Faculty Publications

Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736

Publications by NITK Faculty

Browse

Author: search.filters.author.Anil, S.

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Predictive Selective Repeat - an Optimized Selective Repeat for Noisy Channels
    (Institute of Electrical and Electronics Engineers Inc., 2023) Rati Preethi, S.; Praveen Kumar, P.; Anil, S.; Chandavarkar, B.R.
    Automatic Repeat reQuest (ARQ) is a technique used in two-way communication systems to make sure that the transmitted data is received properly without any errors. The underlying mechanism on which ARQ operates is the acknowledgment (ACK) sent by the receiver to the sender on the orderly arrival of data frames. Some protocols which have been employed include Stop and Wait ARQ, Go-Back-N ARQ, and Selective Repeat ARQ. There have been many attempts to optimize these protocols to decrease the number of Round-Trips and increase the throughput. Predictive Selective Repeat (PSR) ARQ is the technique introduced in this paper to send multiple copies of frames without waiting for ACK. The main goal of PSR ARQ model is to optimally predict the number of required copies for a particular frame so as to reduce the number of Round-Trips by using a Time series Forecasting Long Short-Term Memory (LSTM) model. © 2023 IEEE.
  • No Thumbnail Available
    Item
    Autoencoded Image Compression for Secure and Fast Transmission
    (Institute of Electrical and Electronics Engineers Inc., 2024) Naveen, A.K.; Thunga, S.; Murki, A.; Kalale, M.; Anil, S.
    With exponential growth in the use of digital image data, the need for efficient transmission methods has become imperative. Traditional image compression techniques often sacrifice image fidelity for reduced file sizes, challenging maintaining quality and efficiency. They also compromise security, leaving images vulnerable to threats such as man-in-the-middle attacks. This paper proposes an autoencoder architecture for image compression to not only help in dimensionality reduction but also inherently encrypt the images. The paper also introduces a composite loss function that combines reconstruction loss and residual loss for improved performance. The autoencoder architecture is designed to achieve optimal dimensionality reduction and regeneration accuracy while safeguarding the compressed data during transmission or storage. Images regenerated by the autoencoder are evaluated against three key metrics: reconstruction quality, compression ratio, and one-way delay during image transfer. The experiments reveal that the proposed architecture achieves an SSIM of 97.5% over the regenerated images and an average latency reduction of 87.5%, indicating its effectiveness as a secure and efficient solution for compressed image transfer. © 2024 IEEE.