arXiv subjects

Satyendra Singh

Publications and source records attributed to Satyendra Singh.

8 recordsLinked to original sources

arXiv2026

Classification of Disease from Lungs X-ray Images using VGG16, VGG19 and ResNet50 Models

With the increase in the number of cases related to respiratory diseases, there is an urgent need to detect them early and diagnose them accurately. Convolutional neural networks have given promising results when used for diagnosing diseases using imaging tests. In this study, we investigate the potential of applying deep learning algorithms such as VGG16, VGG19, and ResNet50 for classification of lung ailments based on X-ray images. A detailed analysis of the aforementioned models' performances was conducted to assess how well they can classify various types of lung ailments, including pneumonia, tuberculosis, lung cancer, and normal lungs. In order to do that, these deep learning models were trained on a vast amount of X-ray images. The results of our study show that while all three models provide good results, ResNet-50 performs best in comparison with other models due to its efficiency and high level of accuracy. We believe that these deep learning models can be successfully implemented in the practice of diagnosing pulmonary diseases in the future. It helps with early disease detection and improves patient outcomes.

cs.CV↗

arXiv2026

Motion-Aware Reinforcement Learning For Object Localization

We present MARLNet (Motion-Aware Reinforcement Learning Network), a PPO-based bounding-box refinement agent that incorporates a constant-velocity motion prior into the observation state and an action smoothness penalty into the reward function. The agent operates on 268-dimensional observations encoding the current proposal, a kinematic prediction, the previous action, and a 256-dimensional EfficientNet-B0 crop feature, and learns a five-dimensional policy controlling coordinate adjustments and a binary termination trigger. Evaluated on Pascal VOC 2012 and VisDrone 2019, MARLNet trains stably across all regularization strengths tested and achieves consistent gains in detection success rate at $\text{IoU} \geq 0.5$: up to $+0.011$ on VOC ($\lambda_\text{phys}{=}0.10$), where the motion prior prevents the overshooting that causes plain PPO to regress on this metric, and $+0.007$ on VisDrone ($\lambda_\text{phys}{=}0.70$), where unconstrained PPO achieves a larger gain ($+0.025$) owing to the weaker base detector. Through reward design ablations and training dynamics analysis, we identify a reward interference in which combining a constant-velocity deviation penalty with an absolute IoU term causes trigger collapse, and show that replacing it with the action smoothness penalty resolves this failure. We further characterize a representational ceiling facing crop-feature refinement agents that share a backbone with their base detector, confirmed through a global-plus-local observation ablation. Project page: https://prithviraj97.github.io/marl-net

cs.CV↗

arXiv2024

Sn$_{0.06}$Cr$_3$Te$_4$: A Skyrmion Superconductor

Topological superconductors are an exciting class of quantum materials from the point of view of the fundamental sciences and potential technological applications. Here, we report on the successful introduction of superconductivity in a ferromagnetic layered skyrmion system Cr$_3$Te$_4$, obtained by the Sn intercalation, below a transition temperature of $T_c$$\approx$3.5 K. We observe several interesting physical properties, such as superconductivity, magnetism, and the topological Hall effect, simultaneously in this system. Despite the magnetism and Meissner effects being anisotropic, the superconductivity observed from the in-plane electrical resistivity ($ρ_{\it{bc}}$) is nearly isotropic between $H\parallel \it{bc}$ and $H\parallel \it{a}$, suggesting separate channels of conduction electrons responsible for the superconductivity and magnetism of this system, which is also supported by our spin-resolved DFT calculations. We identify two orders of higher carrier density in superconducting Sn$_{0.06}$Cr$_{3}$Te$_4$ than the parent Cr$_3$Te$_4$. A jump in the specific heat is noticed around the $T_c$ with a volume fraction of 33\%, confirming the bulk superconductivity in Sn$_{0.06}$Cr$_{3}$Te$_4$. In addition to the introduction of superconductivity, tuning of topological Hall properties is noticed with Sn intercalation. Our observation of superconductivity in a skyrmion lattice brings up a new class of topological quantum materials.

cond-mat.supr-con↗

arXiv2024

Medical Image Analysis for Detection, Treatment and Planning of Disease using Artificial Intelligence Approaches

X-ray is one of the prevalent image modalities for the detection and diagnosis of the human body. X-ray provides an actual anatomical structure of an organ present with disease or absence of disease. Segmentation of disease in chest X-ray images is essential for the diagnosis and treatment. In this paper, a framework for the segmentation of X-ray images using artificial intelligence techniques has been discussed. Here data has been pre-processed and cleaned followed by segmentation using SegNet and Residual Net approaches to X-ray images. Finally, segmentation has been evaluated using well known metrics like Loss, Dice Coefficient, Jaccard Coefficient, Precision, Recall, Binary Accuracy, and Validation Accuracy. The experimental results reveal that the proposed approach performs better in all respect of well-known parameters with 16 batch size and 50 epochs. The value of validation accuracy, precision, and recall of SegNet and Residual Unet models are 0.9815, 0.9699, 0.9574, and 0.9901, 0.9864, 0.9750 respectively.

eess.IV↗

arXiv2012

Nanostructured antimony tin oxide synthesized via chemical precipitation method: its characterization and application in humidity sensing

In present investigation we report the synthesis of antimony tin oxide nanoparticles via chemical precipitation method. The synthesized material was characterized using X-ray diffractometer, Scanning Electron Microscope, UV-visible absorption spectroscopy. XRD shows the crystalline nature of the synthesized material and the crystallite size was estimated by using Debye-Scherer equation and its minimum value was 3 nm. Pelletization of synthesized material was done using hydraulic press machine under uniform pressure of 616 MPa. Then the pellets were annealed at 200, 400 and 600°C. Further each pellet was put in humidity sensing chamber and corresponding variations in resistance with relative humidity (%RH) were measured. The average sensitivity was calculated by taking the average of all sensitivities ranging from 10 to 90% RH. The average sensitivity of the pellet annealed at 600°C was best among all the sensing pellets and was 2.18 KΩ/%RH. Results were reproducible {\pm}84% after 2 months.

cond-mat.mtrl-sci↗

arXiv2012

Temperature Sensors based on Semiconducting Oxides: An Overview

Earlier studies show that organic and inorganic semiconducting materials are the most promising materials for use in temperature sensors. In this brief review, attention will be focused on temperature sensors and its applications in various fields. In addition, we have investigated the temperature sensing characteristics of nanostructured ZnO and ZnO-CuO nanocomposite. For this purpose, ZnO and ZnO-CuO nanocomposite were synthesized via chemical precipitation method. Scanning electron microscopy and X-ray diffraction of sensing materials have also performed. The average crystallite size was 45 and 68 nm for ZnO and ZnO-CuO respectively. The pelletization of the synthesized powder was done using hydraulic pressing machine (MB Instrument, Delhi) under a pressure of 616 MPa at room ambient. This pellet was put within the Ag-Pellet-Ag electrode configuration for temperature sensing. Temperature sensitivities of above semiconducting oxides were calculated. Electrical properties of the materials establish the semiconducting nature of these sensing pellets. In addition, the activation energies of ZnO and ZnO-CuO nanocomposite were estimated.

cond-mat.mtrl-sci↗

arXiv2012

Titania Prepared by Ball Milling: Its Characterization and Application as Liquefied Petroleum Gas Sensor

Present paper reports the LPG sensing of TiO2 obtained through ball milling. The milled powder was characterized by XRD, TEM and UV-visible spectroscopy. Further the ball milled powder was compressed in to pellet using hydraulic press. This pellet was investigated with the exposure of LPG. Variations in resistance with exposure of LPG to the sensing pellet were recorded. The sensitivity of the sensor was ~ 11 for 5 vol.% of LPG. Response and recovery times of the sensor were ~ 100 and 250 sec. The sensor was quite sensitive to LPG and results were found reproducible within 91%.

physics.chem-ph↗

arXiv2007

A succession of relaxor ferroelectric transitions coexisting with ferroelectric states in Ba_0.55Sr_0.45TiO_3

We present here the results of frequency dependent dielectric, polarization and powder X-ray powder diffraction studies in the 300 to 100K temperature range for Ba_0.55Sr_0.45TiO_3. The dielectric results indicate a succession of three relaxor ferroelectric transitions accompanying the cubic to tetragonal to orthorhombic to rhombohedral phase transitions confirmed by XRD studies. Our results confirm the coexistence of the relaxor ferroelectric and ferroelectric behaviours.

cond-mat.mtrl-sci↗