13,765 Hits in 5.1 sec

Using Stream Features for Instant Document Filtering

Andreas Bauer, Christian Wolff
In this paper, we discuss how event processing technologies can be employed for real-time text stream processing and information filtering in the context of the TREC 2012 microblog task.  ...  Employing well-known term weighting schemes from document-centric text retrieval for temporally dynamic text streams is discussed next, giving details of the ESPER Event Processing Agents (EPAs) we have  ...  Determining document collection features in text streams For determining the document collection based features we employ sliding time windows as well.  ... 
doi:10.5283/epub.28090 fatcat:5zvr7yeecbcibefz2i4n25jvla

On the Utility of Incremental Feature Selection for the Classification of Textual Data Streams [chapter]

Ioannis Katakis, Grigorios Tsoumakas, Ioannis Vlahavas
2005 Lecture Notes in Computer Science  
In this paper we argue that incrementally updating the features that a text classification algorithm considers is very important for real-world textual data streams, because in most applications the distribution  ...  We propose the coupling of an incremental feature ranking method and an incremental learning algorithm that can consider different subsets of the feature vector during prediction (what we call a feature  ...  In Section 2 we noted that feature selection methods that are commonly used for text classification are filters that evaluate the predictive power of all features and select the N best.  ... 
doi:10.1007/11573036_32 fatcat:jalgk55efjh7lamuvhhvn5k2se

Spotting Rumors via Novelty Detection [article]

Yumeng Qin, Dominik Wurzer, Victor Lavrenko, Cunchen Tang
2016 arXiv   pre-print
To compensate for the absence of repeated signals, we make use of news wire as an additional data source.  ...  We introduce a new category of features based on novelty, tailored to detect rumours early on.  ...  For each document, all possible kterms are formed and hashed onto a Bloom Filter. Novelty is computed by the fraction of unseen kterms.  ... 
arXiv:1611.06322v1 fatcat:qhnuio5nfvbkzpgz37qqgipx7e

Streaming-media knowledge discovery

J. Pieper, S. Srinivasan, B. Dom
2001 Computer  
We view the detection task as a binary classifier function f(x) = y, where x 1, x2, ... xd is a feature vector for a given document.  ...  The live-media indexing-agent server constantly filters the incoming recognized speech for user-defined keywords, sending instant messages when it finds matching results.  ... 
doi:10.1109/2.947094 fatcat:kziydciz7zdmliipnmiyifh744

An adaptive personalized news dissemination system

Ioannis Katakis, Grigorios Tsoumakas, Evangelos Banos, Nick Bassiliades, Ioannis Vlahavas
2008 Journal of Intelligent Information Systems  
PersoNews is freely available for public use on the WWW (  ...  The main features of our system named PersoNews are: a) the aggregation of many different news sources that offer an RSS version of their content, b) incremental filtering, offering dynamic personalization  ...  Of course, a new document can be used as training document only if user feedback has been given. This is a general assumption in stream classification.  ... 
doi:10.1007/s10844-008-0053-8 fatcat:zwyvnbvj75fojn3fyrondpgmga

Frame Fusion for Video Copy Detection

Shikui Wei, Yao Zhao, Ce Zhu, Changsheng Xu, Zhenfeng Zhu
2011 IEEE transactions on circuits and systems for video technology (Print)  
While a lot of work has addressed the problem with good performance, less effort has been made to consider the copy detection problem in the case of a continuous query stream, for which precise temporal  ...  stream but also where the copy is located and where the copy is originated from.  ...  In our experiment, we use the implementation in the Lemur toolkits [19] for both similarity search and text document indexing. D.  ... 
doi:10.1109/tcsvt.2011.2105554 fatcat:4djawhc3lbdzlh5645nvy4enpa


J. C. Whittier, S. Nittel, I. Subasinghe
2017 ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
In previous work, we proposed the field stream data model (Liang et al., 2016) for data stream engines.  ...  In this paper, we undertake a feasibility study of using the field stream model and the open source Data Stream Engine (DSE) Apache Spark(Apache Spark, 2017) to implement a real-time earthquake event detection  ...  ACKNOWLEDGEMENTS The authors would like to acknowledge the National Science Foundation for supporting this work via Award No. 1527504.  ... 
doi:10.5194/isprs-annals-iv-4-w2-215-2017 fatcat:cuou4l55jvc2jc2hryqdps57hq

Distributed Modular Toolbox for Multi-modal Context Recognition [chapter]

David Bannach, Kai Kunze, Paul Lukowicz, Oliver Amft
2006 Lecture Notes in Computer Science  
The main features of the toolbox we focus on here are a set of parameterizable algorithms including different filters, feature computations and classifiers, a runtime environment that supports complex  ...  In addition, components are provided for group-wise, event-based sensor synchronization and data labeling.  ...  If several streams need to be merged (e.g., to create a feature vector containing data from multiple sensors), a special Merger tasks must be used.  ... 
doi:10.1007/11682127_8 fatcat:r5fnow25rzagnbhkdqorbbxsgi

Building and applying geographical information system Grids

Galip Aydin, Ahmet Sayar, Harshawardhan Gadgil, Mehmet S. Aktas, Geoffrey C. Fox, Sunghoon Ko, Hasan Bulut, Marlon E. Pierce
2008 Concurrency and Computation  
Following the WS-I+ approach of building Grids on Web Service standards, we have developed Data Grid components for archival and real-time data, map generating services that can be used to build user interfaces  ...  , information services for storing both stateless and stateful metadata, and service orchestration and management tools.  ...  Such service could be a conferencing, streaming, or instant messaging service.  ... 
doi:10.1002/cpe.1312 fatcat:4lwqkwlkpjaudpe2nh7xrtmosa

A multilevel approach to intelligent information filtering: model, system, and evaluation

J. Mostafa, S. Mukhopadhyay, M. Palakal, W. Lam
1997 ACM Transactions on Information Systems  
In information-filtering environments, uncertainties associated with changing interests of the user and the dynamic document stream must be handled efficiently.  ...  A filtering system, SIFTER, has been implemented based on the model, using established techniques in information retrieval and artificial intelligence.  ...  For all sessions, the document stream size used was 20, and the number of feedbacks per session was fixed at 7.  ... 
doi:10.1145/263479.263481 fatcat:cvofbifnjbhsljgdvt5yktb4vi

Visual Analytics of Bibliographical Data for Strategic Decision Support of University Leaders: A Design Study

Paul Rosenthal, Nicholas Müller, Fabian Bolte
2019 Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications  
Therefore, we present a design study that aims to craft a stream visualization for the easy to use and easy to understand display of publications across university institutions.  ...  As responsibilities about documentation of work in conjunction with an increase in third-party-funding for universities have been shifting over the last decade, new tools for the inspection and reporting  ...  These are implemented as buttons in the top left corner of the tool and allow for instant filtering of a set of departments or the instant selection of the research groups of whole de- As keyboard and  ... 
doi:10.5220/0007396302970305 dblp:conf/grapp/RosenthalMB19 fatcat:ftomia42kjepfdkzvk4sdsjfzy

SPEX: Streamed and Progressive Evaluation of XPath

D. Olteanu
2007 IEEE Transactions on Knowledge and Data Engineering  
This makes SPEX especially suitable for implementation on devices with low-memory and simple logic as used, e.g., in mobile computing.  ...  In many such applications, XML streams are arguably more appropriate than flat streams, for they convey (possibly unbounded) unranked ordered trees with labeled nodes.  ...  for the evaluation of Q against the stream D at any instant.  ... 
doi:10.1109/tkde.2007.1063 fatcat:td3vwi7wwnbffmjvj4n4mkyh2m

On-demand time-decaying bloom filters for telemarketer detection

Giuseppe Bianchi, Nico Nico d'Heureuse, Saverio Niccolini
2011 Computer communication review  
First, our analysis of Time-decaying Bloom filters, formerly proposed data structures devised to perform approximate Exponentially Weighted Moving Averages on streaming data, reveals two major shortcomings  ...  a formerly proposed system for telemarketing call detection.  ...  Beyond the punctual technical contribution here documented, we believe that our work, and the methodologies herein documented, may inspire monitoring applications' developers towards a stream-based rethinking  ... 
doi:10.1145/2043165.2043167 fatcat:5mwngla6pfh5llz4fkofqrts6m

Fusing Text and Image for Event Detection in Twitter

Samar M. Alqhtani, Suhuai Luo, Brian Regan
2015 The International Journal of Multimedia & Its Applications  
The procedure starts with detecting events based on text only by using the feature of the bag-of-words which is calculated using the term frequency-inverse document frequency (TF-IDF) method.  ...  In this contribution, we develop an accurate and effective event detection method to detect events from a Twitter stream, which uses visual and textual information to improve the performance of the mining  ...  It uses "bag of words" as the features of the text which will be collected using the Term Frequency-Inverse Document Frequency method (TF-IDF) [5] .  ... 
doi:10.5121/ijma.2015.7103 fatcat:slde7wpcbfcsbndzgc364zexze

Topic Evolutionary Tweet Stream Clustering Algorithm and TCV Rank Summarization

Selvaraj K, Balaji S
2016 International Journal of Advancements in Technology  
Our proposed work consist three components tweet stream clustering to cluster tweet using kmeans cluster algorithm and second tweet cluster vector technique to generate rank summarization using greedy  ...  Implementing continuous tweet stream reducing a text document is however not a simple task, since a huge number of tweets are worthless, unrelated and raucous in nature, due to the social nature of tweeting  ...  A variety of services on the Web such as news filtering, text crawling, and topic detecting etc. have posed requirements for text stream clustering.  ... 
doi:10.4172/0976-4860.1000162 fatcat:ghiei67gkbhehcuuy24rf43hxa
« Previous Showing results 1 — 15 out of 13,765 results