Optimizing neuro-fuzzy modules for data fusion of vehicular navigation systems using temporal cross-validation

Aboelmagd Noureldin, Ahmed El-Shafie, Mahmoud Reda Taha

Research output: Contribution to journalArticle

57 Citations (Scopus)

Abstract

The last two decades have shown an increasing trend in the use of positioning and navigation technologies in land vehicles. Most of the present navigation systems incorporate global positioning system (GPS) and inertial navigation system (INS), which are integrated using Kalman filtering (KF) to provide reliable positioning information. Due to several inadequacies related to KF-based INS/GPS integration, artificial intelligence (AI) methods have been recently suggested to replace KF. Various neural network and neuro-fuzzy methods for INS/GPS integration were introduced. However, these methods provided relatively poor positioning accuracy during long GPS outages. Moreover, the internal system parameters had to be tuned over time of the navigation mission to reach the desired positioning accuracy. In order to overcome these limitations, this study optimizes the AI-based INS/GPS integration schemes utilizing adaptive neuro-fuzzy inference system (ANFIS) by implementing, a temporal window-based cross-validation approach during the update procedure. The ANFIS-based system considers a non-overlap moving window instead of the commonly used sliding window approach. The proposed system is tested using differential GPS and navigational grade INS field test data obtained from a land vehicle experiment. The results showed that the proposed system is a reliable modeless system and platform independent module that requires no priori knowledge of the navigation equipment utilized. In addition, significant accuracy improvement was achieved during long GPS outages.

Original languageEnglish
Pages (from-to)49-61
Number of pages13
JournalEngineering Applications of Artificial Intelligence
Volume20
Issue number1
DOIs
Publication statusPublished - Feb 2007
Externally publishedYes

Fingerprint

Data fusion
Navigation systems
Global positioning system
Inertial navigation systems
Navigation
Fuzzy inference
Outages
Artificial intelligence
Neural networks

Keywords

  • Navigation systems
  • Neuro-fuzzy modeling
  • Sensor integration

ASJC Scopus subject areas

  • Artificial Intelligence
  • Control and Systems Engineering

Cite this

Optimizing neuro-fuzzy modules for data fusion of vehicular navigation systems using temporal cross-validation. / Noureldin, Aboelmagd; El-Shafie, Ahmed; Reda Taha, Mahmoud.

In: Engineering Applications of Artificial Intelligence, Vol. 20, No. 1, 02.2007, p. 49-61.

Research output: Contribution to journalArticle

@article{776cd30a88ab42fa88901e8d5d9d90a1,
title = "Optimizing neuro-fuzzy modules for data fusion of vehicular navigation systems using temporal cross-validation",
abstract = "The last two decades have shown an increasing trend in the use of positioning and navigation technologies in land vehicles. Most of the present navigation systems incorporate global positioning system (GPS) and inertial navigation system (INS), which are integrated using Kalman filtering (KF) to provide reliable positioning information. Due to several inadequacies related to KF-based INS/GPS integration, artificial intelligence (AI) methods have been recently suggested to replace KF. Various neural network and neuro-fuzzy methods for INS/GPS integration were introduced. However, these methods provided relatively poor positioning accuracy during long GPS outages. Moreover, the internal system parameters had to be tuned over time of the navigation mission to reach the desired positioning accuracy. In order to overcome these limitations, this study optimizes the AI-based INS/GPS integration schemes utilizing adaptive neuro-fuzzy inference system (ANFIS) by implementing, a temporal window-based cross-validation approach during the update procedure. The ANFIS-based system considers a non-overlap moving window instead of the commonly used sliding window approach. The proposed system is tested using differential GPS and navigational grade INS field test data obtained from a land vehicle experiment. The results showed that the proposed system is a reliable modeless system and platform independent module that requires no priori knowledge of the navigation equipment utilized. In addition, significant accuracy improvement was achieved during long GPS outages.",
keywords = "Navigation systems, Neuro-fuzzy modeling, Sensor integration",
author = "Aboelmagd Noureldin and Ahmed El-Shafie and {Reda Taha}, Mahmoud",
year = "2007",
month = "2",
doi = "10.1016/j.engappai.2006.03.002",
language = "English",
volume = "20",
pages = "49--61",
journal = "Engineering Applications of Artificial Intelligence",
issn = "0952-1976",
publisher = "Elsevier Limited",
number = "1",

}

TY - JOUR

T1 - Optimizing neuro-fuzzy modules for data fusion of vehicular navigation systems using temporal cross-validation

AU - Noureldin, Aboelmagd

AU - El-Shafie, Ahmed

AU - Reda Taha, Mahmoud

PY - 2007/2

Y1 - 2007/2

N2 - The last two decades have shown an increasing trend in the use of positioning and navigation technologies in land vehicles. Most of the present navigation systems incorporate global positioning system (GPS) and inertial navigation system (INS), which are integrated using Kalman filtering (KF) to provide reliable positioning information. Due to several inadequacies related to KF-based INS/GPS integration, artificial intelligence (AI) methods have been recently suggested to replace KF. Various neural network and neuro-fuzzy methods for INS/GPS integration were introduced. However, these methods provided relatively poor positioning accuracy during long GPS outages. Moreover, the internal system parameters had to be tuned over time of the navigation mission to reach the desired positioning accuracy. In order to overcome these limitations, this study optimizes the AI-based INS/GPS integration schemes utilizing adaptive neuro-fuzzy inference system (ANFIS) by implementing, a temporal window-based cross-validation approach during the update procedure. The ANFIS-based system considers a non-overlap moving window instead of the commonly used sliding window approach. The proposed system is tested using differential GPS and navigational grade INS field test data obtained from a land vehicle experiment. The results showed that the proposed system is a reliable modeless system and platform independent module that requires no priori knowledge of the navigation equipment utilized. In addition, significant accuracy improvement was achieved during long GPS outages.

AB - The last two decades have shown an increasing trend in the use of positioning and navigation technologies in land vehicles. Most of the present navigation systems incorporate global positioning system (GPS) and inertial navigation system (INS), which are integrated using Kalman filtering (KF) to provide reliable positioning information. Due to several inadequacies related to KF-based INS/GPS integration, artificial intelligence (AI) methods have been recently suggested to replace KF. Various neural network and neuro-fuzzy methods for INS/GPS integration were introduced. However, these methods provided relatively poor positioning accuracy during long GPS outages. Moreover, the internal system parameters had to be tuned over time of the navigation mission to reach the desired positioning accuracy. In order to overcome these limitations, this study optimizes the AI-based INS/GPS integration schemes utilizing adaptive neuro-fuzzy inference system (ANFIS) by implementing, a temporal window-based cross-validation approach during the update procedure. The ANFIS-based system considers a non-overlap moving window instead of the commonly used sliding window approach. The proposed system is tested using differential GPS and navigational grade INS field test data obtained from a land vehicle experiment. The results showed that the proposed system is a reliable modeless system and platform independent module that requires no priori knowledge of the navigation equipment utilized. In addition, significant accuracy improvement was achieved during long GPS outages.

KW - Navigation systems

KW - Neuro-fuzzy modeling

KW - Sensor integration

UR - http://www.scopus.com/inward/record.url?scp=33750605072&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33750605072&partnerID=8YFLogxK

U2 - 10.1016/j.engappai.2006.03.002

DO - 10.1016/j.engappai.2006.03.002

M3 - Article

VL - 20

SP - 49

EP - 61

JO - Engineering Applications of Artificial Intelligence

JF - Engineering Applications of Artificial Intelligence

SN - 0952-1976

IS - 1

ER -