Filters








498 Hits in 3.5 sec

Periodicity testing with sublinear samples and space

Funda Ergun, S. Muthukrishnan, Cenk Sahinalp
2010 ACM Transactions on Algorithms  
In this work, we are interested in finding representative trends in long large data streams in the presence of computational constraints; to this end we present algorithms for discovering periodic trends  ...  Our algorithms may be viewed as working on streaming inputs where each data item is seen once and in order, storing only a sublinear -O( √ n polylog n) -size sample from which periodicities are identified  ...  Acknowledgements The authors would like to thank the anonymous referees for significantly improving the presentation of this paper.  ... 
doi:10.1145/1721837.1721859 fatcat:kbxo32bbyberzbkrjubbpldzj4

SpotLight

Dhivya Eswaran, Christos Faloutsos, Sudipto Guha, Nina Mishra
2018 Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining - KDD '18  
How can we detect port scan or denial of service attacks from IP-IP communication data?  ...  of large dense subgraphs (e.g., near bicliques) in near real-time using sublinear memory?  ...  ACKNOWLEDGMENTS We thank Roger Barga, Charles Elkan, Nima Sharifi Mehr, Morteza Monemizadeh and Yonatan Naamad for insightful discussions.  ... 
doi:10.1145/3219819.3220040 dblp:conf/kdd/EswaranFGM18 fatcat:g4yviy5fhnh5bhoe2rn6iplila

GeoScope

Ceren Budak, Theodore Georgiou, Divyakant Agrawal, Amr El Abbadi
2013 Proceedings of the VLDB Endowment  
GeoScope offers theoretical guarantees for detecting all trending correlated pairs while requiring only sublinear space and running time.  ...  GeoScope is a data streams solution that detects correlations between topics and locations in a sliding window, in addition to analyzing topics and locations independently.  ...  To the best of our knowledge, this is the first work that detects spatial information trends in social networks by capturing correlations in a multi-dimensional data stream.  ... 
doi:10.14778/2732240.2732242 fatcat:wn7biu6frzf4dcsvuxiyjpu3pu

Online L1-Dictionary Learning with Application to Novel Document Detection

Shiva Prasad Kasiviswanathan, Huahua Wang, Arindam Banerjee, Prem Melville
2012 Neural Information Processing Systems  
Empirical results on news-stream and Twitter data, shows that this online 1 -dictionary learning algorithm for novel document detection gives more than an order of magnitude speedup over the previously  ...  We present an efficient online algorithm for this problem based on alternating directions method of multipliers, and establish a sublinear regret bound for this algorithm.  ...  Using this online algorithm for 1 -dictionary learning, we obtain an online algorithm for novel document detection, which we empirically validate on traditional news-streams as well as streaming data from  ... 
dblp:conf/nips/KasiviswanathanWBM12 fatcat:6gg4nmxcdbbqbgutlu5gf2jyzy

Finding surprising patterns in textual data streams

Tristan Snowsill, Florent Nicart, Marco Stefani, Tijl De Bie, Nello Cristianini
2010 2010 2nd International Workshop on Cognitive Information Processing  
We address the task of detecting surprising patterns in large textual data streams.  ...  The volume of interest in such text streams often exceeds human capacity for analysis, such that automatic pattern recognition tools are indispensable.  ...  Outline of the paper In Section II we describe a method for change point analysis in time series data which we will use as a basis to detect Events in text streams.  ... 
doi:10.1109/cip.2010.5604085 dblp:conf/cogip/SnowsillNSBC10 fatcat:ab62kugwfjhgtikkddz76daxxe

Streaming Pattern Discovery in Multiple Time-Series

Spiros Papadimitriou, Jimeng Sun, Christos Faloutsos
2005 Very Large Data Bases Conference  
Given n numerical data streams, all of whose values we observe at each time tick t, SPIRIT can incrementally find correlations and hidden variables, which summarise the key trends in the entire stream  ...  In this paper, we introduce SPIRIT (Streaming Pattern dIscoveRy in multIple Timeseries).  ...  We wish to thank Michael Bigrigg for providing the temperature sensor data.  ... 
dblp:conf/vldb/PapadimitriouSF05 fatcat:fw5mcj443vep7ax32lm5gtgjra

Empirical Studies of Open Source Evolution [chapter]

Juan Fernandez-Ramil, Angela Lozano, Michel Wermelinger, Andrea Capiluppi
2008 Software Evolution  
, to account for the OSS observations.  ...  The chapter also discusses related topics for further research.  ...  data covering the period 1994 to 1999.  ... 
doi:10.1007/978-3-540-76440-3_11 dblp:series/springer/Fernandez-RamilLWC08 fatcat:ui7qjshq7jhv3byfuvpwgcsuzu

Learning from Time-Changing Data with Adaptive Windowing [chapter]

Albert Bifet, Ricard Gavaldà
2007 Proceedings of the 2007 SIAM International Conference on Data Mining  
Using ideas from data stream algorithmics, we develop a time-and memory-efficient version of this algorithm, called ADWIN2.  ...  inside the NB predictor to maintain up-to-date estimations of conditional probabilities in the data.  ...  Note that keeping exact counts for a fixed-window size is provably impossible in sublinear memory.  ... 
doi:10.1137/1.9781611972771.42 dblp:conf/sdm/BifetG07 fatcat:ealup4zuz5htdb342pivoggmhm

A survey on learning from data streams: current and future trends

João Gama
2012 Progress in Artificial Intelligence  
We identify the main issues and current challenges that emerge in learning from data streams that open research lines for further developments.  ...  Nowadays there are applications in which the data is modeled best not as persistent tables but rather as transient data streams.  ...  Discovery from Ubiquitous Data Streams.  ... 
doi:10.1007/s13748-011-0002-6 fatcat:lk3mn36yvbf57p7u2ugy7onkum

One Day in Twitter: Topic Detection Via Joint Complexity

Gérard Burnside, Dimitris Milioris, Philippe Jacquet
2014 The Web Conference  
In this paper we introduce a novel method to perform topic detection in Twitter based on the recent and novel technique of Joint Complexity.  ...  In this paper we exploit a dataset collected by using the Twitter streaming API for one full day, and we extract a significant number of topics for every timeslot.  ...  Conclusion and Future Work In this short paper we presented an implementation of a topic detection method applied to a dataset of tweets emitted during a 24 hour period.  ... 
dblp:conf/www/BurnsideMJ14 fatcat:t32ulydvc5cuxgltqro6u36cdy

Popularity-based Video Caching Techniques for Cache-enabled Networks: A survey

Huda S. Goian, Omar Y. Al-Jarrah, Sami Muhaidat, Yousof Al-Hammadi, Paul Yoo, Mehrdad Dianati
2019 IEEE Access  
In this paper, we first present an overview of caching in wireless networks and then provide a detailed comparison of traditional and popularity-based caching.  ...  Only a few contents are popular, accounting for the majority of viewers, so caching them reduces the latency and download time.  ...  It increases the global network gain for live streaming videos, but typical multicasting is not feasible for videoon-demand (VoD) because streaming periods occur asynchronously at unpredictable times  ... 
doi:10.1109/access.2019.2898734 fatcat:cw5d2naxjfhyxf6pzobbyupcri

Group Anomaly Detection: Past Notions, Present Insights, and Future Prospects

Aqeel Feroze, Ali Daud, Tehmina Amjad, Malik Khizar Hayat
2021 SN Computer Science  
future trends for this particular research area.  ...  In this research, we bifurcated group anomaly detection techniques into activity-based and graph-based methods.  ...  Salehi and Rashidi detected various anomalies in dynamic datasets [16] . They addressed the need for an anomaly detection method for data streams.  ... 
doi:10.1007/s42979-021-00603-x fatcat:oyjzthza7vbhnakpm3t2ko6ctq

A topic modeling framework for spatio-temporal information management

Mohsen Asghari, Daniel Sierra-Sosa, Adel S. Elmaghraby
2020 Information Processing & Management  
This paper introduces a framework for managing, processing, analyzing, detecting, and tracking topics in streaming data.  ...  In this system, we used visualization to have a better understanding of trending topics.  ...  CRediT authorship contribution statement Supplementary material Supplementary material associated with this article can be found, in the online version, at 10.1016/j.ipm.2020.102340  ... 
doi:10.1016/j.ipm.2020.102340 pmid:32836694 pmcid:PMC7338024 fatcat:lxqlo4bokvhlxbgltavjcagw7e

Development of a Cognitive Digital Twin for Building Management and Operations

Karim El Mokhtari, Ivan Panushev, J. J. McArthur
2022 Frontiers in Built Environment  
Streaming data to the cloud has been implemented in existing architectures; to address security concerns from exposing building equipment to undesirable access, a secure streaming architecture from BACnet  ...  (outlier and event detection).  ...  Portions of the research builds on the FuseForward technology for managing and automating the delivery of complex systems, as described in US patents US9406022 and US8595258, entitled "Method and System  ... 
doi:10.3389/fbuil.2022.856873 fatcat:3nv4j5hrgjae5hke4e2n52r5sm

Issues in data stream management

Lukasz Golab, M. Tamer Özsu
2003 SIGMOD record  
Limitations of traditional DBMSs in supporting streaming applications have been recognized, prompting research to augment existing technologies and build new systems to manage streaming data.  ...  The purpose of this paper is to review recent work in data stream management systems, with an emphasis on application requirements, data models, continuous query languages, and query evaluation. *  ...  Data Models and Query Languages for Streams The above requirements demand specific features to be included in the data models and query languages for data streams.  ... 
doi:10.1145/776985.776986 fatcat:soq554qj5nc7rkyifpm5vkuylm
« Previous Showing results 1 — 15 out of 498 results