arXiv subjects

Vivek Singh

Publications and source records attributed to Vivek Singh.

At least 37 records · Page 2Linked to original sources

arXiv2024

Toward Safe Evolution of Artificial Intelligence (AI) based Conversational Agents to Support Adolescent Mental and Sexual Health Knowledge Discovery

Following the recent release of various Artificial Intelligence (AI) based Conversation Agents (CAs), adolescents are increasingly using CAs for interactive knowledge discovery on sensitive topics, including mental and sexual health topics. Exploring such sensitive topics through online search has been an essential part of adolescent development, and CAs can support their knowledge discovery on such topics through human-like dialogues. Yet, unintended risks have been documented with adolescents' interactions with AI-based CAs, such as being exposed to inappropriate content, false information, and/or being given advice that is detrimental to their mental and physical well-being (e.g., to self-harm). In this position paper, we discuss the current landscape and opportunities for CAs to support adolescents' mental and sexual health knowledge discovery. We also discuss some of the challenges related to ensuring the safety of adolescents when interacting with CAs regarding sexual and mental health topics. We call for a discourse on how to set guardrails for the safe evolution of AI-based CAs for adolescents.

cs.HC↗

arXiv2024

Pulsed loading of a magneto-optical trap on atom chip for fast pressure recovery in ultrahigh vacuum environment

This study presents investigations on pulsed loading of a magneto-optical trap (MOT) on an atom chip in an UHV environment. Using three parallel resistively heated Rb-metal dispensers activated by pulsed current supply, approximately 3.0 $\times$ $10^{7}$ cold $^{87}Rb$ atoms were loaded into the MOT. A current pulse of $\sim$ 24 A with duration of $\sim$ 10 s raised the pressure in the chamber from 2.0 $\times$ $10^{-10}$ Torr to 3.3 $\times$ $10^{-10}$ Torr. Remarkably, the pressure recovery time after switching off the dispensers current was found to be $\sim$ 600 ms, making a significant advancement in achieving fast recovery of UHV environment surrounding the MOT region. This study is very useful for laser cooling and magnetic trapping / evaporative cooling of atoms on atom chip in the same UHV chamber.

physics.atom-ph↗

arXiv2024

Feature boosting with efficient attention for scene parsing

The complexity of scene parsing grows with the number of object and scene classes, which is higher in unrestricted open scenes. The biggest challenge is to model the spatial relation between scene elements while succeeding in identifying objects at smaller scales. This paper presents a novel feature-boosting network that gathers spatial context from multiple levels of feature extraction and computes the attention weights for each level of representation to generate the final class labels. A novel `channel attention module' is designed to compute the attention weights, ensuring that features from the relevant extraction stages are boosted while the others are attenuated. The model also learns spatial context information at low resolution to preserve the abstract spatial relationships among scene elements and reduce computation cost. Spatial attention is subsequently concatenated into a final feature set before applying feature boosting. Low-resolution spatial attention features are trained using an auxiliary task that helps learning a coarse global scene structure. The proposed model outperforms all state-of-the-art models on both the ADE20K and the Cityscapes datasets.

cs.CV↗

arXiv2024

Cardiac ultrasound simulation for autonomous ultrasound navigation

Ultrasound is well-established as an imaging modality for diagnostic and interventional purposes. However, the image quality varies with operator skills as acquiring and interpreting ultrasound images requires extensive training due to the imaging artefacts, the range of acquisition parameters and the variability of patient anatomies. Automating the image acquisition task could improve acquisition reproducibility and quality but training such an algorithm requires large amounts of navigation data, not saved in routine examinations. Thus, we propose a method to generate large amounts of ultrasound images from other modalities and from arbitrary positions, such that this pipeline can later be used by learning algorithms for navigation. We present a novel simulation pipeline which uses segmentations from other modalities, an optimized volumetric data representation and GPU-accelerated Monte Carlo path tracing to generate view-dependent and patient-specific ultrasound images. We extensively validate the correctness of our pipeline with a phantom experiment, where structures' sizes, contrast and speckle noise properties are assessed. Furthermore, we demonstrate its usability to train neural networks for navigation in an echocardiography view classification experiment by generating synthetic images from more than 1000 patients. Networks pre-trained with our simulations achieve significantly superior performance in settings where large real datasets are not available, especially for under-represented classes. The proposed approach allows for fast and accurate patient-specific ultrasound image generation, and its usability for training networks for navigation-related tasks is demonstrated.

eess.IV↗

arXiv2024

Improving the Performance of Cryogenic Calorimeters with Nonlinear Multivariate Noise Cancellation Algorithms

State-of-the-art physics experiments require high-resolution, low-noise, and low-threshold detectors to achieve competitive scientific results. However, experimental environments invariably introduce sources of noise, such as electrical interference or microphonics. The sources of this environmental noise can often be monitored by adding specially designed "auxiliary devices" (e.g. microphones, accelerometers, seismometers, magnetometers, and antennae). A model can then be constructed to predict the detector noise based on the auxiliary device information, which can then be subtracted from the true detector signal. Here, we present a multivariate noise cancellation algorithm which can be used in a variety of settings to improve the performance of detectors using multiple auxiliary devices. To validate this approach, we apply it to simulated data to remove noise due to electromagnetic interference and microphonic vibrations. We then employ the algorithm to a cryogenic light detector in the laboratory and show an improvement in the detector performance. Finally, we motivate the use of nonlinear terms to better model vibrational contributions to the noise in thermal detectors. We show a further improvement in the performance of a particular channel of the CUORE detector when using the nonlinear algorithm in combination with optimal filtering techniques.

physics.ins-det↗

arXiv2023

Towards Establishing Dense Correspondence on Multiview Coronary Angiography: From Point-to-Point to Curve-to-Curve Query Matching

Coronary angiography is the gold standard imaging technique for studying and diagnosing coronary artery disease. However, the resulting 2D X-ray projections lose 3D information and exhibit visual ambiguities. In this work, we aim to establish dense correspondence in multi-view angiography, serving as a fundamental basis for various clinical applications and downstream tasks. To overcome the challenge of unavailable annotated data, we designed a data simulation pipeline using 3D Coronary Computed Tomography Angiography (CCTA). We formulated the problem of dense correspondence estimation as a query matching task over all points of interest in the given views. We established point-to-point query matching and advanced it to curve-to-curve correspondence, significantly reducing errors by minimizing ambiguity and improving topological awareness. The method was evaluated on a set of 1260 image pairs from different views across 8 clinically relevant angulation groups, demonstrating compelling results and indicating the feasibility of establishing dense correspondence in multi-view angiography.

cs.CV↗

arXiv2023

EEG-Based Reaction Time Prediction with Fuzzy Common Spatial Patterns and Phase Cohesion using Deep Autoencoder Based Data Fusion

Drowsiness state of a driver is a topic of extensive discussion due to its significant role in causing traffic accidents. This research presents a novel approach that combines Fuzzy Common Spatial Patterns (CSP) optimised Phase Cohesive Sequence (PCS) representations and fuzzy CSP-optimized signal amplitude representations. The research aims to examine alterations in Electroencephalogram (EEG) synchronisation between a state of alertness and drowsiness, forecast drivers' reaction times by analysing EEG data, and subsequently identify the presence of drowsiness. The study's findings indicate that this approach successfully distinguishes between alert and drowsy mental states. By employing a Deep Autoencoder-based data fusion technique and a regression model such as Support Vector Regression (SVR) or Least Absolute Shrinkage and Selection Operator (LASSO), the proposed method outperforms using individual feature sets in combination with a regressor model. This superiority is measured by evaluating the Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), and Correlation Coefficient (CC). In other words, the fusion of autoencoder-based amplitude EEG power features and PCS features, when used in regression, outperforms using either of these features alone in a regressor model. Specifically, the proposed data fusion method achieves a 14.36% reduction in RMSE, a 25.12% reduction in MAPE, and a 10.12% increase in CC compared to the baseline model using only individual amplitude EEG power features and regression.

eess.SP↗

arXiv2023

Development of a pyramidal magneto-optical trap for pressure sensing application

Here, we report the development and working of a compact rubidium (Rb) atom magneto-optical trap (MOT) operated with a hollow pyramidal mirror and a single laser beam. This type of compact MOT is suitable for developing portable atom-optic devices, as it works with less number of optical components as compared to conventional MOT setup. The application of this compact MOT setup for pressure sensing has been demonstrated.

physics.atom-ph↗

arXiv2023

Automated CT Lung Cancer Screening Workflow using 3D Camera

Despite recent developments in CT planning that enabled automation in patient positioning, time-consuming scout scans are still needed to compute dose profile and ensure the patient is properly positioned. In this paper, we present a novel method which eliminates the need for scout scans in CT lung cancer screening by estimating patient scan range, isocenter, and Water Equivalent Diameter (WED) from 3D camera images. We achieve this task by training an implicit generative model on over 60,000 CT scans and introduce a novel approach for updating the prediction using real-time scan data. We demonstrate the effectiveness of our method on a testing set of 110 pairs of depth data and CT scan, resulting in an average error of 5mm in estimating the isocenter, 13mm in determining the scan range, 10mm and 16mm in estimating the AP and lateral WED respectively. The relative WED error of our method is 4%, which is well within the International Electrotechnical Commission (IEC) acceptance criteria of 10%.

eess.IV↗

arXiv2023

Temporal DINO: A Self-supervised Video Strategy to Enhance Action Prediction

The emerging field of action prediction plays a vital role in various computer vision applications such as autonomous driving, activity analysis and human-computer interaction. Despite significant advancements, accurately predicting future actions remains a challenging problem due to high dimensionality, complex dynamics and uncertainties inherent in video data. Traditional supervised approaches require large amounts of labelled data, which is expensive and time-consuming to obtain. This paper introduces a novel self-supervised video strategy for enhancing action prediction inspired by DINO (self-distillation with no labels). The Temporal-DINO approach employs two models; a 'student' processing past frames; and a 'teacher' processing both past and future frames, enabling a broader temporal context. During training, the teacher guides the student to learn future context by only observing past frames. The strategy is evaluated on ROAD dataset for the action prediction downstream task using 3D-ResNet, Transformer, and LSTM architectures. The experimental results showcase significant improvements in prediction performance across these architectures, with our method achieving an average enhancement of 9.9% Precision Points (PP), highlighting its effectiveness in enhancing the backbones' capabilities of capturing long-term dependencies. Furthermore, our approach demonstrates efficiency regarding the pretraining dataset size and the number of epochs required. This method overcomes limitations present in other approaches, including considering various backbone architectures, addressing multiple prediction horizons, reducing reliance on hand-crafted augmentations, and streamlining the pretraining process into a single stage. These findings highlight the potential of our approach in diverse video-based tasks such as activity recognition, motion planning, and scene understanding.

cs.CV↗

arXiv2023

Ultra-high vacuum pressure measurement using cold atoms

In this work, we have measured the background pressure in an ultra-high vacuum (UHV) chamber by measuring the collisional loss rates in a Rb atom magneto-optical trap (MOT) on an atom chip. The loss rate due to non-Rb gases in the background has been estimated by measuring the MOT loss rate in low Rb pressure regime. These results can be useful for development of cold-atoms based UHV pressure standards.

physics.atom-ph↗

arXiv2023

Canonical Purification and the Quantum Extremal Shock

We study the canonical purification (with respect to one of the parties) of pure, bi-partite states obtained by turning on sources in the Euclidean path integral. In holographic conformal field theories, the Lorentzian bulk dual of the canonical purification consists of the corresponding entanglement wedge glued to its CPT image at the quantum extremal surface. However, the mismatch in the classical expansions at the QES due to quantum corrections needs to be supported by a shock in the bulk matter stress tensor in order for the bulk to satisfy Einstein's equations. Working perturbatively to first order in double-trace sources around the thermofield double state, we demonstrate that the state of the bulk matter in the dual to the canonically purified boundary CFT state precisely has this quantum extremal shock in the bulk stress tensor. We interpret our results as the emergence of gravitational physics from the CFT entanglement structure in a context where bulk quantum corrections are important.

hep-th↗

arXiv2022

Large Scale Mask Optimization Via Convolutional Fourier Neural Operator and Litho-Guided Self Training

Machine learning techniques have been extensively studied for mask optimization problems, aiming at better mask printability, shorter turnaround time, better mask manufacturability, and so on. However, most of these researches are focusing on the initial solution generation of small design regions. To further realize the potential of machine learning techniques on mask optimization tasks, we present a Convolutional Fourier Neural Operator (CFNO) that can efficiently learn layout tile dependencies and hence promise stitch-less large-scale mask optimization with the limited intervention of legacy tools. We discover the possibility of litho-guided self-training (LGST) through a trained machine learning model when solving non-convex optimization problems, which allows iterative model and dataset update and brings significant model performance improvement. Experimental results show that, for the first time, our machine learning-based framework outperforms state-of-the-art academic numerical mask optimizers with an order of magnitude speedup.

cs.LG↗

arXiv2022

Generic Lithography Modeling with Dual-band Optics-Inspired Neural Networks

Lithography simulation is a critical step in VLSI design and optimization for manufacturability. Existing solutions for highly accurate lithography simulation with rigorous models are computationally expensive and slow, even when equipped with various approximation techniques. Recently, machine learning has provided alternative solutions for lithography simulation tasks such as coarse-grained edge placement error regression and complete contour prediction. However, the impact of these learning-based methods has been limited due to restrictive usage scenarios or low simulation accuracy. To tackle these concerns, we introduce an dual-band optics-inspired neural network design that considers the optical physics underlying lithography. To the best of our knowledge, our approach yields the first published via/metal layer contour simulation at 1nm^2/pixel resolution with any tile size. Compared to previous machine learning based solutions, we demonstrate that our framework can be trained much faster and offers a significant improvement on efficiency and image quality with 20X smaller model size. We also achieve 85X simulation speedup over traditional lithography simulator with 1% accuracy loss.

cs.OH↗

arXiv2022

Efficient quantum state preparation using Stern-Gerlach effect on cold atoms

The Zeeman hyperfine state dependent force in a Stern-Gerlach (SG) experiment has been exploited to separate and detect atoms having different Zeeman hyperfine states in a cold atom cloud. Utilizing this SG technique, we have made the quantitative estimate of atoms in different Zeeman hyperfine states in an atom cloud, which has been helpful in optimizing the optical pumping of atoms for efficient preparation of atomic state. Employing an optimized optical pumping, nearly $92 \% $ of cold $^{87}Rb$ atoms from a grey magneto-optical trap (G-MOT) on atom-chip have been optically pumped to the trappable Zeeman hyperfine state $\ket{F=2, \, m_{F} = +2}$. These optically pumped atoms have been trapped in an Ioffe-Pritchard magnetic trap near the atom-chip surface.

physics.atom-ph↗

arXiv2020

View Invariant Human Body Detection and Pose Estimation from Multiple Depth Sensors

Point cloud based methods have produced promising results in areas such as 3D object detection in autonomous driving. However, most of the recent point cloud work focuses on single depth sensor data, whereas less work has been done on indoor monitoring applications, such as operation room monitoring in hospitals or indoor surveillance. In these scenarios multiple cameras are often used to tackle occlusion problems. We propose an end-to-end multi-person 3D pose estimation network, Point R-CNN, using multiple point cloud sources. We conduct extensive experiments to simulate challenging real world cases, such as individual camera failures, various target appearances, and complex cluttered scenes with the CMU panoptic dataset and the MVOR operation room dataset. Unlike most of the previous methods that attempt to use multiple sensor information by building complex fusion models, which often lead to poor generalization, we take advantage of the efficiency of concatenating point clouds to fuse the information at the input level. In the meantime, we show our end-to-end network greatly outperforms cascaded state-of-the-art models.

cs.CV↗

arXiv2019

On continuous loading of a U-magneto-optical trap (U-MOT) on atom-chip in ultra high vacuum

Here, we report our studies on the continuous loading of a U-magneto-optical trap (U-MOT) on atom-chip from background rubidium (Rb) vapor generated using a dispenser source in ultra high vacuum (UHV) environment. Using the U-MOT loading curves, the partial pressure due to Rb vapor and pressure due to background gas have been estimated near the MOT cloud position. The estimated pressure due to Rb vapor increased from $\sim \; 1.4 \times 10^{-10}$ Torr to $ \sim \; 4.1 \times 10^{-9} $ Torr as Rb-dispenser current was increased from 2.8 to 3.4 A. The increase in dispenser current also resulted in decrease in loading as well as lifetime of the MOT cloud. This study is useful for magnetic trapping experiments where accurate information of pressure in chamber is important for the lifetime of the magnetic trap.

physics.atom-ph↗

arXiv2019

Female Librarians and Male Computer Programmers? Gender Bias in Occupational Images on Digital Media Platforms

Media platforms, technological systems, and search engines act as conduits and gatekeepers for all kinds of information. They often influence, reflect, and reinforce gender stereotypes, including those that represent occupations. This study examines the prevalence of gender stereotypes on digital media platforms and considers how human efforts to create and curate messages directly may impact these stereotypes. While gender stereotyping in social media and algorithms has received some examination in recent literature, its prevalence in different types of platforms (e.g., wiki vs. news vs. social network) and under differing conditions (e.g., degrees of human and machine led content creation and curation) has yet to be studied. This research explores the extent to which stereotypes of certain strongly gendered professions (librarian, nurse, computer programmer, civil engineer) persist and may vary across digital platforms (Twitter, the New York Times online, Wikipedia, and Shutterstock). The results suggest that gender stereotypes are most likely to be challenged when human beings act directly to create and curate content in digital platforms, and that highly algorithmic approaches for curation showed little inclination towards breaking stereotypes. Implications for the more inclusive design and use of digital media platforms, particularly with regard to mediated occupational messaging, are discussed.

cs.CY↗