arXiv subjects

Mayank Gupta

Publications and source records attributed to Mayank Gupta.

32 records · Page 2Linked to original sources

arXiv2022

Surpassing the Human Accuracy: Detecting Gallbladder Cancer from USG Images with Curriculum Learning

We explore the potential of CNN-based models for gallbladder cancer (GBC) detection from ultrasound (USG) images as no prior study is known. USG is the most common diagnostic modality for GB diseases due to its low cost and accessibility. However, USG images are challenging to analyze due to low image quality, noise, and varying viewpoints due to the handheld nature of the sensor. Our exhaustive study of state-of-the-art (SOTA) image classification techniques for the problem reveals that they often fail to learn the salient GB region due to the presence of shadows in the USG images. SOTA object detection techniques also achieve low accuracy because of spurious textures due to noise or adjacent organs. We propose GBCNet to tackle the challenges in our problem. GBCNet first extracts the regions of interest (ROIs) by detecting the GB (and not the cancer), and then uses a new multi-scale, second-order pooling architecture specializing in classifying GBC. To effectively handle spurious textures, we propose a curriculum inspired by human visual acuity, which reduces the texture biases in GBCNet. Experimental results demonstrate that GBCNet significantly outperforms SOTA CNN models, as well as the expert radiologists. Our technical innovations are generic to other USG image analysis tasks as well. Hence, as a validation, we also show the efficacy of GBCNet in detecting breast cancer from USG images. Project page with source code, trained models, and data is available at https://gbc-iitd.github.io/gbcnet

cs.CV↗

arXiv2022

Spin Texture as Polarization Fingerprint of Halide Perovskites

Halide perovskites are perceived to be the promising class of materials for optoelectronics, spinorbitronics and topological electronics due to presence of strong spin-orbit coupling and polarized field. Here, we develop a Hamiltonian using quasi-degenerate perturbation theory to describe polarized field driven band structures and unique topological phases such as Dirac semimetallic rings for the universal class of Halide perovskites including both inorganic and hybrid members. The spin textures obtained through this theoretical model captures minute effects of polarization and hence can be used as a modern tool to determine the polarized field directions which have significant influence on spinorbitronics. The analysis brings out the concepts of hybrid spin textures intermixing the effects of valence and conduction bands under topological quantum phase transitions, and spin texture binaries where alignment of the spins are reversed between domains in the momentum space with sharp boundaries. The results are validated through density functional calculations.

cond-mat.mtrl-sci↗

arXiv2021

A Supervised Learning Approach for Robust Health Monitoring using Face Videos

Monitoring of cardiovascular activity is highly desired and can enable novel applications in diagnosing potential cardiovascular diseases and maintaining an individual's well-being. Currently, such vital signs are measured using intrusive contact devices such as an electrocardiogram (ECG), chest straps, and pulse oximeters that require the patient or the health provider to manually implement. Non-contact, device-free human sensing methods can eliminate the need for specialized heart and blood pressure monitoring equipment. Non-contact methods can have additional advantages since they are scalable with any environment where video can be captured, can be used for continuous measurements, and can be used on patients with varying levels of dexterity and independence, from people with physical impairments to infants (e.g., baby camera). In this paper, we used a non-contact method that only requires face videos recorded using commercially-available webcams. These videos were exploited to predict the health attributes like pulse rate and variance in pulse rate. The proposed approach used facial recognition to detect the face in each frame of the video using facial landmarks, followed by supervised learning using deep neural networks to train the machine learning model. The videos captured subjects performing different physical activities that result in varying cardiovascular responses. The proposed method did not require training data from every individual and thus the prediction can be obtained for the new individuals for which there is no prior data; critical in approach generalization. The approach was also evaluated on a dataset of people with different ethnicity. The proposed approach had less than a 4.6\% error in predicting the pulse rate.

cs.CV↗

arXiv2021

A Generic Slater-Koster Description of the Electronic Structure of Centrosymmetric Halide Perovskites

The halide perovskites have truly emerged as efficient optoelectronic materials and show the promise of exhibiting nontrivial topological phases. Since the bandgap is the deterministic factor for these quantum phases, here we present a comprehensive electronic structure study using first-principle methods by considering nine inorganic halide perovskites CsBX$_3$ (B = Ge, Sn, Pb; X = Cl, Br, I) in their three structural polymorphs (cubic, tetragonal and orthorhombic). A series of exchange-correlations (XC) functionals are examined towards accurate estimation of the bandgap. Furthermore, while thirteen orbitals are active in constructing the valence and conduction band spectrum, here we establish that a four orbital based minimal basis set is sufficient to build the Slater-Koster tight-binding model (SK-TB), which is capable of reproducing the bulk and surface electronic structure in the vicinity of the Fermi level. Therefore, like the Wannier based TB model, the presented SK-TB model can also be considered as an efficient tool to examine the bulk and surface electronic structure of halide family of compounds. As estimated by comparing the model study and DFT band structure, the dominant electron coupling strengths are found to be nearly independent of XC functionals, which further establishes the utility of the SK-TB model.

cond-mat.mtrl-sci↗

arXiv2020

Improving Human-Labeled Data through Dynamic Automatic Conflict Resolution

This paper develops and implements a scalable methodology for (a) estimating the noisiness of labels produced by a typical crowdsourcing semantic annotation task, and (b) reducing the resulting error of the labeling process by as much as 20-30% in comparison to other common labeling strategies. Importantly, this new approach to the labeling process, which we name Dynamic Automatic Conflict Resolution (DACR), does not require a ground truth dataset and is instead based on inter-project annotation inconsistencies. This makes DACR not only more accurate but also available to a broad range of labeling tasks. In what follows we present results from a text classification task performed at scale for a commercial personal assistant, and evaluate the inherent ambiguity uncovered by this annotation strategy as compared to other common labeling strategies.

cs.CL↗

arXiv2020

Defining the Topological Influencers and Predictive Principles to Engineer Band Structure of Halide Perovskites

Complex quantum coupling phenomena of halide perovskites are examined through ab-initio calculations and exact diagonalization of model Hamiltonians to formulate a set of fundamental guiding rules to engineer the bandgap through strain. The bandgap tuning in halides is crucial for photovoltaic applications and for establishing non-trivial electronic states. Using CsSnI$_3$ as the prototype material, we show that in the cubic phase, the bandgap reduces irrespective of the nature of strain. However, for the tetragonal phase, it reduces with tensile strain and increases with compressive strain, while the reverse is the case for the orthorhombic phase. The reduction can give rise to negative bandgap in the cubic and tetragonal phases leading to normal to topological insulator phase transition. Also, these halides tend to form a stability plateau in a space spanned by strain and octahedral rotation. In this plateau, with negligible cost to the total energy, the bandgap can be varied in a range of 1eV. Furthermore, we present a descriptor model for the perovskite to simulate their bandgap with strain and rotation. Analysis of band topology through model Hamiltonians led to the conceptualization of topological influencers that provide a quantitative measure of the contribution of each chemical bonding towards establishing a normal or topological insulator phase. On the technical aspect, we show that a four orbital based basis set (Sn-$\{s,p\}$ for CsSnI$_3$) is sufficient to construct the model Hamiltonian which can explain the electronic structure of each polymorph of halide perovskites.

cond-mat.mtrl-sci↗

arXiv2020

Pressure and Inversion Symmetry Breaking Field Driven First Order Phase Transition and Formation of Dirac Circle in Perovskites

Through model Hamiltonian studies and first-principle electronic structure calculations, we have examined the effect of inversion symmetry breaking (ISB) field and hydrostatic pressure on the band topology of halide perovskites by taking MAPbI$_3$ as a prototype. Our study shows that while hydrostatic pressure induces normal to topological insulator continuous phase transition, the ISB field makes it first order. The pressure smoothly reduces the normal bandgap, and without ISB, the system achieves a gapless state before it produces a non-trivial bandgap with inverted characters. The ISB field does not stabilize the gapless state, and therefore, the discontinuity in the bandgap with pressure gives rise to the first-order transition. Furthermore, in the non-trivial phase, the ISB field forms an invariant surface Dirac circle in the neighbourhood of TRIM, which is first of its kind. The circle is formed due to interpenetration of Dirac cones resembling the band topology of AA-stacked bilayer graphene.

cond-mat.mtrl-sci↗

arXiv2018

Covfefe: A Computer Vision Approach For Estimating Force Exertion

Cumulative exposure to repetitive and forceful activities may lead to musculoskeletal injuries which not only reduce workers' efficiency and productivity, but also affect their quality of life. Thus, widely accessible techniques for reliable detection of unsafe muscle force exertion levels for human activity is necessary for their well-being. However, measurement of force exertion levels is challenging and the existing techniques pose a great challenge as they are either intrusive, interfere with human-machine interface, and/or subjective in the nature, thus are not scalable for all workers. In this work, we use face videos and the photoplethysmography (PPG) signals to classify force exertion levels of 0\%, 50\%, and 100\% (representing rest, moderate effort, and high effort), thus providing a non-intrusive and scalable approach. Efficient feature extraction approaches have been investigated, including standard deviation of the movement of different landmarks of the face, distances between peaks and troughs in the PPG signals. We note that the PPG signals can be obtained from the face videos, thus giving an efficient classification algorithm for the force exertion levels using face videos. Based on the data collected from 20 subjects, features extracted from the face videos give 90\% accuracy in classification among the 100\% and the combination of 0\% and 50\% datasets. Further combining the PPG signals provide 81.7\% accuracy. The approach is also shown to be robust to the correctly identify force level when the person is talking, even though such datasets are not included in the training.

cs.HC↗

arXiv2018

Parametric Synthesis of Text on Stylized Backgrounds using PGGANs

We describe a novel method of generating high-resolution real-world images of text where the style and textual content of the images are described parametrically. Our method combines text to image retrieval techniques with progressive growing of Generative Adversarial Networks (PGGANs) to achieve conditional generation of photo-realistic images that reflect specific styles, as well as artifacts seen in real-world images. We demonstrate our method in the context of automotive license plates. We assess the impact of varying the number of training images of each style on the fidelity of the generated style, and demonstrate the quality of the generated images using license plate recognition systems.

cs.CV↗

arXiv2018

Learning to Navigate Autonomously in Outdoor Environments : MAVNet

In the modern era of automation and robotics, autonomous vehicles are currently the focus of academic and industrial research. With the ever increasing number of unmanned aerial vehicles getting involved in activities in the civilian and commercial domain, there is an increased need for autonomy in these systems too. Due to guidelines set by the governments regarding the operation ceiling of civil drones, road-tracking based navigation is garnering interest . In an attempt to achieve the above mentioned tasks, we propose an imitation learning based, data-driven solution to UAV autonomy for navigating through city streets by learning to fly by imitating an expert pilot. Derived from the classic image classification algorithms, our classifier has been constructed in the form of a fast 39-layered Inception model, that evaluates the presence of roads using the tomographic reconstructions of the input frames. Based on the Inception-v3 architecture, our system performs better in terms of processing complexity and accuracy than many existing models for imitation learning. The data used for training the system has been captured from the drone, by flying it in and around urban and semi-urban streets, by experts having at least 6-8 years of flying experience. Permissions were taken from required authorities who made sure that minimal risk (to pedestrians) is involved in the data collection process. With the extensive amount of drone data that we collected, we have been able to navigate successfully through roads without crashing or overshooting, with an accuracy of 98.44%. The computational efficiency of MAVNet enables the drone to fly at high speeds of upto 6m/sec. We present the same results in this research and compare them with other state-of-the-art methods of vision and learning based navigation.

cs.RO↗

arXiv2018

Compressive Light Field Reconstructions using Deep Learning

Light field imaging is limited in its computational processing demands of high sampling for both spatial and angular dimensions. Single-shot light field cameras sacrifice spatial resolution to sample angular viewpoints, typically by multiplexing incoming rays onto a 2D sensor array. While this resolution can be recovered using compressive sensing, these iterative solutions are slow in processing a light field. We present a deep learning approach using a new, two branch network architecture, consisting jointly of an autoencoder and a 4D CNN, to recover a high resolution 4D light field from a single coded 2D image. This network decreases reconstruction time significantly while achieving average PSNR values of 26-32 dB on a variety of light fields. In particular, reconstruction time is decreased from 35 minutes to 6.7 minutes as compared to the dictionary method for equivalent visual quality. These reconstructions are performed at small sampling/compression ratios as low as 8%, allowing for cheaper coded light field cameras. We test our network reconstructions on synthetic light fields, simulated coded measurements of real light fields captured from a Lytro Illum camera, and real coded images from a custom CMOS diffractive light field camera. The combination of compressive light field capture with deep learning allows the potential for real-time light field video acquisition systems in the future.

cs.CV↗

arXiv2016

A Comparison of the Triangle Algorithm and SMO for Solving the Hard Margin Problem

In this article we consider the problem of testing, for two finite sets of points in the Euclidean space, if their convex hulls are disjoint and computing an optimal supporting hyperplane if so. This is a fundamental problem of classification in machine learning known as the hard-margin SVM. The problem can be formulated as a quadratic programming problem. The SMO algorithm is the current state of art algorithm for solving it, but it does not answer the question of separability. An alternative to solving both problems is the Triangle Algorithm, a geometrically inspired algorithm, initially described for the convex hull membership problem, a fundamental problem in linear programming. First, we describe the experimental performance of the Triangle Algorithm for testing the intersection of two convex hulls. Next, we compare the performance of Triangle Algorithm with SMO for finding the optimal supporting hyperplane. Based on experimental results ranging up to 5000 points in each set in dimensions up to 10000, the Triangle Algorithm outperforms SMO.

cs.CG↗

arXiv2013

ChaMAILeon: Exploring the Usability of a Privacy Preserving Email Sharing System

While passwords, by definition, are meant to be secret, recent trends have witnessed an increasing number of people sharing their email passwords with friends, colleagues, and significant others. However, leading websites like Google advise their users not to share their passwords with anyone, to avoid security and privacy breaches. To understand users' general password sharing behavior and practices, we conducted an online survey with 209 Indian participants and found that 64.35% of the participants felt a need to share their email passwords. Further, about 77% of the participants said that they would want to use a system which could provide them access control features, to maintain their privacy while sharing emails. To address the privacy concerns of users who need to share emails, we propose ChaMAILeon, a system which enables users to share their email passwords while maintaining their privacy. ChaMAILeon allows users to create multiple passwords for their email account. Each such password corresponds to a different set of access control rules, and gives a different view of the same email account. We conducted a controlled experiment with 30 participants to evaluate the usability of the system. Each participant was required to perform 5 tasks. Each task corresponded to different access control rules, which the participant was required to set, for a dummy email account. We found that, with a reasonable number of multiple attempts, all 30 participants were able to perform all 5 tasks given to them. The system usability score was found out to be 75.42. Moreover, 56.6% of the participants said that they would like to use ChaMAILeon frequently.

cs.CY↗

arXiv2013

ChaMAILeon: Simplified email sharing like never before!

While passwords, by definition, are meant to be secret, recent trends in the Internet usage have witnessed an increasing number of people sharing their email passwords for both personal and professional purposes. As sharing passwords increases the chances of your passwords being compromised, leading websites like Google strongly advise their users not to share their passwords with anyone. To cater to this conflict of usability versus security and privacy, we introduce ChaMAILeon, an experimental service, which allows users to share their email passwords while maintaining their privacy and not compromising their security. In this report, we discuss the technical details of the implementation of ChaMAILeon.

cs.CY↗