Somya D. Mohanty
YOU?
Author Swipe
View article: Optimizing large language models for ontology-based annotation: a study on gene ontology in biomedical texts
Optimizing large language models for ontology-based annotation: a study on gene ontology in biomedical texts Open
Automated ontology annotation of scientific literature plays a critical role in knowledge management, particularly in fields like biology and biomedicine, where accurate concept tagging can enhance information retrieval, semantic search, a…
View article: Optimizing Large Language Models forOntology-Based Annotation: A Study on Gene Ontology in Biomedical Texts
Optimizing Large Language Models forOntology-Based Annotation: A Study on Gene Ontology in Biomedical Texts Open
Automated ontology annotation of scientific literature plays a critical role in knowledge management, particularly in fields like biology and biomedicine, where accurate concept tagging can enhance information retrieval, semantic search, a…
View article: LLMs in Action: Robust Metrics for Evaluating Automated Ontology Annotation Systems
LLMs in Action: Robust Metrics for Evaluating Automated Ontology Annotation Systems Open
Ontologies are critical for organizing and interpreting complex domain-specific knowledge, with applications in data integration, functional prediction, and knowledge discovery. As the manual curation of ontology annotations becomes increa…
View article: Human motion activity recognition and pattern analysis using compressed deep neural networks
Human motion activity recognition and pattern analysis using compressed deep neural networks Open
This work presents an on-device machine learning model with the ability to identify different mobility gestures called human activity recognition (HAR), which includes running, walking, squatting, jumping, and others. The data is collected…
View article: A deep semantic matching approach for identifying relevant messages for social media analysis
A deep semantic matching approach for identifying relevant messages for social media analysis Open
There is a growing interest in using social media content for Natural Language Processing applications. However, it is not easy to computationally identify the most relevant set of tweets related to any specific event. Challenging semantic…
View article: Deep Semantic Matching Approach To-wards Dynamic Text Filtering in Micro-Blog Messages.
Deep Semantic Matching Approach To-wards Dynamic Text Filtering in Micro-Blog Messages. Open
There is a growing interest in using social media content for Natural Language Processing applications. This paper seeks to demonstrate a way to present the changing semantics of Twitter within the context of a crisis event, specifically t…
View article: Labels for Emergency Response Imagery from Hurricane Barry, Delta, Dorian, Florence, Ida, Isaias, Laura, Michael, Sally, Zeta, and Tropical Storm Gordon
Labels for Emergency Response Imagery from Hurricane Barry, Delta, Dorian, Florence, Ida, Isaias, Laura, Michael, Sally, Zeta, and Tropical Storm Gordon Open
The csv files contain human-generated labels for Emergency Response Imagery collected by US National Oceanic and Atmospheric Administration (NOAA) after Hurricane Barry, Delta, Dorian, Florence, Ida, Isaias, Laura, Michael, Sally, Zeta, an…
View article: Labels for Emergency Response Imagery from Hurricane Barry, Delta, Dorian, Florence, Ida, Isaias, Laura, Michael, Sally, Zeta, and Tropical Storm Gordon
Labels for Emergency Response Imagery from Hurricane Barry, Delta, Dorian, Florence, Ida, Isaias, Laura, Michael, Sally, Zeta, and Tropical Storm Gordon Open
The csv files contain human-generated labels for Emergency Response Imagery collected by US National Oceanic and Atmospheric Administration (NOAA) after Hurricane Barry, Delta, Dorian, Florence, Ida, Isaias, Laura, Michael, Sally, Zeta, an…
View article: Deep learning architectures for recognizing ontology concepts from scientific literature
Deep learning architectures for recognizing ontology concepts from scientific literature Open
Background Annotating scientific literature with ontology concepts is a critical task in biology and several other domains for knowledge discovery. Ontology based annotations can power large-scale comparative analyses in a wide range of ap…
View article: Labeling Poststorm Coastal Imagery for Machine Learning: Measurement of Interrater Agreement
Labeling Poststorm Coastal Imagery for Machine Learning: Measurement of Interrater Agreement Open
Classifying images using supervised machine learning (ML) relies on labeled training data—classes or text descriptions, for example, associated with each image. Data‐driven models are only as good as the data used for training, and this po…
View article: Labels for Emergency Response Imagery from Hurricane Florence, Hurricane Michael, and Hurricane Isaias
Labels for Emergency Response Imagery from Hurricane Florence, Hurricane Michael, and Hurricane Isaias Open
The csv files contain human-generated labels for Emergency Response Imagery collected by US National Oceanic and Atmospheric Administration (NOAA) after Hurricane Florence (2018), Hurricane Michael (2018) and Hurricane Isaias (2020). All a…
View article: A multi-modal approach towards mining social media data during natural\n disasters -- a case study of Hurricane Irma
A multi-modal approach towards mining social media data during natural\n disasters -- a case study of Hurricane Irma Open
Streaming social media provides a real-time glimpse of extreme weather\nimpacts. However, the volume of streaming data makes mining information a\nchallenge for emergency managers, policy makers, and disciplinary scientists.\nHere we explo…
View article: An Active Learning Pipeline to Detect Hurricane Washover in Post-Storm Aerial Images
An Active Learning Pipeline to Detect Hurricane Washover in Post-Storm Aerial Images Open
We present an active learning pipeline to identify hurricane impacts on coastal landscapes. Previously unlabeled post-storm images are used in a three component workflow — first an online interface is used to crowd-source labels for imager…
View article: A multi-modal machine learning approach towards predicting patient readmission
A multi-modal machine learning approach towards predicting patient readmission Open
Healthcare costs that can be attributed to unplanned readmissions are staggeringly high and negatively impact health and wellness of patients. In the United States, hospital systems and care providers have strong financial motivations to r…
View article: Automated ontology-based annotation of scientific literature using deep learning
Automated ontology-based annotation of scientific literature using deep learning Open
Representing scientific knowledge using ontologies enables data integration, consistent machine-readable data representation, and allows for large-scale computational analyses. Text mining approaches that can automatically process and anno…
View article: psi-collect: A Python module for post-storm image collection and cataloging
psi-collect: A Python module for post-storm image collection and cataloging Open
This imagery aids in recovery efforts as well as rapid assessment of storm impacts along developed and undeveloped coastlines (Madore, Imahori, Kum, White, & Worthem, 2018).
View article: Geolocated Tweets from Florida, USA during Hurricane Irma (2017) with Relevance Scores
Geolocated Tweets from Florida, USA during Hurricane Irma (2017) with Relevance Scores Open
The dataset is a csv file of all tweets from the US state of Florida that contain images from Sept. 10-12, 2017. Tweets were collected using a geolocated bounding box around the state of Florida. In compliance with Twitter's data sharing p…
View article: Labels for Hurricane Florence (2018) Emergency Response Imagery from NOAA
Labels for Hurricane Florence (2018) Emergency Response Imagery from NOAA Open
This csv file contains labels for >300 images obtained by the US National Oceanic and Atmospheric Administration (NOAA) in response to Hurricane Florence. Images were taken on Sept. 17th 2018, and are downloadable from the NOAA Emergency R…
View article: A data-driven approach to predicting diabetes and cardiovascular disease with machine learning
A data-driven approach to predicting diabetes and cardiovascular disease with machine learning Open
Background Diabetes and cardiovascular disease are two of the main causes of death in the United States. Identifying and predicting these diseases in patients is the first step towards stopping their progression. We evaluate the capabiliti…
View article: COMPARISON OF A FRAILTY RISK SCORE AND COMORBIDITY FOR EARLY REHOSPITALIZATION USING ELECTRONIC HEALTH RECORD DATA
COMPARISON OF A FRAILTY RISK SCORE AND COMORBIDITY FOR EARLY REHOSPITALIZATION USING ELECTRONIC HEALTH RECORD DATA Open
Frailty is a clinical syndrome of impaired homeostasis and decreased physiologic reserve and resilience resulting in diminished ability to recover from stressors. In the hospital setting, barriers to adoption of popular frailty assessments…
View article: Enhancing Trip Distribution Using Twitter Data: Comparison of Gravity and Neural Networks
Enhancing Trip Distribution Using Twitter Data: Comparison of Gravity and Neural Networks Open
Predicting human mobility within cities is an important task in urban and transportation planning. With the vast amount of digital traces available through social media platforms, we investigate the potential application of such data in pr…
View article: A Scalable, Trustworthy Infrastructure for Collaborative Container Repositories
A Scalable, Trustworthy Infrastructure for Collaborative Container Repositories Open
We present a scalable "Trustworthy Container Repository" (TCR) infrastructure for the storage of software container images, such as those used by Docker. Using an authenticated data structure based on index-ordered Merkle trees (IOMTs), TC…
View article: Taking a Dive: Experiments in Deep Learning for Automatic Ontology-based Annotation of Scientific Literature
Taking a Dive: Experiments in Deep Learning for Automatic Ontology-based Annotation of Scientific Literature Open
I. Abstract Text mining approaches for automated ontology-based curation of biological and biomedical literature have largely focused on syntactic and lexical analysis along with machine learning. Recent advances in deep learning have show…