Browsing by Author "Karmakar, S."

Filter results by typing the first few letters
Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    A study on solubility of bismuth cations in nickel cobalt ferrite nanoparticles and their influence on dielectric and magnetic properties
    (Elsevier Ltd, 2023) Patil, S.; Meti, S.; Kanavi, P.S.; Bhajantri, R.F.; Anandalli, M.; Mondal, R.; Karmakar, S.; Muhiuddin, M.; Rahman, M.R.; Kumar, B.C.; Hegde, B.G.
    In this work, a low temperature (∼600 °C) solution combustion technique is employed for the synthesis of Ni0.5Co0.5BixFe2-xO4 (NCBFO, where x = 0.0, 0.05, 0.1, 0.15, & 0.2) nanoparticles with crystallite size variation of 17–22 nm. The X-ray diffraction (XRD) technique is used to confirm the formation of cubic spinel phase of Bi3+ doped (for x ≤ 0.05 samples) nickel–cobalt ferrite (NCFO) nanoparticles. The increase in bismuth substitution (x > 0.05) results in the formation of the Bi2O3 along with the NCFO structure, which results in the reduction of binding energy and is confirmed by the XRD and X-ray photoelectron spectroscopy (XPS) techniques. From the Raman spectra, the change in the intensities of the peaks is observed due to the variation of Bi3+ in NCFO matrix. Due to increasing cation concentration and electronegativity, the FTIR absorption band shifts toward the lower wave numbers. Dielectric measurements were carried out to examine the charge transport behavior and electric conduction mechanism. The FESEM images shows the non-magnetic bismuth atoms are diffused into the NCFO nanoparticles. From the vibrating sample magnetometer (VSM) analysis, it is observed that saturation magnetization, remanent magnetization, coercivity and squareness ratio are found to be maximum for x = 0.15 NCBFO sample. The high coercivity (Hc = 916.8 Oe) for the x = 0.15 sample indicates the hard ferromagnetic behaviour of the samples. © 2023 Elsevier B.V.
  • No Thumbnail Available
    Item
    Measuring the Severity of the Signs of Eating Disorders Using Machine Learning Techniques
    (CEUR-WS, 2024) Prasanna, S.; Gulati, A.; Karmakar, S.; Hiranmayi, M.Y.; Anand Kumar, M.
    The paper presents the results submitted by Team SCaLAR-NITK for task 3 of eRisk Lab at CLEF 2024 [1]. The dataset provided by the task organizers consisted of 74 subjects for training and 18 for testing. We begin by describing the data cleaning and preprocessing steps. Subsequently, we outline various approaches used to address the problem, such as Word2Vec, TF-IDF, Backtranslation and Dimensionality Reduction, among others. Finally, we summarize the results obtained from each approach. Our solutions demonstrated strong performance, achieving the best results in 7 out of the 8 evaluated metrics. © 2024 Copyright for this paper by its authors.
  • No Thumbnail Available
    Item
    Rice Disease Prediction using Deep Learning for farmers
    (Institute of Electrical and Electronics Engineers Inc., 2025) Prasanna, S.; Rasal, S.S.; Karmakar, S.; Guddeti, R.M.R.
    This paper addresses the problem of classifying diseases prevalent in Rice (Paddy) crops in Karnataka by leveraging deep learning and feature extraction techniques. Two distinct methodologies were explored to enhance disease identification accuracy. The first method utilized a transfer learning approach with ResNet-50, incorporating dynamic learning rate scheduling with warm-up and cosine annealing strategies. This ensured efficient convergence while maintaining high generalization performance. The second method combined deep learning-based feature extraction with handcrafted features such as HOG, LBP, and color histograms. This hybrid feature fusion approach enabled a comprehensive representation of disease patterns. Experimental results demonstrated that both methodologies achieved high classification accuracy, with the hybrid model excelling in complex disease identification scenarios. © 2025 IEEE.