5,099 Hits in 7.7 sec

Filtering large-scale event collections using a combination of supervised and unsupervised learning for event trigger classification

Farrokh Mehryary, Suwisa Kaewphan, Kai Hakala, Filip Ginter
2016 Journal of Biomedical Semantics  
For rarely occurring trigger words we introduce a supervised approach trained on the combination of trigger word classification produced by the unsupervised clustering method and manual annotation.  ...  In this paper we propose a novel approach for filtering falsely identified triggers from large-scale event databases, thus improving the quality of knowledge extraction.  ...  Acknowledgments We would like to thank Sofie Van Landeghem, Ghent University, for initiating the ideas for this project and her valuable suggestions.  ... 
doi:10.1186/s13326-016-0070-4 pmid:27175227 pmcid:PMC4864999 fatcat:fvhbzfqfofg5tf2mt5leicuoue

Artificial Neural Networks as Emerging Tools for Earthquake Detection

Otilio Rojas, Beatriz Otero, Leonardo Alvarado, Sergi Mus, Rubén Tous Tous
2019 Journal of Computacion y Sistemas  
P and S seismic waves, earthquake hypocenters, supervised, unsupervised and semisupervised, deep and convolutional neural networks, training and testing data sets.  ...  These have fueled the research for the automation of interpretation tasks such as event detection, event identification, hypocenter location, and source mechanism analysis.  ...  Acknowledgements This work is partially supported by the Spanish Ministry of Economy and Competitivity under contract TIN2015-65316-P, by the SGR programmes We thank FUNVISIS for providing the seismic  ... 
doi:10.13053/cys-23-2-3197 fatcat:2jnub4tmanadldwcisaxkgzb5y

Revealing Fundamental Physics from the Daya Bay Neutrino Experiment Using Deep Neural Networks

Evan Racah, Seyoon Ko, Peter Sadowski, Wahid Bhimji, Craig Tull, Sang-Yun Oh, Pierre Baldi, Prabhat
2016 2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA)  
We further show how convolutional deep neural networks can provide an effective classification filter with greater than 97% accuracy across different classes of physics events, significantly better than  ...  In this work, we show that meaningful physical content can be revealed by transforming the raw data into a learned high-level representation using deep neural networks, with measurements taken at the Daya  ...  ACKNOWLEDGMENTS The authors gratefully acknowledge the Daya Bay Collaboration for access to their experimental data and many useful discussions, and specifically Yasuhiro Nakajima for the dataset labels  ... 
doi:10.1109/icmla.2016.0160 dblp:conf/icmla/RacahKSBTOBP16 fatcat:htmjg5pgmfayxdskmmawdd5toq

Semi-supervised Eigenbasis novelty detection

David R. Thompson, Walid A. Majid, Colorado J. Reed, Kiri L. Wagstaff
2012 Statistical analysis and data mining  
We present a semi-supervised online method for novelty detection and evaluate its performance for radio astronomy time series data.  ...  Our approach uses sparse, adaptive eigenbases to combine (1) prior knowledge about uninteresting signals with (2) online estimation of the current data properties to enable highly sensitive and precise  ...  More generally we would also thank Swinburne University and CSIRO for a generous data access policy.  ... 
doi:10.1002/sam.11148 fatcat:uch3gbche5fvxdzjtmuyztxc2a

Learning for Biomedical Information Extraction: Methodological Review of Recent Advances [article]

Feifan Liu, Jinying Chen, Abhyuday Jagannatha, Hong Yu
2016 arXiv   pre-print
In addition, we dive into open information extraction and deep learning, two emerging and influential techniques and envision next generation of BioIE.  ...  Unlike existing reviews covering a holistic view on BioIE, this review focuses on mainly recent advances in learning based approaches, by systematically summarizing them into different aspects of methodological  ...  training using existing benchmark data; (2) learning from unlabeled data (i.e. semi-supervised and unsupervised learning) which involves incorporating large amount of unlabeled data into the learning  ... 
arXiv:1606.07993v1 fatcat:7d5om7zxxzhoviiriasrfwg3xi

Applications of Machine Learning in Ambulatory ECG

Joel Xue, Long Yu
2021 Hearts  
At the core of these devices and applications are the algorithms responsible for signal conditioning, ECG beat detection and classification, and event detections.  ...  The center tasks of AECG signal processing listed in the review include signal preprocessing, beat detection and classification, event detection, and event prediction.  ...  Acknowledgments: The authors would like to acknowledge discussions of AECG and machine learning with Gari Clifford and Bioinformatics group of Emory University and machine learning group of Alivecor Inc  ... 
doi:10.3390/hearts2040037 fatcat:c2up34ys7bejbofaj3doxokepu

In Situ Analysis for Intelligent Control

Maria Fox, Derek Long, Frederic Py, Kanna Rajan, John Ryan
2007 OCEANS 2007 - Europe  
Specifically we analyse a set of techniques for automated sample acquisition in the water-column using an electro-mechanical "Gulper", designed at MBARI.  ...  The objective of the study is to investigate techniques which use machine intelligence to enable event-response scenarios.  ...  The coastal environment and its resources are influenced by fluctuations extending over a vast range of time and space scales, from global-scale multidecadal variability [2] to smallscale episodic events  ... 
doi:10.1109/oceanse.2007.4302447 fatcat:env5d64o5rbqvbeoc45otdmwam

Unsupervised inference of implicit biomedical events using context triggers

Jin-Woo Chung, Wonsuk Yang, Jong C. Park
2020 BMC Bioinformatics  
systems have treated them as false negatives because labeled data is not sufficiently large enough to model a complex reasoning process using supervised learning frameworks.  ...  The experimental results demonstrate that our unsupervised system extracts cross-sentence events quite well and outperforms all the state-of-the-art supervised systems when combined with existing methods  ...  J-WC wrote the first draft of the manuscript with support from JP. JP supervised all steps of the research.  ... 
doi:10.1186/s12859-020-3341-0 pmid:31992184 pmcid:PMC6988352 fatcat:edrrrkh7xzdafexzynpyuo7hq4

An overview of event extraction and its applications [article]

Jiangwei Liu, Liangyu Min, Xiaohong Huang
2021 arXiv   pre-print
This study provides a comprehensive overview of the state-of-the-art event extraction methods and their applications from text, including closed-domain and open-domain event extraction.  ...  We hope this work could help researchers and practitioners obtain a quick overview of recent event extraction.  ...  [50] employ joint learning for Chinese event extraction and solve the high ratio of pseudo trigger mentions to true ones by using trigger filtering schemas.  ... 
arXiv:2111.03212v1 fatcat:o3oagnjrybh3vapvvp7twgjtuu

User re-authentication via mouse movements

Maja Pusara, Carla E. Brodley
2004 Proceedings of the 2004 ACM workshop on Visualization and data mining for computer security - VizSEC/DMSEC '04  
We apply a supervised learning method to discriminate among k users.  ...  Our empirical results for eleven users show that we can differentiate these individuals based on their mouse movement behavior with a false positive rate of 0.43% and a false negative rate of 1.75%.  ...  Related to this, model scalability to a large number of users and applications may become an issue. In addition, we are currently in the process of collecting a much larger scale dataset.  ... 
doi:10.1145/1029208.1029210 dblp:conf/vizsec/PusaraB04 fatcat:mnm7zxfpbnfojnzhafqtgudure

Processing Social Media Messages in Mass Emergency

Muhammad Imran, Carlos Castillo, Fernando Diaz, Sarah Vieweg
2018 Companion of the The Web Conference 2018 on The Web Conference 2018 - WWW '18  
Millions of people use social media to share information during disasters and mass emergencies.  ...  Information available on social media, particularly in the early hours of an event when few other sources are available, can be extremely valuable for emergency responders and decision makers, helping  ...  The latter includes large-scale events such as disasters, emergencies, and mass convergence events.  ... 
doi:10.1145/3184558.3186242 dblp:conf/www/000200V18 fatcat:qccrrnreaffhlptqc6vtkdhmki

Detecting Transitions in Manual Tasks from Wearables: An Unsupervised Labeling Approach

Sebastian Böttcher, Philipp Scholl, Kristof Van Laerhoven
2018 Informatics  
† This article is an expanded version of the original conference paper [1] and includes a new, in-depth review of related work, as well as additional classification results for some supervised methods  ...  on the same datasets and a performance comparison of all methods.  ...  Support for the data collection and analysis for this paper was funded in part by the collaborative EU research Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/informatics5020016 fatcat:x2sun6l5hfggbh5wlxhazf5lgu

A Compact Survey on Event Extraction: Approaches and Applications [article]

Qian Li, Jianxin Li, Jiawei Sheng, Shiyao Cui, Jia Wu, Yiming Hei, Hao Peng, Shu Guo, Lihong Wang, Amin Beheshti, Philip S. Yu
2021 arXiv   pre-print
With the rapid development of deep learning technology, event extraction technology based on deep learning has become a research hotspot.  ...  Event extraction is a critical technique to apprehend the essential content of events promptly.  ...  ACKNOWLEDGMENTS This work was partly supported by the NSFC through grants U20B2053, 61872022 and 62002007, S&T Program of Hebei through grant 20310101D; partly supported by the ARC DECRA Project under  ... 
arXiv:2107.02126v5 fatcat:ncnlgrssqbcfpekvm4rrmrd6gi

Natural Language Processing for EHR-Based Computational Phenotyping

Zexian Zeng, Yu Deng, Xiaoyu Li, Tristan Naumann, Yuan Luo
2018 IEEE/ACM Transactions on Computational Biology & Bioinformatics  
Supervised machine learning models have been favored because they are capable of acquiring both classification patterns and structures from data.  ...  Recently, deep learning and unsupervised learning have received growing attention, with the former favored for its performance and the latter for its ability to find novel phenotypes.  ...  Acknowledgment This work was supported in part by NIH Grant 1R21LM012618-01, NLM Biomedical Informatics Training Grant 2T15 LM007092-22, and the Intel Science and Technology Center for Big Data.  ... 
doi:10.1109/tcbb.2018.2849968 pmid:29994486 pmcid:PMC6388621 fatcat:wsksxvr7lfbgjowrsymghld64u

An unsupervised long short-term memory neural network for event detection in cell videos [article]

Ha Tran Hong Phan, Ashnil Kumar, David Feng, Michael Fulham, Jinman Kim
2017 arXiv   pre-print
We used an F1-score, which is a balanced measure for both precision and recall.  ...  We propose an automatic unsupervised cell event detection and classification method, which expands convolutional Long Short-Term Memory (LSTM) neural networks, for cellular events in cell video sequences  ...  , can also be used to filter the input for our unsupervised model.  ... 
arXiv:1709.02081v1 fatcat:7vscp3z4jjge3ka7yjeteseffm
« Previous Showing results 1 — 15 out of 5,099 results