Conference Papers

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

Browse

Search Results

Now showing 1 - 2 of 2
  • Item
    Accurate Estimation for Stability of Slope and Partition Over Old Underground Coal Workings Using Regression-Based Algorithms
    (Springer Science and Business Media Deutschland GmbH, 2022) Dorthi, K.; Kumar, A.; Ram Chandar, K.R.
    Numerical modeling simulation has found to be best solution for predicting slope and partition stability over old underground coal workings. But it has taken huge time to complete a single simulation model. In this regard, machine learning-based framework is used to predict the stability of old galleries. A case study is taken up in opencast mine and simulation is carried out using numerical model and machine learning-based framework. Framework has shown an overall accuracy of 94–95% for different slope and partition stability. Framework shows a speedup of 2366 × against numerical simulator. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
  • Item
    ESIS-SSI: Efficient (n,n) Secret Image Sharing with Shrinking Shadow Images
    (Institute of Electrical and Electronics Engineers Inc., 2024) Purushothama, B.R.
    The problem of secret image sharing has been extensively studied, and the size of the shadow images is a critical factor for applying these schemes in resource-limited environments. Most existing schemes generate shadow images that are approximately the same size as the original secret image. This work addresses the issue of reducing shadow image size. A (n, n) threshold scheme that produces smaller shadow images is proposed. The new method for sharing the secret image results in shadow images of size ⌈nh ⌉ × w, as opposed to the standard h×w size in most existing schemes. The secret key is not needed at the Combiner while reconstructing I. The proposed scheme has been rigorously validated and implemented, demonstrating both efficiency and security, with shadow images not disclosing any information about the original secret image. Compared to existing methods, our scheme is shown to generate the shadow images with the reduced size and is efficient. © 2024 IEEE.