Search

Your search keyword '"Agrawal, Sumit"' showing total 776 results
Start Over Author "Agrawal, Sumit"
776 results on '"Agrawal, Sumit"'

1. Extracting Entities of Interest from Comparative Product Reviews

Author

Arora, Jatin, Agrawal, Sumit, Goyal, Pawan, and Pathak, Sayan

Subjects
Computer Science - Information Retrieval, Computer Science - Computation and Language, Computer Science - Machine Learning, I.2.7, H.3.3
Abstract

This paper presents a deep learning based approach to extract product comparison information out of user reviews on various e-commerce websites. Any comparative product review has three major entities of information: the names of the products being compared, the user opinion (predicate) and the feature or aspect under comparison. All these informing entities are dependent on each other and bound by the rules of the language, in the review. We observe that their inter-dependencies can be captured well using LSTMs. We evaluate our system on existing manually labeled datasets and observe out-performance over the existing Semantic Role Labeling (SRL) framework popular for this task., Comment: Source Code: https://github.com/jatinarora2702/Review-Information-Extraction

Published
2023
Full Text
View/download PDF

3. Simultaneous Denoising and Localization Network for Photoacoustic Target Localization

Author

Yazdani, Amirsaeed, Agrawal, Sumit, Johnstonbaugh, Kerrick, Kothapalli, Sri-Rajasekhar, and Monga, Vishal

Subjects
Electrical Engineering and Systems Science - Image and Video Processing
Abstract

A significant research problem of recent interest is the localization of targets like vessels, surgical needles, and tumors in photoacoustic (PA) images. To achieve accurate localization, a high photoacoustic signal-to-noise ratio (SNR) is required. However, this is not guaranteed for deep targets, as optical scattering causes an exponential decay in optical fluence with respect to tissue depth. To address this, we develop a novel deep learning method designed to explicitly exhibit robustness to noise present in photoacoustic radio-frequency (RF) data. More precisely, we describe and evaluate a deep neural network architecture consisting of a shared encoder and two parallel decoders. One decoder extracts the target coordinates from the input RF data while the other boosts the SNR and estimates clean RF data. The joint optimization of the shared encoder and dual decoders lends significant noise robustness to the features extracted by the encoder, which in turn enables the network to contain detailed information about deep targets that may be obscured by noise. Additional custom layers and newly proposed regularizers in the training loss function (designed based on observed RF data signal and noise behavior) serve to increase the SNR in the cleaned RF output and improve model performance. To account for depth-dependent strong optical scattering, our network was trained with simulated photoacoustic datasets of targets embedded at different depths inside tissue media of different scattering levels. The network trained on this novel dataset accurately locates targets in experimental PA data that is clinically relevant with respect to the localization of vessels, needles, or brachytherapy seeds. We verify the merits of the proposed architecture by outperforming the state of the art on both simulated and experimental datasets., Comment: Accepted by IEEE Transactions on Medical Imaging

Published
2021

5. An open repository of real-time COVID-19 indicators

Author

Reinhart, Alex, Brooks, Logan, Jahja, Maria, Rumack, Aaron, Tang, Jingjing, Agrawal, Sumit, Saeed, Wael Al, Arnold, Taylor, Basu, Amartya, Bien, Jacob, Cabrera, Ángel A, Chin, Andrew, Chua, Eu Jing, Clark, Brian, Colquhoun, Sarah, DeFries, Nat, Farrow, David C, Forlizzi, Jodi, Grabman, Jed, Gratzl, Samuel, Green, Alden, Haff, George, Han, Robin, Harwood, Kate, Hu, Addison J, Hyde, Raphael, Hyun, Sangwon, Joshi, Ananya, Kim, Jimi, Kuznetsov, Andrew, La Motte-Kerr, Wichada, Lee, Yeon Jin, Lee, Kenneth, Lipton, Zachary C, Liu, Michael X, Mackey, Lester, Mazaitis, Kathryn, McDonald, Daniel J, McGuinness, Phillip, Narasimhan, Balasubramanian, O’Brien, Michael P, Oliveira, Natalia L, Patil, Pratik, Perer, Adam, Politsch, Collin A, Rajanala, Samyak, Rucker, Dawn, Scott, Chris, Shah, Nigam H, Shankar, Vishnu, Sharpnack, James, Shemetov, Dmitry, Simon, Noah, Smith, Benjamin Y, Srivastava, Vishakha, Tan, Shuyi, Tibshirani, Robert, Tuzhilina, Elena, Van Nortwick, Ana Karina, Ventura, Valérie, Wasserman, Larry, Weaver, Benjamin, Weiss, Jeremy C, Whitman, Spencer, Williams, Kristin, Rosenfeld, Roni, and Tibshirani, Ryan J

Subjects
Bioengineering, Ambulatory Care, COVID-19, Databases, Factual, Epidemiologic Methods, Health Status Indicators, Humans, Internet, Physical Distancing, Surveys and Questionnaires, Travel, United States, open data, digital surveillance, internet surveys, medical insurance claims
Abstract

The COVID-19 pandemic presented enormous data challenges in the United States. Policy makers, epidemiological modelers, and health researchers all require up-to-date data on the pandemic and relevant public behavior, ideally at fine spatial and temporal resolution. The COVIDcast API is our attempt to fill this need: Operational since April 2020, it provides open access to both traditional public health surveillance signals (cases, deaths, and hospitalizations) and many auxiliary indicators of COVID-19 activity, such as signals extracted from deidentified medical claims data, massive online surveys, cell phone mobility data, and internet search trends. These are available at a fine geographic resolution (mostly at the county level) and are updated daily. The COVIDcast API also tracks all revisions to historical data, allowing modelers to account for the frequent revisions and backfill that are common for many public health data sources. All of the data are available in a common format through the API and accompanying R and Python software packages. This paper describes the data sources and signals, and provides examples demonstrating that the auxiliary signals in the COVIDcast API present information relevant to tracking COVID activity, augmenting traditional public health reporting and empowering research and decision-making.

Published
2021

11. A pathogenic deletion in Forkhead Box L1 (FOXL1) identifies the first otosclerosis (OTSC) gene

Author

Abdelfatah, Nelly, Mostafa, Ahmed A., French, Curtis R., Doucette, Lance P., Penney, Cindy, Lucas, Matthew B., Griffin, Anne, Booth, Valerie, Rowley, Christopher, Besaw, Jessica E., Tranebjærg, Lisbeth, Rendtorff, Nanna Dahl, Hodgkinson, Kathy A., Little, Leichelle A., Agrawal, Sumit, Parnes, Lorne, Batten, Tony, Moore, Susan, Hu, Pingzhao, Pater, Justin A., Houston, Jim, Galutira, Dante, Benteau, Tammy, MacDonald, Courtney, French, Danielle, O’Rielly, Darren D., Stanton, Susan G., and Young, Terry-Lynn

Published
2022
Full Text
View/download PDF

17. Multiparametric Brain Hemodynamics Imaging Using a Combined Ultrafast Ultrasound and Photoacoustic System.

Author

Chen, Haoyang, Mirg, Shubham, Gaddale, Prameth, Agrawal, Sumit, Li, Menghan, Nguyen, Van, Xu, Tianbao, Li, Qiong, Liu, Jinyun, Tu, Wenyu, Liu, Xiao, Drew, Patrick J., Zhang, Nanyin, Gluckman, Bruce J., and Kothapalli, Sri‐Rajasekhar

Subjects
ACOUSTIC imaging, BRAIN imaging, ULTRASONIC imaging, CEREBRAL circulation, MULTISPECTRAL imaging, HIGH resolution imaging
Abstract

Studying brain‐wide hemodynamic responses to different stimuli at high spatiotemporal resolutions can help gain new insights into the mechanisms of neuro‐ diseases and ‐disorders. Nonetheless, this task is challenging, primarily due to the complexity of neurovascular coupling, which encompasses interdependent hemodynamic parameters including cerebral blood volume (CBV), cerebral blood flow (CBF), and cerebral oxygen saturation (SO2). The current brain imaging technologies exhibit inherent limitations in resolution, sensitivity, and imaging depth, restricting their capacity to comprehensively capture the intricacies of cerebral functions. To address this, a multimodal functional ultrasound and photoacoustic (fUSPA) imaging platform is reported, which integrates ultrafast ultrasound and multispectral photoacoustic imaging methods in a compact head‐mountable device, to quantitatively map individual dynamics of CBV, CBF, and SO2 as well as contrast agent enhanced brain imaging at high spatiotemporal resolutions. Following systematic characterization, the fUSPA system is applied to study brain‐wide cerebrovascular reactivity (CVR) at single‐vessel resolution via relative changes in CBV, CBF, and SO2 in response to hypercapnia stimulation. These results show that cortical veins and arteries exhibit differences in CVR in the stimulated state and consistent anti‐correlation in CBV oscillations during the resting state, demonstrating the multiparametric fUSPA system's unique capabilities in investigating complex mechanisms of brain functions. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

24. Closed-Loop Simulation for Attitude Control of Nano-satellite

Author

Riya, Chirame, Sanket, Joshi, Anant A., Verma, Ram Milan Kumar, Agrawal, Sumit, Anand, Ravit, Singh, Shrita, Bhansali, Sanskriti, Jirwankar, Piyush, Parikh, Niket, Chaari, Fakher, Series Editor, Haddar, Mohamed, Series Editor, Kwon, Young W., Series Editor, Gherardini, Francesco, Series Editor, Ivanov, Vitalii, Series Editor, Sastry, PSR Srinivasa, editor, CV, Jiji, editor, Raghavamurthy, D.V.A., editor, and Rao, Samba Siva, editor

Published
2020
Full Text
View/download PDF

29. Immuno-surveillance and protection of the human cochlea.

Author

Wei Liu, Hao Li, Kämpfe Nordström, Charlotta, Danckwardt-Lillieström, Niklas, Agrawal, Sumit, Ladak, Hanif M., and Rask-Andersen, Helge

Subjects
COCHLEA, SPIRAL ganglion, CELL anatomy, INNER ear, BASILAR membrane
Abstract

Background: Despite its location near infection-prone areas, the human inner ear demonstrates remarkable resilience. This suggests that there are inherent instruments deterring the invasion and spread of pathogens into the inner ear. Here, we combined high-resolution light microscopy, super-resolution immunohistochemistry (SR-SIM) and synchrotron phase contrast imaging (SRPCI) to identify the protection and barrier systems in the various parts of the human inner ear, focusing on the lateral wall, spiral ganglion, and endolymphatic sac. Materials and methods: Light microscopy was conducted on mid-modiolar, semi-thin sections, after direct glutaraldehyde/osmium tetroxide fixation. The tonotopic locations were estimated using SR-PCI and 3D reconstruction in cadaveric specimens. The sections were analyzed for leucocyte and macrophage activity, and the results were correlated with immunohistochemistry using confocal microscopy and SR-SIM. Results: Light microscopy revealed unprecedented preservation of cell anatomy and several macrophage-like cells that were localized in the cochlea. Immunohistochemistry demonstrated IBA1 cells frequently co-expressing MHC II in the spiral ganglion, nerve fibers, lateral wall, spiral limbus, and tympanic covering layer at all cochlear turns as well as in the endolymphatic sac. RNAscope assays revealed extensive expression of fractalkine gene transcripts in type I spiral ganglion cells. CD4 and CD8 cells occasionally surrounded blood vessels in the modiolus and lateral wall. TMEM119 and P2Y12 were not expressed, indicating that the cells labeled with IBA1 were not microglia. The round window niche, compact basilar membrane, and secondary spiral lamina may form protective shields in the cochlear base. Discussion: The results suggest that the human cochlea is surveilled by dwelling and circulating immune cells. Resident and blood-borne macrophages may initiate protective immune responses via chemokine signaling in the lateral wall, spiral lamina, and spiral ganglion at different frequency locations. Synchrotron imaging revealed intriguing protective barriers in the base of the cochlea. The role of the endolymphatic sac in human inner ear innate and adaptive immunity is discussed. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

32. Dissecting Multiparametric Cerebral Hemodynamics using Integrated Ultrafast Ultrasound and Multispectral Photoacoustic Imaging

Author

Chen, Haoyang, primary, Mirg, Shubham, additional, Gaddale, Prameth, additional, Agrawal, Sumit, additional, Li, Menghan, additional, Nguyen, Van, additional, Xu, Tianbao, additional, Li, Qiong, additional, Liu, Jinyun, additional, Tu, Wenyu, additional, Liu, Xiao, additional, Drew, Patrick J., additional, Zhang, Nanyin, additional, Gluckman, Bruce J., additional, and Kothpalli, Sri-Rajasekhar, additional

Published
2023
Full Text
View/download PDF

44. A case report and genetic characterization of a massive acinic cell carcinoma of the parotid with delayed distant metastases.

Author

Nichols, Anthony C, Chan-Seng-Yue, Michelle, Yoo, John, Agrawal, Sumit K, Starmans, Maud HW, Waggott, Daryl, Harding, Nicholas J, Dowthwaite, Samuel A, Palma, David A, Fung, Kevin, Wehrli, Bret, Macneil, S Danielle, Lambin, Philippe, Winquist, Eric, Koropatnick, James, Mymryk, Joe S, Boutros, Paul C, and Barrett, John W

Abstract

We describe the presentation, management, and clinical outcome of a massive acinic cell carcinoma of the parotid gland. The primary tumor and blood underwent exome sequencing which revealed deletions in CDKN2A as well as PPP1R13B, which induces p53. A damaging nonsynonymous mutation was noted in EP300, a histone acetylase which plays a role in cellular proliferation. This study provides the first insights into the genetic underpinnings of this cancer. Future large-scale efforts will be necessary to define the mutational landscape of salivary gland malignancies to identify therapeutic targets and biomarkers of treatment failure.

Published
2013

Catalog

Books, media, physical & digital resources
See catalog results