Classification of structured validation data using stateless and stateful features

G. Schwenk, R. Pabst, Klaus Muller

Research output: Contribution to journalArticle

Abstract

To reliably identify problems impacting the service quality and system dependability of mobile communication networks, the monitored data needs to be validated. This paper proposes and evaluates analysis methods, features and learning methods for the automatic validation of such data, with a special focus on failure data of mobile communication data. This data can be analyzed for discriminating failures caused by problems in the infrastructure (valid failures) from those caused by other circumstances like device imperfections (invalid failures), with the purpose of filtering the invalid failures, which effectively increases both dependability and value of the underlying data. To represent the complex structural and temporal properties of the mobile communication data, two complementary feature representations are proposed and compared, followed by a discussion of classification methods which are suitable for these feature spaces and for an interpretation of their results to support manual auditing. Their classification performances on these feature spaces are evaluated and compared to competitive approaches. In the evaluation a classification performances of up to 97% AUC–ROC is achieved. This renders our approach a good alternative to using manual matching rules, which require costly expert-knowledge and are much more time-consuming to define and maintain — while also highlighting the relevance of combining feature spaces of different problem perspectives. Additionally it is shown that using non-proprietary data analysis can enable feature representations nearly as expressive as those created by using proprietary analysis methods, which allows a broader application of the proposed methods, due to the lower processing requirements.

Original languageEnglish
Pages (from-to)54-66
Number of pages13
JournalComputer Communications
Volume138
DOIs
Publication statusPublished - 2019 Apr 15

Fingerprint

Communication
Telecommunication networks
Defects
Processing

Keywords

  • Feature modeling
  • Interpretable learning
  • Mobile communication
  • Quality of service
  • Stateless and stateful features
  • Structured data
  • Supervised learning

ASJC Scopus subject areas

  • Computer Networks and Communications

Cite this

Classification of structured validation data using stateless and stateful features. / Schwenk, G.; Pabst, R.; Muller, Klaus.

In: Computer Communications, Vol. 138, 15.04.2019, p. 54-66.

Research output: Contribution to journalArticle

Schwenk, G. ; Pabst, R. ; Muller, Klaus. / Classification of structured validation data using stateless and stateful features. In: Computer Communications. 2019 ; Vol. 138. pp. 54-66.
@article{a6565ac6ad074e15998faacd69601174,
title = "Classification of structured validation data using stateless and stateful features",
abstract = "To reliably identify problems impacting the service quality and system dependability of mobile communication networks, the monitored data needs to be validated. This paper proposes and evaluates analysis methods, features and learning methods for the automatic validation of such data, with a special focus on failure data of mobile communication data. This data can be analyzed for discriminating failures caused by problems in the infrastructure (valid failures) from those caused by other circumstances like device imperfections (invalid failures), with the purpose of filtering the invalid failures, which effectively increases both dependability and value of the underlying data. To represent the complex structural and temporal properties of the mobile communication data, two complementary feature representations are proposed and compared, followed by a discussion of classification methods which are suitable for these feature spaces and for an interpretation of their results to support manual auditing. Their classification performances on these feature spaces are evaluated and compared to competitive approaches. In the evaluation a classification performances of up to 97{\%} AUC–ROC is achieved. This renders our approach a good alternative to using manual matching rules, which require costly expert-knowledge and are much more time-consuming to define and maintain — while also highlighting the relevance of combining feature spaces of different problem perspectives. Additionally it is shown that using non-proprietary data analysis can enable feature representations nearly as expressive as those created by using proprietary analysis methods, which allows a broader application of the proposed methods, due to the lower processing requirements.",
keywords = "Feature modeling, Interpretable learning, Mobile communication, Quality of service, Stateless and stateful features, Structured data, Supervised learning",
author = "G. Schwenk and R. Pabst and Klaus Muller",
year = "2019",
month = "4",
day = "15",
doi = "10.1016/j.comcom.2019.02.007",
language = "English",
volume = "138",
pages = "54--66",
journal = "Computer Communications",
issn = "0140-3664",
publisher = "Elsevier",

}

TY - JOUR

T1 - Classification of structured validation data using stateless and stateful features

AU - Schwenk, G.

AU - Pabst, R.

AU - Muller, Klaus

PY - 2019/4/15

Y1 - 2019/4/15

N2 - To reliably identify problems impacting the service quality and system dependability of mobile communication networks, the monitored data needs to be validated. This paper proposes and evaluates analysis methods, features and learning methods for the automatic validation of such data, with a special focus on failure data of mobile communication data. This data can be analyzed for discriminating failures caused by problems in the infrastructure (valid failures) from those caused by other circumstances like device imperfections (invalid failures), with the purpose of filtering the invalid failures, which effectively increases both dependability and value of the underlying data. To represent the complex structural and temporal properties of the mobile communication data, two complementary feature representations are proposed and compared, followed by a discussion of classification methods which are suitable for these feature spaces and for an interpretation of their results to support manual auditing. Their classification performances on these feature spaces are evaluated and compared to competitive approaches. In the evaluation a classification performances of up to 97% AUC–ROC is achieved. This renders our approach a good alternative to using manual matching rules, which require costly expert-knowledge and are much more time-consuming to define and maintain — while also highlighting the relevance of combining feature spaces of different problem perspectives. Additionally it is shown that using non-proprietary data analysis can enable feature representations nearly as expressive as those created by using proprietary analysis methods, which allows a broader application of the proposed methods, due to the lower processing requirements.

AB - To reliably identify problems impacting the service quality and system dependability of mobile communication networks, the monitored data needs to be validated. This paper proposes and evaluates analysis methods, features and learning methods for the automatic validation of such data, with a special focus on failure data of mobile communication data. This data can be analyzed for discriminating failures caused by problems in the infrastructure (valid failures) from those caused by other circumstances like device imperfections (invalid failures), with the purpose of filtering the invalid failures, which effectively increases both dependability and value of the underlying data. To represent the complex structural and temporal properties of the mobile communication data, two complementary feature representations are proposed and compared, followed by a discussion of classification methods which are suitable for these feature spaces and for an interpretation of their results to support manual auditing. Their classification performances on these feature spaces are evaluated and compared to competitive approaches. In the evaluation a classification performances of up to 97% AUC–ROC is achieved. This renders our approach a good alternative to using manual matching rules, which require costly expert-knowledge and are much more time-consuming to define and maintain — while also highlighting the relevance of combining feature spaces of different problem perspectives. Additionally it is shown that using non-proprietary data analysis can enable feature representations nearly as expressive as those created by using proprietary analysis methods, which allows a broader application of the proposed methods, due to the lower processing requirements.

KW - Feature modeling

KW - Interpretable learning

KW - Mobile communication

KW - Quality of service

KW - Stateless and stateful features

KW - Structured data

KW - Supervised learning

UR - http://www.scopus.com/inward/record.url?scp=85062691719&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062691719&partnerID=8YFLogxK

U2 - 10.1016/j.comcom.2019.02.007

DO - 10.1016/j.comcom.2019.02.007

M3 - Article

AN - SCOPUS:85062691719

VL - 138

SP - 54

EP - 66

JO - Computer Communications

JF - Computer Communications

SN - 0140-3664

ER -