Conference Papers

Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506

Browse

Author: search.filters.author.Mukesh, B.R.

Search Results

Now showing 1 - 4 of 4
  • No Thumbnail Available
    Item
    Performance evaluation of deep learning frameworks on computer vision problems
    (Institute of Electrical and Electronics Engineers Inc., 2019) Nara, M.; Mukesh, B.R.; Padala, P.; Kinnal, B.
    Deep Learning (DL) applications have skyrocketed in recent years and are being applied in various domains. There has been a tremendous surge in the development of DL frameworks to make implementation easier. In this paper, we aim to make a comparative study of GPU-accelerated deep learning software frameworks such as Torch and TenserFlow (with Keras API). We attempt to benchmark the performance of these frameworks by implementing three different neural networks, each designed for a popular Computer Vision problem (MNIST, CIFAR10, Fashion MNIST). We performed this experiment on both CPU and GPU(Nvidia GeForce GTX 960M) settings. The performance metrics used here include evaluation time, training time, and accuracy. This paper aims to act as a guide to selecting the most suitable framework for a particular problem. The special interest of the paper is to evaluate the performance lost due to the utility of an API like Keras and a comparative study of the performance over a user-defined neural network and a standard network. Our interest also lies in their performance when subjected to networks of different sizes. ©2019 IEEE.
  • No Thumbnail Available
    Item
    Clustering Enhanced Encoder–Decoder Approach to Dimensionality Reduction and Encryption
    (Springer Science and Business Media Deutschland GmbH info@springer-sbm.com, 2021) Mukesh, B.R.; Madhumitha, N.; Aditya, N.P.; Vivek, S.; Anand Kumar, M.
    Dimensionality reduction refers to reducing the number of attributes that are being considered, by producing a set of principal variables. It can be divided into feature selection and feature extraction. Dimensionality reduction serves as one of the preliminary challenges in storage management and is useful for effective transmission over the Internet. In this paper, we propose a deep learning approach using encoder–decoder networks for effective (almost-lossless) compression and encryption. The neural network essentially encrypts data into an encoded format which can only be decrypted using the corresponding decoders. Clustering is essential to reduce the variation in the dataset to ensure overfit. Using clustering resulted in a net gain of 1% over the standard encoder architecture over three MNIST datasets. The compression ratio achieved was 24.6:1. The usage of image datasets is for visualization only and the proposed pipeline could be applied for textual and visual data as well. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
  • No Thumbnail Available
    Item
    Deep Learning based detection of Diabetic Retinopathy from Inexpensive fundus imaging techniques
    (Institute of Electrical and Electronics Engineers Inc., 2021) Mukesh, B.R.; Harish, T.; Mayya, V.; Kamath S․, S.
    Diabetic Retinopathy is the leading cause of blindness across the world as per statistics published by the World Health Organization. Recently, there has been significant research on adopting deep learning methodologies to automate and improve the process of evaluating the advent and progress of chronic eye diseases using eye fundus images. Typically, eye fundus imaging equipment is used by trained specialists for evaluating eye health, however, fundus imaging tends to be expensive, and also the high-end equipment used is typically available in large hospitals and urban areas. This cost barrier leads to an imbalance in care between the developed and developing parts of the world. In this paper, we propose an inexpensive stand-in for such a device and a deep neural model pipeline that is able to analyze these images to determine the need for further evaluation from a trained ophthalmologist. The pipeline is able to achieve an AUC score of 0.9781 in detecting Referable DR. We also benchmark the proposed deep learning pipeline against other pipelines on standard datasets to demonstrate the capability of the network. © 2021 IEEE.
  • No Thumbnail Available
    Item
    AuthNet: A Deep Learning Based Authentication Mechanism Using Temporal Facial Feature Movements (Student Abstract)
    (Association for the Advancement of Artificial Intelligence, 2021) Raghavendra, M.; Omprakash, P.; Mukesh, B.R.
    Deep learning algorithms are widely used to extend modern biometric authentication mechanisms in resource-constrained environments like smartphones, providing ease-of-use and user comfort, while maintaining a non-invasive nature. In this paper, an alternative is proposed, that uses both facial recognition and the unique movements of that particular face while uttering a password. The proposed model is language independent, the password doesn't necessarily need to be a set of meaningful words or numbers, and also, is a contact-less system. When evaluated on the standard MIRACL-VC1 dataset, the proposed model achieved a testing accuracy of 98.1%, underscoring its effectiveness. © © 2021, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved