TITLE

Fully Connected Neural Networks Ensemble with Signal Strength Clustering for Indoor Localization in Wireless Sensor Networks

AUTHOR(S)
Bernas, Marcin; Płaczek, Bartłomiej
PUB. DATE
December 2015
SOURCE
International Journal of Distributed Sensor Networks;12/27/2015, p1
SOURCE TYPE
Academic Journal
DOC. TYPE
Article
ABSTRACT
The paper introduces a method which improves localization accuracy of the signal strength fingerprinting approach. According to the proposed method, entire localization area is divided into regions by clustering the fingerprint database. For each region a prototype of the received signal strength is determined and a dedicated artificial neural network (ANN) is trained by using only those fingerprints that belong to this region (cluster). Final estimation of the location is obtained by fusion of the coordinates delivered by selected ANNs. Sensor nodes have to store only the signal strength prototypes and synaptic weights of the ANNs in order to estimate their locations. This approach significantly reduces the amount of memory required to store a received signal strength map. Various ANN topologies were considered in this study. Improvement of the localization accuracy as well as speedup of learning process was achieved by employing fully connected neural networks. The proposed method was verified and compared against state-of-the-art localization approaches in real world indoor environment by using both stationary and mobile sensor nodes.
ACCESSION #
111961628

 

Related Articles

  • Analysis of Some Feedforward Artificial Neural Network Training Algorithms for Developing Localization Framework in Wireless Sensor Networks. Payal, Ashish; Rai, C.; Reddy, B. // Wireless Personal Communications;Jun2015, Vol. 82 Issue 4, p2519 

    Wireless sensor networks (WSNs) have gained global attention of both, the research community and various application users. Localisation in WSN plays a crucial role in implementing myriad of applications such as healthcare management, disaster management, environment management, and agriculture...

  • Improved Correction Localization Algorithm Based on Wave Direction Spectrum for Underwater Wireless Sensor Networks. Zhang Ming; Zhang Jinxue // Sensors & Transducers (1726-5479);Sep2014, Vol. 179 Issue 9, p7 

    Localization is an important topic in the underwater wireless sensor networks (UWSN) because sensor nodes are randomly scattered over a region and can get connected into a network on their own. In this paper, we proposed an improved correction localization algorithm based on wave direction...

  • GPS-free and Anchor-free Indoor Localization for Wireless Sensor Networks. Yuanfang Chen; Mingchu Li; Weifeng Sun; Lei Shu; Xuemin Cheng // International Journal of Advancements in Computing Technology;Sep2012, Vol. 4 Issue 16, p64 

    In wireless sensor networks (WSNs), many applications require location awareness. GPS is generally not suitable to establish indoor locations. In this paper, we propose a GPS-free and Anchor-free (GFAF) indoor localization algorithm. GFAF algorithm uses a mobile node to move according to a...

  • Channel-Aware Adaptive Quantization Method for Source Localization in Wireless Sensor Networks. Liu, Guiyun; Yao, Jing; Liu, Yonggui; Chen, Hongbin; Tang, Dong // International Journal of Distributed Sensor Networks;10/4/2015, Vol. 2015, p1 

    This paper considers the problem of source localization using quantized observations in wireless sensor networks where, due to bandwidth constraint, each sensor’s observation is usually quantized into one bit of information. First, a channel-aware adaptive quantization scheme for target...

  • Localization Scheme for Wireless Sensor Networks Based on "Shortcut" Constraint. NAN JIANG; XIANG XIAO; LING FENG LIU // Adhoc & Sensor Wireless Networks;2015, Vol. 26 Issue 1-4, p1 

    Adding a Tew shortcuts to a wireless sensor network can construct a small-world network, which not only reduces the average energy expenditure per sensor node, but also the non-uniformity energy expenditure across the nodes. Localization still is a fundamental and essential issue lor the...

  • An Eliminating Method to Improve Localization Accuracy. Liangyin Chen; Bingshu Yan; Junjun He; Jingyu Zhang; Wen Chen; Yushi Jiang; Yan Liu; Qian Luo; Baoqiu Wang // International Journal of Distributed Sensor Networks;2014, p1 

    Node localization is essential in wireless sensor networks (WSNs). However, due to limited node energy and overhead network, node localization faces many challenges in WSNs. In addition, it is difficult to meet the requirement of localization accuracy and energy consumption at the same time in...

  • A GPS-less Framework for Localization and Coverage Maintenance in Wireless Sensor Networks. Mahjri, Imen; Dhraief, Amine; Belghith, Abdelfettah; Drira, Khalil; Mathkour, Hassan // KSII Transactions on Internet & Information Systems;Jan2016, Vol. 10 Issue 1, p96 

    Sensing coverage is a fundamental issue for Wireless Sensor Networks (WSNs). Several coverage configuration protocols have been developed; most of them presume the availability of precise knowledge about each node location via GPS receivers. However, equipping each sensor node with a GPS is very...

  • Improving Localization in Wireless Sensor Network Using Fixed and Mobile Guide Nodes. Ahmadi, R.; Ekbatanifard, G.; Jahangiry, A.; Kordlar, M. // Journal of Sensors;10/24/2016, p1 

    Wireless sensor network contains very large number of tiny sensors; some nodes with known position are recognized as guide nodes. Other nodes with unknown position are localized by guide nodes. This article uses the combination of fixed and mobile guide nodes in wireless network localization. So...

  • Indoor localization algorithm using clustering on signal and coordination pattern. Cheng, Chen-Yang // Annals of Operations Research;May2014, Vol. 216 Issue 1, p83 

    In recent years, the demand for indoor location-based services has gradually received greater attention. The presence of multipath interference has a tendency to interfere with traditional algorithms calculated based on received signal strength (RSS). The application of virtual tags can greatly...

Share

Read the Article

Courtesy of THE LIBRARY OF VIRGINIA

Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics