Semantic reasoning for smog disaster analysis

Jiaoyan Chen; Huajun Chen; Jeff Z. Pan

Semantic reasoning for smog disaster analysis

Jiaoyan Chen
, Huajun Chen
, Jeff Z. Pan

Computing Science

Zhejiang University

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

Abstract

Smog disaster is a severe global problem. Although it has been investigated for decades in environmental sciences, the analysis of smog data recently becomes an open problem in fields like big data and artificial intelligence. In this paper, we present our study of utilizing semantic reasoning techniques for accurate and explanatory smog disaster prediction. To this end, we enriched the smog data streams with background knowledge by ontology modeling, inferred underlying knowledge like semantic assertions and rules, built consistent prediction models by embedding the knowledge (i.e., assertions and rules) in machine learning algorithms, and finally provided explanations by rule-based reasoning.

Original language	English
Title of host publication	DL 2016 International Workshop on Description Logics
Subtitle of host publication	Proceedings of the 29th International Workshop on Description Logics
Editors	M Lenzerini, R Penaloza
Publisher	CEUR-WS
Volume	1577
ISBN (Print)	1613-0073
Publication status	Published - 2016
Event	29th International Workshop on Description Logics, DL 2016 - Cape Town, South Africa Duration: 22 Apr 2016 → 25 Apr 2016

Conference

Conference	29th International Workshop on Description Logics, DL 2016
Country/Territory	South Africa
City	Cape Town
Period	22/04/16 → 25/04/16

Bibliographical note

Code 121200
This work is funded by NSFC 61473260, national key S and T Special projects 2015ZX03003012, and supported by the Fundamental Research Funds for the Central Universities.

Keywords

Ontology
OWL
Rule
Semantic reasoning
Smog disaster

Access to Document

http://ceur-ws.org/Vol-1577/Licence: Unspecified

Cite this

Chen, J, Chen, H & Pan, JZ 2016, Semantic reasoning for smog disaster analysis. in M Lenzerini & R Penaloza (eds), DL 2016 International Workshop on Description Logics: Proceedings of the 29th International Workshop on Description Logics. vol. 1577, CEUR-WS, 29th International Workshop on Description Logics, DL 2016, Cape Town, South Africa, 22/04/16. <http://ceur-ws.org/Vol-1577/>

@inproceedings{1901c161b6554a88a98cf38f3a0b7eb1,

title = "Semantic reasoning for smog disaster analysis",

abstract = "Smog disaster is a severe global problem. Although it has been investigated for decades in environmental sciences, the analysis of smog data recently becomes an open problem in fields like big data and artificial intelligence. In this paper, we present our study of utilizing semantic reasoning techniques for accurate and explanatory smog disaster prediction. To this end, we enriched the smog data streams with background knowledge by ontology modeling, inferred underlying knowledge like semantic assertions and rules, built consistent prediction models by embedding the knowledge (i.e., assertions and rules) in machine learning algorithms, and finally provided explanations by rule-based reasoning.",

keywords = "Ontology, OWL, Rule, Semantic reasoning, Smog disaster",

author = "Jiaoyan Chen and Huajun Chen and Pan, \{Jeff Z.\}",

note = "Code 121200 This work is funded by NSFC 61473260, national key S and T Special projects 2015ZX03003012, and supported by the Fundamental Research Funds for the Central Universities. ; 29th International Workshop on Description Logics, DL 2016 ; Conference date: 22-04-2016 Through 25-04-2016",

year = "2016",

language = "English",

isbn = "1613-0073",

volume = "1577",

editor = "M Lenzerini and R Penaloza",

booktitle = "DL 2016 International Workshop on Description Logics",

publisher = "CEUR-WS",

}

TY - GEN

T1 - Semantic reasoning for smog disaster analysis

AU - Chen, Jiaoyan

AU - Chen, Huajun

AU - Pan, Jeff Z.

N1 - Code 121200 This work is funded by NSFC 61473260, national key S and T Special projects 2015ZX03003012, and supported by the Fundamental Research Funds for the Central Universities.

PY - 2016

Y1 - 2016

N2 - Smog disaster is a severe global problem. Although it has been investigated for decades in environmental sciences, the analysis of smog data recently becomes an open problem in fields like big data and artificial intelligence. In this paper, we present our study of utilizing semantic reasoning techniques for accurate and explanatory smog disaster prediction. To this end, we enriched the smog data streams with background knowledge by ontology modeling, inferred underlying knowledge like semantic assertions and rules, built consistent prediction models by embedding the knowledge (i.e., assertions and rules) in machine learning algorithms, and finally provided explanations by rule-based reasoning.

AB - Smog disaster is a severe global problem. Although it has been investigated for decades in environmental sciences, the analysis of smog data recently becomes an open problem in fields like big data and artificial intelligence. In this paper, we present our study of utilizing semantic reasoning techniques for accurate and explanatory smog disaster prediction. To this end, we enriched the smog data streams with background knowledge by ontology modeling, inferred underlying knowledge like semantic assertions and rules, built consistent prediction models by embedding the knowledge (i.e., assertions and rules) in machine learning algorithms, and finally provided explanations by rule-based reasoning.

KW - Ontology

KW - OWL

KW - Rule

KW - Semantic reasoning

KW - Smog disaster

UR - https://www.scopus.com/pages/publications/84978153979

M3 - Published conference contribution

AN - SCOPUS:84978153979

SN - 1613-0073

VL - 1577

BT - DL 2016 International Workshop on Description Logics

A2 - Lenzerini, M

A2 - Penaloza, R

PB - CEUR-WS

T2 - 29th International Workshop on Description Logics, DL 2016

Y2 - 22 April 2016 through 25 April 2016

ER -

Semantic reasoning for smog disaster analysis

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this