Conference Papers

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

Browse

Filters

2020 - 20232

Settings

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

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Brain tumor segmentation based on 3D residual U-Net
    (Springer, 2020) Bhalerao, M.; Thakur, S.
    We propose a deep learning based approach for automatic brain tumor segmentation utilizing a three-dimensional U-Net extended by residual connections. In this work, we did not incorporate architectural modifications to the existing 3D U-Net, but rather evaluated different training strategies for potential improvement of performance. Our model was trained on the dataset of the International Brain Tumor Segmentation (BraTS) challenge 2019 that comprise multi-parametric magnetic resonance imaging (mpMRI) scans from 335 patients diagnosed with a glial tumor. Furthermore, our model was evaluated on the BraTS 2019 independent validation data that consisted of another 125 brain tumor mpMRI scans. The results that our 3D Residual U-Net obtained on the BraTS 2019 test data are Mean Dice scores of 0.697, 0.828, 0.772 and Hausdorff95 distances of 25.56, 14.64, 26.69 for enhancing tumor, whole tumor, and tumor core, respectively. © Springer Nature Switzerland AG 2020.
  • No Thumbnail Available
    Item
    Fuzzy Logic Based Totem pole- PFC Converter
    (Institute of Electrical and Electronics Engineers Inc., 2023) Khaza, M.F.; Thakur, S.; Nagendrappa, H.; Balasubramanian, B.
    Power quality is always a major threat to grid-connected systems. Different topologies can be used in EV chargers. However, due to several limitations in the active Power Factor Correction (PFC) and proportional-integral (PI) based PFC has led to exploring advanced schemes. This paper presents novelty by introducing fuzzy logic with totem pole power factor correction. An attempt has been made to use this PFC for Electric Vehicle (EV) chargers. Totem pole topology offers high efficiency, low conduction loss, and high speed. The proposed scheme uses two loops with an inner loop having a current error amplifier to control the input line current and the outer loop involving fuzzy logic controller (FLC), to control the output voltage. This makes the input current be shaped in phase with input voltage accordingly with reference parameters. The proposed system is verified using extensive simulations in MATLAB/Simulink and the results are compared with PI-based PFC. Results show that the proposed scheme improves the performance significantly with total harmonic distortion (THD) limited to IEEE standards limit having nearly unity power factor. © 2023 IEEE.