An event-based service framework for learning, querying and monitoring multivariate time series

Chun Kit Ngan; Alexander Brodsky; Jessica Lin

doi:10.1007/978-3-642-29958-2_14

An event-based service framework for learning, querying and monitoring multivariate time series

Chun Kit Ngan, Alexander Brodsky, Jessica Lin

Engineering Division (Great Valley)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Scopus citations

Abstract

We propose an event-based service framework for Multivariate Time Series Analytics (MTSA) that supports model definition, querying, parameter learning, model evaluation, monitoring, and decision recommendation on events. Our approach combines the strengths of both domain-knowledge-based and formal-learning-based approaches for maximizing utility on events over multivariate time series. More specifically, we identify multivariate time series parametric estimation problems, in which the objective function is dependent on the time points from which the parameters are learned. We propose an algorithm that guarantees to find the optimal time point(s), and we show that our approach produces results that are superior to those of the domain-knowledge-based approach and the logit regression model. We also develop MTSA data model and query language for the services of parameter learning, querying, and monitoring.

Original language	English (US)
Title of host publication	Enterprise Information Systems - 13th International Conference, ICEIS 2011, Revised Selected Papers
Publisher	Springer Verlag
Pages	208-223
Number of pages	16
ISBN (Print)	9783642299575
DOIs	https://doi.org/10.1007/978-3-642-29958-2_14
State	Published - 2012
Event	13th International Conference on Enterprise Information Systems, ICEIS 2011 - Beijing, China Duration: Jun 8 2011 → Jun 11 2011

Publication series

Name	Lecture Notes in Business Information Processing
Volume	102 LNBIP
ISSN (Print)	1865-1348

Other

Other	13th International Conference on Enterprise Information Systems, ICEIS 2011
Country/Territory	China
City	Beijing
Period	6/8/11 → 6/11/11

All Science Journal Classification (ASJC) codes

Management Information Systems
Control and Systems Engineering
Business and International Management
Information Systems
Modeling and Simulation
Information Systems and Management

Access to Document

10.1007/978-3-642-29958-2_14

Cite this

Ngan, C. K., Brodsky, A., & Lin, J. (2012). An event-based service framework for learning, querying and monitoring multivariate time series. In Enterprise Information Systems - 13th International Conference, ICEIS 2011, Revised Selected Papers (pp. 208-223). (Lecture Notes in Business Information Processing; Vol. 102 LNBIP). Springer Verlag. https://doi.org/10.1007/978-3-642-29958-2_14

@inproceedings{80d5b5e923234dee993c1004476ee70a,

title = "An event-based service framework for learning, querying and monitoring multivariate time series",

abstract = "We propose an event-based service framework for Multivariate Time Series Analytics (MTSA) that supports model definition, querying, parameter learning, model evaluation, monitoring, and decision recommendation on events. Our approach combines the strengths of both domain-knowledge-based and formal-learning-based approaches for maximizing utility on events over multivariate time series. More specifically, we identify multivariate time series parametric estimation problems, in which the objective function is dependent on the time points from which the parameters are learned. We propose an algorithm that guarantees to find the optimal time point(s), and we show that our approach produces results that are superior to those of the domain-knowledge-based approach and the logit regression model. We also develop MTSA data model and query language for the services of parameter learning, querying, and monitoring.",

author = "Ngan, {Chun Kit} and Alexander Brodsky and Jessica Lin",

year = "2012",

doi = "10.1007/978-3-642-29958-2_14",

language = "English (US)",

isbn = "9783642299575",

series = "Lecture Notes in Business Information Processing",

publisher = "Springer Verlag",

pages = "208--223",

booktitle = "Enterprise Information Systems - 13th International Conference, ICEIS 2011, Revised Selected Papers",

address = "Germany",

note = "13th International Conference on Enterprise Information Systems, ICEIS 2011 ; Conference date: 08-06-2011 Through 11-06-2011",

}

Ngan, CK, Brodsky, A & Lin, J 2012, An event-based service framework for learning, querying and monitoring multivariate time series. in Enterprise Information Systems - 13th International Conference, ICEIS 2011, Revised Selected Papers. Lecture Notes in Business Information Processing, vol. 102 LNBIP, Springer Verlag, pp. 208-223, 13th International Conference on Enterprise Information Systems, ICEIS 2011, Beijing, China, 6/8/11. https://doi.org/10.1007/978-3-642-29958-2_14

An event-based service framework for learning, querying and monitoring multivariate time series. / Ngan, Chun Kit; Brodsky, Alexander; Lin, Jessica.
Enterprise Information Systems - 13th International Conference, ICEIS 2011, Revised Selected Papers. Springer Verlag, 2012. p. 208-223 (Lecture Notes in Business Information Processing; Vol. 102 LNBIP).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - An event-based service framework for learning, querying and monitoring multivariate time series

AU - Ngan, Chun Kit

AU - Brodsky, Alexander

AU - Lin, Jessica

PY - 2012

Y1 - 2012

N2 - We propose an event-based service framework for Multivariate Time Series Analytics (MTSA) that supports model definition, querying, parameter learning, model evaluation, monitoring, and decision recommendation on events. Our approach combines the strengths of both domain-knowledge-based and formal-learning-based approaches for maximizing utility on events over multivariate time series. More specifically, we identify multivariate time series parametric estimation problems, in which the objective function is dependent on the time points from which the parameters are learned. We propose an algorithm that guarantees to find the optimal time point(s), and we show that our approach produces results that are superior to those of the domain-knowledge-based approach and the logit regression model. We also develop MTSA data model and query language for the services of parameter learning, querying, and monitoring.

AB - We propose an event-based service framework for Multivariate Time Series Analytics (MTSA) that supports model definition, querying, parameter learning, model evaluation, monitoring, and decision recommendation on events. Our approach combines the strengths of both domain-knowledge-based and formal-learning-based approaches for maximizing utility on events over multivariate time series. More specifically, we identify multivariate time series parametric estimation problems, in which the objective function is dependent on the time points from which the parameters are learned. We propose an algorithm that guarantees to find the optimal time point(s), and we show that our approach produces results that are superior to those of the domain-knowledge-based approach and the logit regression model. We also develop MTSA data model and query language for the services of parameter learning, querying, and monitoring.

UR - http://www.scopus.com/inward/record.url?scp=84861673765&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84861673765&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-29958-2_14

DO - 10.1007/978-3-642-29958-2_14

M3 - Conference contribution

AN - SCOPUS:84861673765

SN - 9783642299575

T3 - Lecture Notes in Business Information Processing

SP - 208

EP - 223

BT - Enterprise Information Systems - 13th International Conference, ICEIS 2011, Revised Selected Papers

PB - Springer Verlag

T2 - 13th International Conference on Enterprise Information Systems, ICEIS 2011

Y2 - 8 June 2011 through 11 June 2011

ER -

An event-based service framework for learning, querying and monitoring multivariate time series

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this