The Investigation of Mercury Presence in Human Blood: An Extrapolation From Animal Data Using Neural Networks

Ray R. Hashemi; Mahmood Bahar; Alexander A. Tyler; John Young

The Investigation of Mercury Presence in Human Blood: An Extrapolation From Animal Data Using Neural Networks

Ray R. Hashemi, Mahmood Bahar, Alexander A. Tyler, John Young

Computer Science

Research output: Contribution to book or proceeding › Chapter

2 Scopus citations

Abstract

In this research effort, a neural network approach was used as a method of extrapolating the presence of mercury in human blood from animal data. We also investigated the effect of different data representations (as-is, category, simple binary, thermometer and flag) on the model performance. In addition, we used the rough sets methodology to identify the redundant independent variables and then examined the proposed extrapolation model's performance for a reduced set of independent variables. Moreover, a quality measure was introduced that revealed that the proposed extrapolation model performed extremely well for the thermometer data representation.

Original language	American English
Title of host publication	Proceedings of The 2002 IEEE International Conference on Information Technology: Coding and Computing (ITCC-2002)
State	Published - Apr 2002

Disciplines

Computer Sciences
Engineering

Keywords

Animal data
As-is data representation
Category data representation
Extrapolation model performance
Flag data representation
Hg presence
Human blood
Neural network
Quality measure
Reduced variables set
Redundant independent variables identification
Rough sets methodology
Simple binary data representation
Thermometer data representation

Cite this

@inbook{05eb9a97fb1143f49c54a98e4e8bc3fb,

title = "The Investigation of Mercury Presence in Human Blood: An Extrapolation From Animal Data Using Neural Networks",

abstract = " In this research effort, a neural network approach was used as a method of extrapolating the presence of mercury in human blood from animal data. We also investigated the effect of different data representations (as-is, category, simple binary, thermometer and flag) on the model performance. In addition, we used the rough sets methodology to identify the redundant independent variables and then examined the proposed extrapolation model's performance for a reduced set of independent variables. Moreover, a quality measure was introduced that revealed that the proposed extrapolation model performed extremely well for the thermometer data representation.",

keywords = "Animal data, As-is data representation, Category data representation, Extrapolation model performance, Flag data representation, Hg presence, Human blood, Neural network, Quality measure, Reduced variables set, Redundant independent variables identification, Rough sets methodology, Simple binary data representation, Thermometer data representation",

author = "Hashemi, {Ray R.} and Mahmood Bahar and Tyler, {Alexander A.} and John Young",

note = "In this research effort, a neural network approach was used as a method of extrapolating the presence of mercury in human blood from animal data. We also i",

year = "2002",

month = apr,

language = "American English",

booktitle = "Proceedings of The 2002 IEEE International Conference on Information Technology: Coding and Computing (ITCC-2002)",

}

TY - CHAP

T1 - The Investigation of Mercury Presence in Human Blood

T2 - An Extrapolation From Animal Data Using Neural Networks

AU - Hashemi, Ray R.

AU - Bahar, Mahmood

AU - Tyler, Alexander A.

AU - Young, John

N1 - In this research effort, a neural network approach was used as a method of extrapolating the presence of mercury in human blood from animal data. We also i

PY - 2002/4

Y1 - 2002/4

N2 - In this research effort, a neural network approach was used as a method of extrapolating the presence of mercury in human blood from animal data. We also investigated the effect of different data representations (as-is, category, simple binary, thermometer and flag) on the model performance. In addition, we used the rough sets methodology to identify the redundant independent variables and then examined the proposed extrapolation model's performance for a reduced set of independent variables. Moreover, a quality measure was introduced that revealed that the proposed extrapolation model performed extremely well for the thermometer data representation.

AB - In this research effort, a neural network approach was used as a method of extrapolating the presence of mercury in human blood from animal data. We also investigated the effect of different data representations (as-is, category, simple binary, thermometer and flag) on the model performance. In addition, we used the rough sets methodology to identify the redundant independent variables and then examined the proposed extrapolation model's performance for a reduced set of independent variables. Moreover, a quality measure was introduced that revealed that the proposed extrapolation model performed extremely well for the thermometer data representation.

KW - Animal data

KW - As-is data representation

KW - Category data representation

KW - Extrapolation model performance

KW - Flag data representation

KW - Hg presence

KW - Human blood

KW - Neural network

KW - Quality measure

KW - Reduced variables set

KW - Redundant independent variables identification

KW - Rough sets methodology

KW - Simple binary data representation

KW - Thermometer data representation

UR - https://doi.org/10.1109/ITCC.2002.1000440

M3 - Chapter

BT - Proceedings of The 2002 IEEE International Conference on Information Technology: Coding and Computing (ITCC-2002)

ER -

The Investigation of Mercury Presence in Human Blood: An Extrapolation From Animal Data Using Neural Networks

Abstract

Disciplines

Keywords

Other files and links

Fingerprint

Cite this