Comparing Knowledge-Driven and Data-Driven Modeling methods for susceptibility mapping in spatial epidemiology : a case study in Visceral Leishmaniasis

Mohammadreza Rajabi; Ali Mansourian; Petter Pilesjö; Finn Hedefalk; Roger Groth; Ahad Bazmani

Comparing Knowledge-Driven and Data-Driven Modeling methods for susceptibility mapping in spatial epidemiology : a case study in Visceral Leishmaniasis

Mohammadreza Rajabi, Ali Mansourian, Petter Pilesjö, Finn Hedefalk, Roger Groth, Ahad Bazmani

Tabriz University of Medical Sciences

Research output: Chapter in Book/Report/Conference proceeding › Paper in conference proceeding › peer-review

1 Downloads (Pure)

Abstract

The aim of this study is to compare knowledge-driven and data-driven methods for susceptibility mapping in spatial epidemiology. Our comparison focuses on one of the arguably most important requisites in such models, namely predictability. We compare one data-driven modelling method called Radial Basis Functional Link Net (RBFLN - a well-established Neural Network method) with two knowledge-driven modelling methods, Fuzzy AHP_OWA and Fuzzy GIS-based group decision making (multi criteria decision making methods). These methods are compared in the context of a concrete case study, namely the environmental modelling of Visceral Leishmaniasis (VL) for predictive mapping of risky areas. Our results show that, at least in this particular application, RBFLN model offers the best predictive accuracy

Original language	English
Title of host publication	Proceedings of the AGILE'2014 International Conference on Geographic Information Science, Castellón, June, 3-6
Publisher	Association of Geographic Information Laboratories for Europe
Pages	1-5
Number of pages	5
Publication status	Published - 2014
Event	17th AGILE International Conference on Geographic Information Science, 2014 - Castellon, Spain Duration: 2014 Jun 2 → 2014 Jun 6

Conference

Conference	17th AGILE International Conference on Geographic Information Science, 2014
Country/Territory	Spain
City	Castellon
Period	2014/06/02 → 2014/06/06

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Subject classification (UKÄ)

Physical Geography

Free keywords

Visceral Leishmaniasis (VL)
spatial epidemiology
prediction
knowledge-driven method
data-driven method.
Artificial Intelligence (AI)
Geospatial Artificial Intelligence (GeoAI)

Access to Document

agile2014_126

Geospatial modeling and simulation techniques to study prevalence and spread of diseases
Mansourian, A. (Supervisor), Pilesjö, P. (Assistant supervisor) & RAJABI GURANDANI, M. (Research student)
2013/09/01 → 2017/09/30
Project: Dissertation

Cite this

Rajabi, M., Mansourian, A., Pilesjö, P., Hedefalk, F., Groth, R., & Bazmani, A. (2014). Comparing Knowledge-Driven and Data-Driven Modeling methods for susceptibility mapping in spatial epidemiology : a case study in Visceral Leishmaniasis. In Proceedings of the AGILE'2014 International Conference on Geographic Information Science, Castellón, June, 3-6 (pp. 1-5). Association of Geographic Information Laboratories for Europe.

Rajabi, Mohammadreza ; Mansourian, Ali ; Pilesjö, Petter et al. / Comparing Knowledge-Driven and Data-Driven Modeling methods for susceptibility mapping in spatial epidemiology : a case study in Visceral Leishmaniasis. Proceedings of the AGILE'2014 International Conference on Geographic Information Science, Castellón, June, 3-6. Association of Geographic Information Laboratories for Europe, 2014. pp. 1-5

@inproceedings{3f2adb14c3234061b1ca5b3638b711a6,

title = "Comparing Knowledge-Driven and Data-Driven Modeling methods for susceptibility mapping in spatial epidemiology : a case study in Visceral Leishmaniasis",

abstract = "The aim of this study is to compare knowledge-driven and data-driven methods for susceptibility mapping in spatial epidemiology. Our comparison focuses on one of the arguably most important requisites in such models, namely predictability. We compare one data-driven modelling method called Radial Basis Functional Link Net (RBFLN - a well-established Neural Network method) with two knowledge-driven modelling methods, Fuzzy AHP\_OWA and Fuzzy GIS-based group decision making (multi criteria decision making methods). These methods are compared in the context of a concrete case study, namely the environmental modelling of Visceral Leishmaniasis (VL) for predictive mapping of risky areas. Our results show that, at least in this particular application, RBFLN model offers the best predictive accuracy",

keywords = "Visceral Leishmaniasis (VL), spatial epidemiology, prediction, knowledge-driven method, data-driven method., Artificial Intelligence (AI), Geospatial Artificial Intelligence (GeoAI)",

author = "Mohammadreza Rajabi and Ali Mansourian and Petter Pilesj{\"o} and Finn Hedefalk and Roger Groth and Ahad Bazmani",

year = "2014",

language = "English",

pages = "1--5",

booktitle = "Proceedings of the AGILE'2014 International Conference on Geographic Information Science, Castell{\'o}n, June, 3-6",

publisher = "Association of Geographic Information Laboratories for Europe",

note = "17th AGILE International Conference on Geographic Information Science, 2014 ; Conference date: 02-06-2014 Through 06-06-2014",

}

Rajabi, M, Mansourian, A , Pilesjö, P , Hedefalk, F, Groth, R & Bazmani, A 2014, Comparing Knowledge-Driven and Data-Driven Modeling methods for susceptibility mapping in spatial epidemiology : a case study in Visceral Leishmaniasis. in Proceedings of the AGILE'2014 International Conference on Geographic Information Science, Castellón, June, 3-6. Association of Geographic Information Laboratories for Europe, pp. 1-5, 17th AGILE International Conference on Geographic Information Science, 2014, Castellon, Spain, 2014/06/02.

Comparing Knowledge-Driven and Data-Driven Modeling methods for susceptibility mapping in spatial epidemiology : a case study in Visceral Leishmaniasis. / Rajabi, Mohammadreza; Mansourian, Ali ; Pilesjö, Petter et al.
Proceedings of the AGILE'2014 International Conference on Geographic Information Science, Castellón, June, 3-6. Association of Geographic Information Laboratories for Europe, 2014. p. 1-5.

Research output: Chapter in Book/Report/Conference proceeding › Paper in conference proceeding › peer-review

TY - GEN

T1 - Comparing Knowledge-Driven and Data-Driven Modeling methods for susceptibility mapping in spatial epidemiology : a case study in Visceral Leishmaniasis

AU - Rajabi, Mohammadreza

AU - Mansourian, Ali

AU - Pilesjö, Petter

AU - Hedefalk, Finn

AU - Groth, Roger

AU - Bazmani, Ahad

PY - 2014

Y1 - 2014

N2 - The aim of this study is to compare knowledge-driven and data-driven methods for susceptibility mapping in spatial epidemiology. Our comparison focuses on one of the arguably most important requisites in such models, namely predictability. We compare one data-driven modelling method called Radial Basis Functional Link Net (RBFLN - a well-established Neural Network method) with two knowledge-driven modelling methods, Fuzzy AHP_OWA and Fuzzy GIS-based group decision making (multi criteria decision making methods). These methods are compared in the context of a concrete case study, namely the environmental modelling of Visceral Leishmaniasis (VL) for predictive mapping of risky areas. Our results show that, at least in this particular application, RBFLN model offers the best predictive accuracy

AB - The aim of this study is to compare knowledge-driven and data-driven methods for susceptibility mapping in spatial epidemiology. Our comparison focuses on one of the arguably most important requisites in such models, namely predictability. We compare one data-driven modelling method called Radial Basis Functional Link Net (RBFLN - a well-established Neural Network method) with two knowledge-driven modelling methods, Fuzzy AHP_OWA and Fuzzy GIS-based group decision making (multi criteria decision making methods). These methods are compared in the context of a concrete case study, namely the environmental modelling of Visceral Leishmaniasis (VL) for predictive mapping of risky areas. Our results show that, at least in this particular application, RBFLN model offers the best predictive accuracy

KW - Visceral Leishmaniasis (VL)

KW - spatial epidemiology

KW - prediction

KW - knowledge-driven method

KW - data-driven method.

KW - Artificial Intelligence (AI)

KW - Geospatial Artificial Intelligence (GeoAI)

M3 - Paper in conference proceeding

SP - 1

EP - 5

BT - Proceedings of the AGILE'2014 International Conference on Geographic Information Science, Castellón, June, 3-6

PB - Association of Geographic Information Laboratories for Europe

T2 - 17th AGILE International Conference on Geographic Information Science, 2014

Y2 - 2 June 2014 through 6 June 2014

ER -

Rajabi M, Mansourian A , Pilesjö P , Hedefalk F, Groth R, Bazmani A. Comparing Knowledge-Driven and Data-Driven Modeling methods for susceptibility mapping in spatial epidemiology : a case study in Visceral Leishmaniasis. In Proceedings of the AGILE'2014 International Conference on Geographic Information Science, Castellón, June, 3-6. Association of Geographic Information Laboratories for Europe. 2014. p. 1-5

Comparing Knowledge-Driven and Data-Driven Modeling methods for susceptibility mapping in spatial epidemiology : a case study in Visceral Leishmaniasis

Abstract

Conference

UN SDGs

Subject classification (UKÄ)

Free keywords

Access to Document

Fingerprint

Projects

Geospatial modeling and simulation techniques to study prevalence and spread of diseases

Cite this