their inner functionalities. With an attempt to make CNNs more interpretable and trustworthy, we propose IS-CAM (Integrated Score-CAM), where we introduce the integration operation within the Score-CAM pipeline to achieve visually sharper attribution maps quantitatively. Our method is evaluated on 2000 randomly selected images from the ILSVRC 2012 Validation dataset, which proves the versatility of IS-CAM to account for different models and methods.
Read more

Download here