Localization of industrial wireless sensor networks: an artificial neural network approach

Authors:
Mohammad Gholami;Robert W. Brennan
Affiliations:
Department of Mechanical and Manufacturing Engineering, Schulich School of Engineering, University of Calgary, Calgary, Alberta, Canada;Department of Mechanical and Manufacturing Engineering, Schulich School of Engineering, University of Calgary, Calgary, Alberta, Canada
Venue:
HoloMAS'11 Proceedings of the 5th international conference on Industrial applications of holonic and multi-agent systems for manufacturing
Year:
2011

Citing 8
Cited 1

Neurocomputing

Neurocomputing
Fundamentals of neural networks: architectures, algorithms, and applications

Fundamentals of neural networks: architectures, algorithms, and applications
A New In-Door Location Detection Method Adopting Learning Algorithms

PERCOM '03 Proceedings of the First IEEE International Conference on Pervasive Computing and Communications
Robust distributed network localization with noisy range measurements

SenSys '04 Proceedings of the 2nd international conference on Embedded networked sensor systems
Novel self-configurable positioning technique for multihop wireless networks

IEEE/ACM Transactions on Networking (TON)
Wireless sensor network survey

Computer Networks: The International Journal of Computer and Telecommunications Networking
A soft computing approach to localization in wireless sensor networks

Expert Systems with Applications: An International Journal
An artificial neural network approach to the problem of wireless sensors network localization

Robotics and Computer-Integrated Manufacturing

Evaluating alternative approaches to mobile object localization in wireless sensor networks with passive architecture

Computers in Industry

Quantified Score

Hi-index	0.00

Visualization

Abstract

With the augmentation of industrial applications of wireless sensor networks, the problem of localization in such networks gains more attention. Although a considerable amount of research has been conducted in this area, many of the proposed approaches produce unsatisfactory results when exposed to the harsh, uncertain, noisy conditions of a manufacturing environment. An artificial neural network approach is developed in this study to abate the effects of the environmental noise sources and harsh factory conditions on the localization of the wireless sensors. A simulator, imitating the noisy and dynamic shop conditions of manufacturing environments, is employed to examine our proposed neural network. Subsequently, a sensitivity analysis is conducted using design of experiments methods. The results obtained indicate that noise intensity and anchor node topology give the most significant impact on the performance of the proposed localization technique. These results, combined with the inherent distributed and changeable nature of wireless sensor networks, have led us to investigate a multi-agent solution to this problem.