Pattern Identification for State Prediction in Dynamic Data Streams
Authors:
- Shirin EnshaeifarSEShirin Enshaeifar
- Seyed Amir HoseinitabatabaeiSHSeyed Amir Hoseinitabatabaei
- Alireza AhrabianAAAlireza Ahrabian
- Payam BarnaghiPBPayam Barnaghi
- 1 June 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 800-805
Abstract
This work proposes a pattern identification and online prediction algorithm for processing Internet of Things (IoT) time-series data. This is achieved by first proposing a new data aggregation and data driven discretisation method that does not require data segment normalisation. We apply a dictionary based algorithm in order to identify patterns of interest along with prediction of the next pattern. The performance of the proposed method is evaluated using synthetic and real-world datasets. The evaluations results shows that our system is able to identify the patterns by up to 85% accuracy which is 16.5% higher than a baseline using the Symbolic Aggregation Approximation (SAX) method.Keywords
This publication has 11 references indexed in Scilit:
- On Searching the Internet of Things: Requirements and ChallengesIEEE Intelligent Systems, 2016
- A Practical Evaluation of Information Processing and Abstraction Techniques for the Internet of ThingsIEEE Internet of Things Journal, 2015
- Information Abstraction for Heterogeneous Real World Internet DataIEEE Sensors Journal, 2013
- Semantics for the Internet of ThingsInternational Journal on Semantic Web and Information Systems, 2012
- SPITFIRE: toward a semantic web of thingsIEEE Communications Magazine, 2011
- Internet of Things: Applications and Challenges in Technology and StandardizationWireless Personal Communications, 2011
- From the Internet of Things to the Web of Things: Resource-oriented Architecture and Best Practices2011
- The WEKA data mining softwareACM SIGKDD Explorations Newsletter, 2009
- Complex-valued prediction of wind profile using augmented complex statisticsRenewable Energy, 2009
- A symbolic representation of time series, with implications for streaming algorithms2003