Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
4 results
Search Results
Item 3D AttU-NET for Brain Tumor Segmentation with a Novel Loss Function(Institute of Electrical and Electronics Engineers Inc., 2023) Roy, R.; Annappa, B.; Dodia, S.In the United States of America (USA), every year 150,000 patients are registered with a secondary brain tumor that is not generated in the brain. This necessitates the need for early brain tumor detection, which in turn will help patients to live longer. For clinical evaluation and treatment, precise segmentation of brain tumors in MRI images is required. This process can be aided by machine learning and efficient image processing, but manual imaging can be time-consuming. In this study, we aim to develop an 3D automated segmentation algorithm with a novel loss function. A 3D attention UNET CNN model was trained using the novel loss function, which was calculated by taking the weighted average of dice loss and focal loss to overcome the class imbalance. Results show the enhancement in the segmentation performance of attention UNET model with an average increase of 5% in the Dice coefficient for all three classes. However, the model's performance was not as strong for enhanced and core tumors. Further research may be needed to optimize performance in these areas. . © 2023 IEEE.Item A modified quasilinearization method for fractional differential equations and its applications(Elsevier Inc. usjcs@elsevier.com, 2015) Vijesh, V.; Roy, R.; Godavarma, G.Abstract In this paper, we prove an existence and uniqueness theorem for solving the nonlinear fractional differential equation of Caputo's type of order q ? (0, 1] using the method of modified quasilinearization. The main theorem has been illustrated numerically using appropriate examples which shows that the proposed quasilinearization method is robust and easy to apply. © 2015 Elsevier Inc.Item Iterative methods for a fractional-order Volterra population model(Rocky Mountain Mathematics Consortium PO Box 871804 Tempe AZ 85287-1804, 2019) Roy, R.; Vijesh, V.A.; Godavarma, G.We prove an existence and uniqueness theorem for a fractional-order Volterra population model via an efficient monotone iterative scheme. By coupling a spectral method with the proposed iterative scheme, the fractional-order integrodiffer- ential equation is solved numerically. The numerical experiments show that the proposed iterative scheme is more efficient than an existing iterative scheme in the literature, the convergence of which is very sensitive to various parameters, including the fractional order of the derivative. The spectral method based on our proposed iterative scheme shows greater flexibility with respect to various parameters. Sufficient conditions are provided to select the initial guess that ensures the quadratic convergence of the quasilinearization scheme. © 2019 Rocky Mountain Mathematics Consortium.Item Fundamental physics opportunities with future ground-based mm/sub-mm VLBI arrays(Springer Science and Business Media Deutschland GmbH, 2025) Ayzenberg, D.; Blackburn, L.; Brito, R.; Britzen, S.; Broderick, A.E.; Carballo-Rubio, R.; Cardoso, V.; Chael, A.; Chatterjee, K.; Chen, Y.; Cunha, P.V.P.; Davoudiasl, H.; Denton, P.B.; Doeleman, S.S.; Eichhorn, A.; Eubanks, M.; Fang, Y.; Foschi, A.; Fromm, C.M.; Galison, P.; Ghosh, S.G.; Gold, R.; Gurvits, L.I.; Hadar, S.; Held, A.; Houston, J.; Hu, Y.; Johnson, M.D.; Kocherlakota, P.; Natarajan, P.; Olivares Sánchez, H.; Palumbo, D.; Pesce, D.W.; Rajendran, S.; Roy, R.; Saurabh; Shao, L.; Tahura, S.; Tamar, A.; Tiede, P.; Vincent, F.H.; Visinelli, L.; Wang, Z.; Wielgus, M.; Xue, X.; Yakut, K.; Yang, H.; Younsi, Z.The Event Horizon Telescope (EHT) Collaboration recently published the first images of the supermassive black holes in the cores of the Messier 87 and Milky Way galaxies. These observations have provided a new means to study supermassive black holes and probe physical processes occurring in the strong-field regime. We review the prospects of future observations and theoretical studies of supermassive black hole systems. Current ground-based very-long-baseline interferometry (VLBI) arrays like the EHT and proposed future extensions like the next-generation Event Horizon Telescope will greatly enhance the capabilities of black-hole imaging interferometry. These enhancements will open up several previously inaccessible avenues of investigation, thereby providing important new insights into the properties of supermassive black holes and their environments. This review describes the current state of knowledge for five key science cases, summarising the unique challenges and opportunities for fundamental physics investigations that future mm/sub-mm VLBI developments will enable. © The Author(s) 2025.