Showing papers by "National Institute of Technology, Karnataka published in 2022"

Molybdenum as a versatile dopant in SnTe: a promising material for thermoelectric application

Abstract: The key to enhancing the thermoelectric performance of SnTe is to engineer its electronic structure by doping. It is essential that the beneficial features are exhibited at the Fermi level so as to exploit the benefits without the use of a co-dopant. We report molybdenum as such a versatile dopant in SnTe. The first-principles calculations reveal that Mo is able to introduce resonance levels as well as increase the band gap in SnTe. It not only causes the convergence of light and heavy hole valence sub-bands but also does so in the conduction band. The unique feature is the Rashba splitting of the conduction bands, leading to multiband transport. The transport properties calculated using Boltzmann transport equations predict the dual nature of the resonant dopant with a promising ZT of ∼1.84 and ∼1.1 as a p- and an n-type dopant, respectively, in SnTe at 800 K.

Classification of Multiple Retinal Disorders from Enhanced Fundus Images Using Semi-supervised GAN

Abstract: Automatic detection of retinal disorders is gaining considerable attention with the emergence of deep learning. Ophthalmologists primarily use color fundus photographs to examine the human retina and diagnose the abnormalities. As there is a surge in the number of visual impairments, an AI-enabled retina screening system can expedite the retina examination process. Existing works in this direction are primarily focused on either segmentation or classification. Furthermore, the majority of the works are implemented using preprocessed good quality fundus images. In reality, however, the quality of color fundus images is degraded due to the illumination inhomogeneity and low contrast issues. Thus, there is a need to develop an end-to-end fundus image analysing system. Steering in this direction, the proposed work attempts to analyze the performance of semi-supervised Generative Adversarial Networks (GANs) for the classification of retinal fundus images into multiple categories. Besides, the nonlocal retinex framework is applied to enhance the quality of fundus images without over-smoothing the edges. The large data set of raw fundus acquired from multiple Eye hospitals and released in public domain is used to implement the proposed work. The results obtained are compared with the transfer learning method, and an average accuracy of 87% is obtained. It suggests that the semi-supervised GANs can be potentially used to classify heterogeneous retinal disorders.

An Echo State Network Imparts a Curve Fitting

Abstract: Recurrent neural networks (RNNs) are successfully employed in processing information from temporal data. Approaches to training such networks are varied and reservoir computing-based attainments, such as the echo state network (ESN), provide great ease in training. Akin to many machine learning algorithms rendering an interpolation function or fitting a curve, we observe that a driven system, such as an RNN, renders a continuous curve fitting if and only if it satisfies the echo state property. The domain of the learned curve is an abstract space of the left-infinite sequence of inputs and the codomain is the space of readout values. When the input originates from discrete-time dynamical systems, we find theoretical conditions under which a topological conjugacy between the input and reservoir dynamics can exist and present some numerical results relating the linearity in the reservoir to the forecasting abilities of the ESNs.

Deep Learning for COVID-19

Abstract: Ever since the outbreak in Wuhan, China, a variant of Coronavirus named “COVID 19” has taken human lives in millions all around the world. The detection of the infection is quite tedious since it takes 3–14 days for the symptoms to surface in patients. Early detection of the infection and prohibiting it would limit the spread to only to Local Transmission. Deep learning techniques can be used to gain insights on the early detection of infection on the medical image data such as Computed Tomography (CT images), Magnetic resonance Imaging (MRI images), and X-Ray images collected from the infected patients provided by the Medical institution or from the publicly available databases. The same techniques can be applied to do the analysis of infection rates and do predictions for the coming days. A wide range of open-source pre-trained models that are trained for general classification or segmentation is available for the proposed study. Using these models with the concept of transfer learning, obtained resultant models when applied to the medical image datasets would draw much more insights into the COVID-19 detection and prediction process. Innumerable works have been done by researchers all over the world on the publicly available COVID-19 datasets and were successful in deriving good results. Visualizing the results and presenting the summarized data of prediction in a cleaner, unambiguous way to the doctors would also facilitate the early detection and prevention of COVID-19 Infection.

Comparison of Hyperspectral Atmospheric Correction Algorithms for Precise Mapping of Rice Crop

Abstract: For millions of people, rice means life, and therefore, it is harvested in many regions of the world. Two rice species are primarily cultivated in the world, namely Asian and African rice. It grows primarily in major river deltas, such as Asia and Southeast Asia. Conventional method of mapping rice crop area is tedious and time-consuming job and more often subjected to erroneous results. In this study advanced remote sensing technique is used for mapping, to map precisely hyperspectral remote sensing with different atmospheric algorithms were compared for better accuracy. Also different supervised classification techniques were compared for the accurate area mapping of rice crop. The ASD field spec Pro hand held spectroradiometer is used for reference spectra collection. And high accuracy GPS device is used to collect ground truth information. Results show that both FLAASH and HAC algorithms produce a good spectrum with respect to the rice spectra obtained from ASD handheld spectroradiometer. SAM image classification and Parallelepiped classifier were used for classification of imagery. From the accuracy assessment performed, accuracy of 88% by using SAM and 84% obtained using Parallelepiped classifier for Hooghly region and 93% using SAM and 87% using Parallelepiped for West Godavari region. From the study, it was found that the best approach for rice crop mapping in Hooghly and West Godavari is SAM classification. The study helps to map the rice crop area accurately; it can be used for yield estimation, indirectly which is helpful for policy makers and to estimate the export, import potential.

Deep neural models for automated multi-task diagnostic scan management-quality enhancement, view classification and report generation.

Abstract: The detailed physiological perspectives captured by medical imaging provides actionable insights to doctors to manage comprehensive care of patients. However, the quality of such diagnostic image modalities is often affected by mismanagement of the image capturing process by poorly trained technicians and older/poorly maintained imaging equipment. Further, a patient is often subjected to scanning at different orientations to capture the frontal, lateral and sagittal views of the affected areas. Due to the large volume of diagnostic scans performed at a modern hospital, adequate documentation of such additional perspectives is mostly overlooked, which is also an essential key element of quality diagnostic systems and predictive analytics systems. Another crucial challenge affecting effective medical image data management is that the diagnostic scans are essentially stored as unstructured data, lacking a well-defined processing methodology for enabling intelligent image data management for supporting applications like similar patient retrieval , automated disease prediction etc. One solution is to incorporate automated diagnostic image descriptions of the observation/findings by leveraging computer vision and natural language processing. In this work, we present multi-task neural models capable of addressing these critical challenges. We propose ESRGAN, an image enhancement technique for improving the quality and visualization of medical chest x-ray images, thereby substantially improving the potential for accurate diagnosis, automatic detection and region-of-interest segmentation. We also propose a CNN-based model called ViewNet for predicting the view orientation of the x-ray image and generating a medical report using Xception net, thus facilitating a robust medical image management system for intelligent diagnosis applications. Experimental results are demonstrated using standard metrics like BRISQUE, PIQE and BLEU scores, indicating that the proposed models achieved excellent performance. Further, the proposed deep learning approaches enable diagnosis in a lesser time and their hybrid architecture shows significant potential for supporting many intelligent diagnosis applications.