853 Hits in 8.9 sec

Millimeter-Level Plant Disease Detection From Aerial Photographs via Deep Learning and Crowdsourced Data

Tyr Wiesner-Hanks, Harvey Wu, Ethan Stewart, Chad DeChant, Nicholas Kaczmar, Hod Lipson, Michael A. Gore, Rebecca J. Nelson
2019 Frontiers in Plant Science  
The CNN trained on crowdsourced data showed greatly improved spatial resolution compared to one trained on expert-generated data, despite using only one fifth as many expert annotations.  ...  The final model was able to accurately delineate lesions down to the millimeter level from UAV-collected images, the finest scale of aerial plant disease detection achieved to date.  ...  Accurate identification of many plant features requires a certain level of expertise, however.  ... 
doi:10.3389/fpls.2019.01550 pmid:31921228 pmcid:PMC6927297 fatcat:dpoqdgf3freihg6jphba73iegq

Can The Crowd Identify Misinformation Objectively? The Effects of Judgment Scale and Assessor's Background [article]

Kevin Roitero, Michael Soprano, Shaoyang Fan, Damiano Spina, Stefano Mizzaro, Gianluca Demartini
2020 arXiv   pre-print
To address this issue, we present the results of an extensive study based on crowdsourcing: we collect thousands of truthfulness assessments over two datasets, and we compare expert judgments with crowd  ...  judgments, expressed on scales with various granularity levels.  ...  (i.e., with three, six, and one hundred levels).  ... 
arXiv:2005.06915v1 fatcat:u3utoxzp5ncx3f5dvrvk2zsfy4

Can the Crowd Judge Truthfulness? A Longitudinal Study on Recent Misinformation about COVID-19 [article]

Kevin Roitero and Michael Soprano and Beatrice Portelli and Massimiliano De Luise and Damiano Spina and Vincenzo Della Mea and Giuseppe Serra and Stefano Mizzaro and Gianluca Demartini
2021 arXiv   pre-print
Recently, the misinformation problem has been addressed with a crowdsourcing-based approach: to assess the truthfulness of a statement, instead of relying on a few experts, a crowd of non-expert is exploited  ...  Besides showing that the crowd is able to accurately judge the truthfulness of the statements, we report results on workers behavior, agreement among workers, effect of aggregation functions, of scales  ...  We thank the reviewers which provided insightful and detailed remarks that helped to improve the quality of the paper.  ... 
arXiv:2107.11755v1 fatcat:pxyasrohpvdevcnbfx42utklfy

Lessons Learned from Crowdsourcing Complex Engineering Tasks

Matthew Staffelbach, Peter Sempolinski, Tracy Kijewski-Correa, Douglas Thain, Daniel Wei, Ahsan Kareem, Gregory Madey, Luís A. Nunes Amaral
2015 PLoS ONE  
We explored the limits of crowdsourcing by using Mechanical Turk for a more complicated task: analysis and creation of wind simulations.  ...  Crowdsourcing Crowdsourcing is the practice of obtaining needed ideas, services, or content by requesting contributions from a large group of people.  ...  Acknowledgments Zhi Zhai assisted in the design of the web pages used in the HITs. Charles Jhin assisted with the statistical analysis. Ruizhongtai (Charles) Qi assisted with Amazon Mechanical Turk.  ... 
doi:10.1371/journal.pone.0134978 pmid:26383029 pmcid:PMC4575153 fatcat:wbgmxplv6jhhbd5dqemtdq5bsa

Predictive modeling for trustworthiness and other subjective text properties in online nutrition and health communication

Janne Kauttonen, Jenni Hannukainen, Pia Tikka, Jyrki Suomala, Amira M. Idrees
2020 PLoS ONE  
Our best regression models explained up to 70% of the total variance of consensus ratings based on the low-level properties of texts, such as semantic embeddings, presence of key-terms and part-of-speech  ...  While critical evaluation of truthfulness cannot be surrendered to the machine only, our findings provide new insights into automated evaluation of subjective text properties and analysis of morphologically-rich  ...  , or retired), (4) amount of physical exercise (how many hours per week/ day), (5) education, and (6) gender.  ... 
doi:10.1371/journal.pone.0237144 pmid:32760095 fatcat:b7ie4jqmfzhwrev6whv6awry7m

Accounting for Civilian Casualties: From the Past to the Future

Nicholas P. Jewell, Michael Spagat, Britta L. Jewell
2018 Social science history  
We provide an overview of several accounting methodologies including excess mortality, epidemiologic surveys, direct and indirect counts, multiple list estimation, and crowdsourcing.  ...  In this article, we briefly consider the motivation and use of casualty accounting and review historical approaches to these questions with illustrative comments on the US Civil War, World War I, World  ...  Up to a point, the many powerful testimonies received by truth commissions can stand on their own.  ... 
doi:10.1017/ssh.2018.9 fatcat:lfmvvyp4f5dxri5m2vi77xnoqy

Large-Scale, Multiple Level-of-Detail Change Detection from Remote Sensing Imagery Using Deep Visual Feature Clustering

Rasha S. Gargees, Grant J. Scott
2021 Remote Sensing  
The performance of our proposed method has been validated using various quantitative and statisticalmetrics in addition to presenting the visual geo-maps and the percentage of the change.  ...  The resulting chip cluster memberships allow arbitrary level-of-detail change analysis that can also support irregular geospatial extent based agglomerations.  ...  Acknowledgments: The authors thank the Digital Globe Foundation for their generous donation of imagery for this research. Conflicts of Interest: The authors declare no conflicts of interest.  ... 
doi:10.3390/rs13091661 doaj:0fc701740b6c418ebdbd42bc69cafcaf fatcat:d5hl6jbjhbew5nojmx4p34ol5i

StakeRare: Using Social Networks and Collaborative Filtering for Large-Scale Requirements Elicitation

Soo Ling Lim, A. Finkelstein
2012 IEEE Transactions on Software Engineering  
It involves identifying and prioritising requirements -a process difficult to scale to large software projects with many stakeholders.  ...  list of requirements compared to the existing method used in the project, taking only a fraction of the time.  ...  statement many requirements".  ... 
doi:10.1109/tse.2011.36 fatcat:ruuycvz3yjc55pztjgyoepoduq

Staging User Feedback toward Rapid Conflict Resolution in Data Fusion

Romila Pradhan, Siarhei Bykau, Sunil Prabhakar
2017 Proceedings of the 2017 ACM International Conference on Management of Data - SIGMOD '17  
To present the most beneficial data items for the user to validate, we take advantage of the level of consensus among sources, and the output of fusion to generate an effective ordering of items.  ...  We empirically evaluate our algorithms on three real-world datasets with different characteristics, and show that the accuracy of fusion can be significantly improved even while requesting feedback on  ...  In contrast, the true claim of an item disputed by many sources may be questioned. In such cases, it might be more beneficial to validate the latter data item.  ... 
doi:10.1145/3035918.3035941 dblp:conf/sigmod/PradhanBP17 fatcat:ca42gbjtdnaoles4avtpe5aksa

Joint Reasoning for Multi-Faceted Commonsense Knowledge [article]

Yohan Chalier, Simon Razniewski, Gerhard Weikum
2020 arXiv   pre-print
Each concept is treated in isolation from other concepts, and the only quantitative measure (or ranking) of properties is a confidence score that the statement is valid.  ...  Prior works on acquiring CSK, such as ConceptNet, have compiled statements that associate concepts, like everyday objects or activities, with properties that hold for most or some instances of the concept  ...  contain some kind of CSK by the relatedness of word-level or phrase-level vectors or more advanced representation.  ... 
arXiv:2001.04170v2 fatcat:wlih2w4wl5cr5okfimh7l5zwoe

Distinguishing mirror from glass: A 'big data' approach to material perception [article]

Hideki Tamura, Konrad E. Prokott, Roland W. Fleming
2019 arXiv   pre-print
We trained thousands of convolutional neural networks on >750,000 simulated mirror and glass objects, and compared their performance with human judgments, as well as alternative classifiers based on 'hand-engineered  ...  of human vision.  ...  The authors wish to thank Shigeki Nakauchi for enabling the exchange visits necessary for this project and Karl Gegenfurtner for comments on an earlier version of the manuscript.  ... 
arXiv:1903.01671v1 fatcat:j5evvoxadndklahwthbruexc4m


Feng Niu, Ce Zhang, Christopher Ré, Jude Shavlik
2012 International Journal on Semantic Web and Information Systems (IJSWIS)  
To validate the effectiveness of Elementary's approach to KBC, we experimentally show that its ability to incorporate diverse signals has positive impacts on KBC quality.  ...  enriches Wikipedia with structured data by reading millions of webpages on a daily basis.  ...  All URLs in this paper are active as of July 20, 2012.  ... 
doi:10.4018/jswis.2012070103 fatcat:wyh2u3thlnbodpyfg74uug5g44

Direct answers for search queries in the long tail

Michael S. Bernstein, Jaime Teevan, Susan Dumais, Daniel Liebling, Eric Horvitz
2012 Proceedings of the 2012 ACM annual conference on Human Factors in Computing Systems - CHI '12  
We introduce a combination of search log mining and paid crowdsourcing techniques to create Tail Answers.  ...  Web search engines now offer more than ranked results.  ...  Of the 350 needs, one hundred forty six (42%) were short phrase answers, one hundred twenty seven (36%) were short list answers, and seventy seven (22%) were summary answers.  ... 
doi:10.1145/2207676.2207710 dblp:conf/chi/BernsteinTDLH12 fatcat:obeouidnxnhwvpy4pbwgdpm6ka

Crowd intelligence in AI 2.0 era

Wei Li, Wen-jun Wu, Huai-min Wang, Xue-qi Cheng, Hua-jun Chen, Zhi-hua Zhou, Rong Ding
2017 Frontiers of Information Technology & Electronic Engineering  
As one of the most prominent characteristics of research in AI 2.0 era, crowd intelligence has attracted much attention from both industry and research communities.  ...  First, we describe the concept of crowd intelligence, and explain its relationship to the existing related concepts, e.g., crowdsourcing and human computation.  ...  How to assess, control, and guarantee the quality of the work, and how to use the work even of low quality are important issues.  ... 
doi:10.1631/fitee.1601859 fatcat:x6aijr7ud5eojjuelaq3sv4v7a

KGEval: Estimating Accuracy of Automatically Constructed Knowledge Graphs [article]

Prakhar Ojha, Partha Talukdar
2016 arXiv   pre-print
KGEval binds facts of a KG using coupling constraints and crowdsources the facts that infer correctness of large parts of the KG.  ...  Through extensive experiments on real-world datasets, we demonstrate that KGEval is able to estimate KG accuracy more accurately compared to other competitive baselines, while requiring significantly lesser  ...  PSL is a declarative language to reason uncertainty in relational domains via first order logic statements.  ... 
arXiv:1610.06912v2 fatcat:xjyxgno5sjalfeadxjcmumxwfu
« Previous Showing results 1 — 15 out of 853 results