Browsing by Author "Gupta, V."

Now showing 1 - 6 of 6

Automated discontinuity detection and reconstruction in subsurface environment of mars using deep learning: A case study of SHARAD observation
(MDPI AG membranes@mdpi.com, 2020) Gupta, V.; Gupta, S.K.; Kim, J.
Machine learning (ML) algorithmic developments and improvements in Earth and planetary science are expected to bring enormous benefits for areas such as geospatial database construction, automated geological feature reconstruction, and surface dating. In this study, we aim to develop a deep learning (DL) approach to reconstruct the subsurface discontinuities in the subsurface environment of Mars employing the echoes of the Shallow Subsurface Radar (SHARAD), a sounding radar equipped on the Mars Reconnaissance Orbiter (MRO). Although SHARAD has produced highly valuable information about the Martian subsurface, the interpretation of the radar echo of SHARAD is a challenging task considering the vast stocks of datasets and the noisy signal. Therefore, we introduced a 3D subsurface mapping strategy consisting of radar echo pre-processors and a DL algorithm to automatically detect subsurface discontinuities. The developed components the of DL algorithm were synthesized into a subsurface mapping scheme and applied over a few target areas such as mid-latitude lobate debris aprons (LDAs), polar deposits and shallow icy bodies around the Phoenix landing site. The outcomes of the subsurface discontinuity detection scheme were rigorously validated by computing several quality metrics such as accuracy, recall, Jaccard index, etc. In the context of undergoing development and its output, we expect to automatically trace the shapes of Martian subsurface icy structures with further improvements in the DL algorithm. © 2020 by the authors.
Conceptualization and Design ofÂ Remotely-Accessible Hardware Interface (RAHI) Laboratory
(Springer Science and Business Media Deutschland GmbH info@springer-sbm.com, 2021) Potdar, S.M.; Gupta, V.; Umesh, P.; Gangadharan, K.V.
With the rising popularity of e-learning through means like Massive Open Online Courses (MOOCs), remote-triggered and virtual laboratories, new and innovative technologies for enhancing the learning experience are in demand. E-learning resources for electronics hardware are generally simulation-based, as getting access to high-end hardware is difficult for students due to cost and availability. In this paper, a novel method to create a remotely-accessible, low-cost, modular, and scalable hardware learning platform is proposed and demonstrated through a prototype. Users can interact with the system through a web interface anytime-anywhere and verify results on actual hardware through real-time visual and textual feedback and learn at their pace. The prototype demonstrates a web application hosted on a Linux-PC server interacting with a Raspberry Pi. Student activities are logged in a database for future reference and correction by instructors. The software stack used for the system is free and open-source. The prototype system was launched on a pilot run, gaining positive feedback from students and teachers. Hence, such a system can undergo comprehensive implementation in educational institutions and for the delivery of MOOCs with minimal investment for both laboratory setups and learners. Â© 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
Fractal-based supervised approach for dimensionality reduction of hyperspectral images
(Elsevier Ltd, 2024) Gupta, V.; Gupta, S.K.; Shetty, A.
Dimensionality reduction is one of the most challenging and crucial issues apart from data mining, security, and scalability, which have retained much traction due to the ever-growing need to analyze the large volumes of data generated daily. Fractal Dimension (FD) has been successfully used to characterize data sets and has found relevant applications in dimension reduction. This paper presents an application of the FD Reduction (FDR) Algorithm on geospatial hyperspectral data, examining its usefulness for data sets with a relatively high embedding dimension. We examine the algorithm at two levels. First is the conventional FDR approach (unsupervised) at the image level. Alternatively, we propose a pixel-level supervised approach for band reduction based on time-series complexity analysis. Techniques for determining an optimal intrinsic dimension for the dataset using these two techniques are examined. We also develop a parallel GPU-based implementation for the unsupervised image-level FDR algorithm, reducing the run-time by nearly 10 times. Furthermore, both approaches use a support vector machine classifier to compare the classification performance of the original and reduced image obtained. © 2024 Elsevier Ltd
Non-subsampled Shearlet Domain-based De-speckling Framework for Optical Coherence Tomography Images
(International Hellenic University - School of Science, 2023) Gupta, P.K.; Chanchal, A.K.; Lal, S.; Gupta, V.
An effective instrument for obtaining an image of the retina is an optical coherence tomography (OCT) imaging device. OCT images of the retina are useful for diagnosing and tracking eye diseases. However, different physical configurations in the imaging apparatus are to blame for the speckle noise in retinal OCT images. The OCT image quality and assessment reliability are reduced due to aforementioned noise. This paper offered a paradigm for reducing speckle noise that was motivated by the mathematical formulation of speckle noise. Two distinct noise components make up speckle noise, one of which is additive and the other of which is multiplicative in nature. For each sort of noise, the suggested structure employs a different filter. To reduce the additive component of speckle noise, Weiner filtering is used. To minimize the multiplicative component of noise, a particular arrangement based on non-subsampled shearlet transform (NSST) is used. It is now widely acknowledge that NSST overcome the limitations of traditional wavelet transform therefore it very useful in dealing of distributed discontinuities therefore it is prefer in this research work.Real retinal OCT pictures are used to assess the proposed framework's quantitative and qualitative performance. The PSNR, MSE, SSIM, and CNR metrics are used to compare the suggested framework. In comparison to existing cutting-edge filters, the proposed framework performs better in terms of noise suppression capability with structure preservation capabilities. The proposed technique gives highest PSNR, SSIM and CNR value that indicate the effectiveness of proposed work in addition to this proposed work give lowest MSE value. The proposed work give better enhance images in comparison to other existing filter therefore it may be helpful to find out any abnormality in OCT image and improve the diagnose of OCT retinal image. © 2023 School of Science, IHU. All rights reserved.
Optimal Selection of Bands for Hyperspectral Images Using Spectral Clustering
(2019) Gupta, V.; Gupta, S.K.; Shukla, D.P.
High spectral resolution of hyperspectral images comes hand in hand with high data redundancy (i.e. multiple bands carrying similar information), which further contributes to high computational costs, complexity and data storage. Hence, in this work, we aim at performing dimensionality reduction by selection of non-redundant bands from hyperspectral image of Indian Pines using spectral clustering. We represent the dataset in the form of similarity graphs computed from metrics such as Euclidean, and Tanimoto Similarity using K-Nearest neighbor method. The optimum k for our dataset is identified using methods like Distribution Compactness (DC) algorithm, elbow plot, histogram and visual inspection of the similarity graphs. These methods give us a range for the optimum value of k. The exact value of clusters k is estimated using Silhouette, Calinski-Harbasz, Dunn�s and Davies-Bouldin Index. The value indicated by majority of indices is chosen as value of k. Finally, we have selected the bands closest to the centroids of the clusters, computed by using K-means algorithm. Tanimoto similarity suggests 17 bands out of 220 bands, whereas the Euclidean metric suggests 15 bands for the same. The accuracy of classified image before band selection using support vector machine (SVM) classifier is 76.94% and after band selection is 75.21% & 75.56% for Tanimoto and Euclidean matrices respectively. � 2019, Springer Nature Singapore Pte Ltd.
Optimal Selection of Bands for Hyperspectral Images Using Spectral Clustering
(Springer Verlag service@springer.de, 2019) Gupta, V.; Gupta, S.K.; Shukla, D.P.
High spectral resolution of hyperspectral images comes hand in hand with high data redundancy (i.e. multiple bands carrying similar information), which further contributes to high computational costs, complexity and data storage. Hence, in this work, we aim at performing dimensionality reduction by selection of non-redundant bands from hyperspectral image of Indian Pines using spectral clustering. We represent the dataset in the form of similarity graphs computed from metrics such as Euclidean, and Tanimoto Similarity using K-Nearest neighbor method. The optimum k for our dataset is identified using methods like Distribution Compactness (DC) algorithm, elbow plot, histogram and visual inspection of the similarity graphs. These methods give us a range for the optimum value of k. The exact value of clusters k is estimated using Silhouette, Calinski-Harbasz, Dunnâ€™s and Davies-Bouldin Index. The value indicated by majority of indices is chosen as value of k. Finally, we have selected the bands closest to the centroids of the clusters, computed by using K-means algorithm. Tanimoto similarity suggests 17 bands out of 220 bands, whereas the Euclidean metric suggests 15 bands for the same. The accuracy of classified image before band selection using support vector machine (SVM) classifier is 76.94% and after band selection is 75.21% & 75.56% for Tanimoto and Euclidean matrices respectively. Â© 2019, Springer Nature Singapore Pte Ltd.