189 Hits in 2.0 sec

Common-Knowledge Concept Recognition for SEVA [article]

Jitin Krishnan, Patrick Coronado, Hemant Purohit, Huzefa Rangwala
2020 arXiv   pre-print
We build a common-knowledge concept recognition system for a Systems Engineer's Virtual Assistant (SEVA) which can be used for downstream tasks such as relation extraction, knowledge graph construction, and question-answering. The problem is formulated as a token classification task similar to named entity extraction. With the help of a domain expert and text processing methods, we construct a dataset annotated at the word-level by carefully defining a labelling scheme to train a sequence model
more » ... to recognize systems engineering concepts. We use a pre-trained language model and fine-tune it with the labeled dataset of concepts. In addition, we also create some essential datasets for information such as abbreviations and definitions from the systems engineering domain. Finally, we construct a simple knowledge graph using these extracted concepts along with some hyponym relations.
arXiv:2003.11687v1 fatcat:fttahxsaxnfare5h7k377segbu

Genomic tools in bioremediation

Atya Kapley, Hemant J. Purohit
2009 Indian Journal of Microbiology  
Bioremediation is a process that uses microorganisms or their enzymes to remove pollutants from the environment. Generally, bioremediation technologies can be classifi ed as in situ or ex situ. In situ bioremediation involves treating the contaminated material at the site while ex situ involves the removal of the contaminated material to be treated elsewhere. Like so much else in biology, the ease and availability of genomic data has created a new level of understanding this system.
more » ... on capabilities of the microbial population can be analyzed; not only by physiological parameters, but also by the use of genomic tools, and effi cient remediation strategies can be planned. PCR and DNA-or oligonucleotide-based microarray technology is a powerful functional genomics tool that allows researchers to view the physiology of a living cell from a comprehensive and dynamic molecular perspective. This paper explores the use of such tools in bioremediation process.
doi:10.1007/s12088-009-0012-2 pmid:23100758 pmcid:PMC3450142 fatcat:waze7ndmb5cyjhhrfhmr3mqmp4

Bioremediation and Circular Biotechnology

Sunita Varjani, Abhay Bajaj, Hemant J. Purohit, V. C. Kalia
2021 Indian Journal of Microbiology  
Sunita Varjani (Guest Editor), Abhay Bajaj (Guest Editor), Hemant J. Purohit (Editor), Vipin Chandra Kalia (Editor in Chief) Indian J Microbiol (July-Sept 2021) 61(3):235-236  ... 
doi:10.1007/s12088-021-00953-3 fatcat:up6nfh6j4fhwhj3jjw57sehpea

UTPO: User's Trust Profile Ontology - Modeling trust towards Online Health Information Sources [article]

Prakruthi Karuna, Hemant Purohit, Vivian Motti
2019 arXiv   pre-print
Despite the overwhelming quantity of health information that is available online today, finding reliable and trustworthy information is still challenging, even when advanced recommender systems are used. To tackle this challenge and improve our recommended sources, we need to first understand and capture the user behavior of what is considered to be trustworthy. This paper presents a taxonomy of relevant factors that influence user' trust towards online health information sources. We design a
more » ... rvey experiment to validate the taxonomical factors, and propose an ontology using the taxonomy of factors, such that each user's trust could be modeled as an instance of our ontology and this could later be used programmatically to recommend trustworthy information sources. Our work will inform the design of personalized recommendation systems and websites to improve online delivery of health information.
arXiv:1901.01276v1 fatcat:uyhfmj6gabbwdcvownxnhhogea


Soudip Roy Chowdhury, Hemant Purohit, Muhammad Imran
2015 Proceedings of the 24th International Conference on World Wide Web - WWW '15 Companion  
Existing literature demonstrates the usefulness of systemmediated algorithms, such as supervised machine learning for detecting classes of messages in the social-data stream (e.g., topically relevant vs. irrelevant). The classification accuracies of these algorithms largely depend upon the size of labeled samples that are provided during the learning phase. Other factors such as class distribution, term distribution among the training set also play an important role on classifier's accuracy.
more » ... ever, due to several reasons (money / time constraints, limited number of skilled labelers etc.), a large sample of labeled messages is often not available immediately for learning an efficient classification model. Consequently, classifier trained on a poor model often misclassifies data and hence, the applicability of such learning techniques (especially for the online setting) during ongoing crisis response remains limited. In this paper, we propose a post-classification processing step leveraging upon two additional content features-stable hashtag association and stable named entity association, to improve the classification accuracy for a classifier in realistic settings. We have tested our algorithms on two crisis datasets from Twitter (Hurricane Sandy 2012 and Queensland Floods 2013), and compared our results against the results produced by a "best-in-class" baseline online classifier. By showing the consistent better quality results than the baseline algorithm i.e., by correctly classifying the misclassified data points from the prior step (false negative and false positive to true positive and true negative classes, respectively), we demonstrate the applicability of our approach in practice.
doi:10.1145/2740908.2741731 dblp:conf/www/ChowdhuryPI15 fatcat:q2g6xb2trzcvrl32bhyzw6n7gy

Emergency Incident Detection from Crowdsourced Waze Data using Bayesian Information Fusion [article]

Yasas Senarath, Saideep Nannapaneni, Hemant Purohit, Abhishek Dubey
2020 arXiv   pre-print
The number of emergencies have increased over the years with the growth in urbanization. This pattern has overwhelmed the emergency services with limited resources and demands the optimization of response processes. It is partly due to traditional 'reactive' approach of emergency services to collect data about incidents, where a source initiates a call to the emergency number (e.g., 911 in U.S.), delaying and limiting the potentially optimal response. Crowdsourcing platforms such as Waze
more » ... s an opportunity to develop a rapid, 'proactive' approach to collect data about incidents through crowd-generated observational reports. However, the reliability of reporting sources and spatio-temporal uncertainty of the reported incidents challenge the design of such a proactive approach. Thus, this paper presents a novel method for emergency incident detection using noisy crowdsourced Waze data. We propose a principled computational framework based on Bayesian theory to model the uncertainty in the reliability of crowd-generated reports and their integration across space and time to detect incidents. Extensive experiments using data collected from Waze and the official reported incidents in Nashville, Tenessee in the U.S. show our method can outperform strong baselines for both F1-score and AUC. The application of this work provides an extensible framework to incorporate different noisy data sources for proactive incident detection to improve and optimize emergency response operations in our communities.
arXiv:2011.05440v1 fatcat:ksntuaufr5gsxcrhb42ijy5fra

User Taglines: Alternative Presentations of Expertise and Interest in Social Media [article]

Hemant Purohit, Alex Dow, Omar Alonso, Lei Duan, Kevin Haas
2012 arXiv   pre-print
Web applications are increasingly showing recommended users from social media along with some descriptions, an attempt to show relevancy - why they are being shown. For example, Twitter search for a topical keyword shows expert twitterers on the side for 'whom to follow'. Google+ and Facebook also recommend users to follow or add to friend circle. Popular Internet newspaper- The Huffington Post shows Twitter influencers/ experts on the side of an article for authoritative relevant tweets. The
more » ... ate of the art shows user profile bios as summary for Twitter experts, but it has issues with length constraint imposed by user interface (UI) design, missing bio and sometimes funny profile bio. Alternatively, applications can use human generated user summary, but it will not scale. Therefore, we study the problem of automatic generation of informative expertise summary or taglines for Twitter experts in space constraint imposed by UI design. We propose three methods for expertise summary generation- Occupation-Pattern based, Link-Triangulation based and User-Classification based, with use of knowledge-enhanced computing approaches. We also propose methods for final summary selection for users with multiple candidates of generated summaries. We evaluate the proposed approaches by user-study using a number of experiments. Our results show promising quality of 92.8% good summaries with majority agreement in the best case and 70% with majority agreement in the worst case. Our approaches also outperform the state of the art up to 88%. This study has implications in the area of expert profiling, user presentation and application design for engaging user experience.
arXiv:1212.1927v1 fatcat:mbo2i57adnhvtkmu44etlw5swi

Distributional Semantics Approach to Detect Intent in Twitter Conversations on Sexual Assaults [article]

Rahul Pandey, Hemant Purohit, Bonnie Stabile, Aubrey Grant
2018 arXiv   pre-print
The recent surge in women reporting sexual assault and harassment (e.g., #metoo campaign) has highlighted a longstanding societal crisis. This injustice is partly due to a culture of discrediting women who report such crimes and also, rape myths (e.g., 'women lie about rape'). Social web can facilitate the further proliferation of deceptive beliefs and culture of rape myths through intentional messaging by malicious actors. This multidisciplinary study investigates Twitter posts related to
more » ... l assaults and rape myths for characterizing the types of malicious intent, which leads to the beliefs on discrediting women and rape myths. Specifically, we first propose a novel malicious intent typology for social media using the guidance of social construction theory from policy literature that includes Accusational, Validational, or Sensational intent categories. We then present and evaluate a malicious intent classification model for a Twitter post using semantic features of the intent senses learned with the help of convolutional neural networks. Lastly, we analyze a Twitter dataset of four months using the intent classification model to study narrative contexts in which malicious intents are expressed and discuss their implications for gender violence policy design.
arXiv:1810.01012v1 fatcat:qpybej2675dendbuai2re2jl3u

Ranking of Social Media Alerts with Workload Bounds in Emergency Operation Centers [article]

Hemant Purohit, Carlos Castillo, Muhammad Imran, Rahul Pandey
2018 arXiv   pre-print
Also, Purohit thanks US National Science Foundation grants IIS-1657379 & IIS-1815459 and Castillo thanks La Caixa project LCF/PR/PR16/11110009 for partial support.  ... 
arXiv:1809.08489v1 fatcat:e3nncq7sbnh77nr726igggkm6q

CinC-GAN for Effective F0 prediction for Whisper-to-Normal Speech Conversion [article]

Maitreya Patel, Mirali Purohit, Jui Shah, Hemant A. Patil
2020 arXiv   pre-print
Recently, Generative Adversarial Networks (GAN)-based methods have shown remarkable performance for the Voice Conversion and WHiSPer-to-normal SPeeCH (WHSP2SPCH) conversion. One of the key challenges in WHSP2SPCH conversion is the prediction of fundamental frequency (F0). Recently, authors have proposed state-of-the-art method Cycle-Consistent Generative Adversarial Networks (CycleGAN) for WHSP2SPCH conversion. The CycleGAN-based method uses two different models, one for Mel Cepstral
more » ... s (MCC) mapping, and another for F0 prediction, where F0 is highly dependent on the pre-trained model of MCC mapping. This leads to additional non-linear noise in predicted F0. To suppress this noise, we propose Cycle-in-Cycle GAN (i.e., CinC-GAN). It is specially designed to increase the effectiveness in F0 prediction without losing the accuracy of MCC mapping. We evaluated the proposed method on a non-parallel setting and analyzed on speaker-specific, and gender-specific tasks. The objective and subjective tests show that CinC-GAN significantly outperforms the CycleGAN. In addition, we analyze the CycleGAN and CinC-GAN for unseen speakers and the results show the clear superiority of CinC-GAN.
arXiv:2008.07788v1 fatcat:2xh27jaoezfypnpjwbwn7noocm

AI for Trustworthiness! Credible User Identification on Social Web for Disaster Response Agencies [article]

Rahul Pandey, Hemant Purohit, Jennifer Chan, Aditya Johri
2018 arXiv   pre-print
GBV is a worldwide societal crisis with diverse acts of violence (Russo et al. 2006; Purohit et al. 2016) , including domestic assault and human trafficking.  ...  leveraged these affordances of social media across a range of socially relevant events from #BlackLivesMatter movements to marketing and awareness campaigns to natural disasters such as #HurricaneSandy (Purohit  ... 
arXiv:1810.01013v1 fatcat:b6cl5fx62rf73o3y43viyj4k7e

Diverse Metabolic Capacities of Fungi for Bioremediation

Radhika Deshmukh, Anshuman A. Khardenavis, Hemant J. Purohit
2016 Indian Journal of Microbiology  
Bioremediation refers to cost-effective and environment-friendly method for converting the toxic, recalcitrant pollutants into environmentally benign products through the action of various biological treatments. Fungi play a major role in bioremediation owing to their robust morphology and diverse metabolic capacity. The review focuses on different fungal groups from a variety of habitats with their role in bioremediation of different toxic and recalcitrant compounds; persistent organic
more » ... ts, textile dyes, effluents from textile, bleached kraft pulp, leather tanning industries, petroleum, polyaromatic hydrocarbons, pharmaceuticals and personal care products, and pesticides. Bioremediation of toxic organics by fungi is the most sustainable and green route for cleanup of contaminated sites and we discuss the multiple modes employed by fungi for detoxification of different toxic and recalcitrant compounds including prominent fungal enzymes viz., catalases, laccases, peroxidases and cyrochrome P450 monooxygeneses. We have also discussed the recent advances in enzyme engineering and genomics and research being carried out to trace the less understood bioremediation pathways.
doi:10.1007/s12088-016-0584-6 pmid:27407289 pmcid:PMC4920763 fatcat:3acow6f6xbd3zk52nmpdojap5q

Microbe-assisted biodegradation, bioremediation and metabolic engineering

Hemant J. Purohit, S Dayananda, Prashant Phale
2019 Proceedings of the Indian National Science Academy  
Hemant J Purohit et al.  ...  Purohit et al., 2003b , Moharikar et al., 2005 .  ... 
doi:10.16943/ptinsa/2019/49720 fatcat:rpeplryhdbamreh3lralqvx7qu

Dynamic gene network selection through stress modulation: An E. coli model

Hemant J. Purohit
2013 Journal of Microbial & Biochemical Technology  
T he resistance of human malaria parasites to antimalarial compounds has become of considerable concern, particularly in view of the shortage of novel classes of antimalarial drugs. One way to prevent resistance is by using new compounds that are not based on existing synthetic antimicrobial agents. Sensitivity of one hundred (100) P. falciparum isolates to chloroquine, quinine, amodiaquine, mefloquine, sulphadoxine/pyrimethamine, artemisinin, Momordicacharantia (Ejirin) Diospyrosmonbuttensis
more » ... eguneja) and Morindalucida (Oruwo) was determined using the in-vitro microtest (Mark III) technique to determine the IC 50 of the drugs. All the isolates tested were sensitive to quinine, mefloquine and artesunate. Only 51% of the isolates were resistant to chloroquine, 13% to amodiaquine and 5% to sulphadoxinepyrimethamine respectively. Highest resistance to chloroquine (68.9%) was recorded among isolates from Yewa zone while highest resistance to amodiaquine (30%) was observed in Ijebu zone. Highest resistance to sulphadoxine and pyrimethamine was recorded in Yewa and Egba zones respectively. A significant positive correlation was observed between the responses to artemisinin and mefloquine (P=0.001), artemisinin and quinine (P=0.05), quinine and mefloquine (P=0.01). A significant negative correlation was observed between the responses to chloroquine and mefloquine (P=0.05). Highest antiplasmodial activity was obtained with the ethanolic extract of Diospyrosmon buttensis (IC 50 =32 µg/ml) while the lowest was obtained from Morinda lucida (IC50=250 µg/ml). Natural products isolated from plants used in traditional medicine, which have potent antiplasmodial action in vitro, represents potential sources of new antimalarial drugs.
doi:10.4172/1948-5948.s1.009 fatcat:7ndgroj56bdmbajlzrlyxunxka

Assisting coordination during crisis

Shreyansh P. Bhatt, Hemant Purohit, Andrew Hampton, Valerie Shalin, Amit Sheth, John Flach
2014 Proceedings of the 2014 ACM conference on Web science - WebSci '14  
Ubiquitous social media during crises provides citizen reports on the situation, needs and supplies. Previous research extracts resource needs directly from the text (e.g. "Power cut to Coney Island and Brighton beach" indicates a power need). This approach assumes that citizens derive and write about specific needs from their observations, properly specified for the emergency response system, an assumption that is not consistent with general conversational behavior. In our study, Twitter 1
more » ... ages (tweets) from Hurricane Sandy in 2012 clearly indicate power blackouts, but not their probable implications (e.g. loss of power to hospital life support systems). We use a domain model to capture such interdependencies between resources and needs. Using semantic web technology, we represent these dependencies in an ontology that specifies the functional association between resources. Accurate interpretation of resource need/supply also depends on the location of a message. We show how inference based on a domain model combined with location detection and interpretation in the social data can enhance situational awareness, e.g., predicting a medical emergency before it is reported as critical.
doi:10.1145/2615569.2615652 dblp:conf/websci/BhattPHSSF14 fatcat:3xy22s3zgfadxpljspuwvwnepe
« Previous Showing results 1 — 15 out of 189 results