In-building Localization using Neural Networks

Ahmad, Uzair; Gavrilov, A. V.; NASİR, Usama; Iqbal, M.J.; Cho, Seong Jin; Lee, Sungyoung

doi:10.1109/iceis.2006.1703135

Cited by 48 publications

(29 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, this simplicity of implementation is acquired at the cost of relatively poor accuracy of location estimates [10]. Many authors have also investigated the use of ANNs for indoor localization, see for example [14], [15], [16], [17], and [18]. In [14] the authors have used an ANN along with TOA and AOA methods to reduce location estimation errors in non-lineof-sight (NLOS) scenarios.…”

Section: Introductionmentioning

confidence: 99%

“…This work revisits the localization performance of the modular MLP-ANN approach of [18], and also proposes alternative low-complexity approaches to handle missing APs in the online stage. In contrast to [18], our localization evaluations show that only one hidden layer in the ANN is sufficient to achieve good accuracy.…”

Section: Introductionmentioning

confidence: 99%

“…However, details of the chosen ANN parameters were not provided and the authors did not discuss how to handle the case of missing APs in the online phase; such a scenario may arise when RSS values from certain APs are available in the offline phase but are not received in online stage due to severe fading. In [18] an ANN with fingerprinting approach has been investigated and the authors propose a modular MLP-ANN approach to handle the problem of missing APs in online stage. The authors select an ANN architecture with two hidden layers that can result in increased complexity.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Wlan–Based Indoor Localization Using Neural Networks

Saleem

Wyne

2016

Journal of Electrical Engineering

View full text Add to dashboard Cite

Wireless indoor localization has generated recent research interest due to its numerous applications. This work investigates Wi-Fi based indoor localization using two variants of the fingerprinting approach. Specifically, we study the application of an artificial neural network (ANN) for implementing the fingerprinting approach and compare its localization performance with a probabilistic fingerprinting method that is based on maximum likelihood estimation (MLE) of the user location. We incorporate spatial correlation of fading into our investigations, which is often neglected in simulation studies and leads to erroneous location estimates. The localization performance is quantified in terms of accuracy, precision, robustness, and complexity. Multiple methods for handling the case of missing APs in online stage are investigated. Our results indicate that ANN-based fingerprinting outperforms the probabilistic approach for all performance metrics considered in this work.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Wlan–Based Indoor Localization Using Neural Networks

Saleem

Wyne

2016

Journal of Electrical Engineering

View full text Add to dashboard Cite

show abstract

“…The standard SVR learning [13,14], manifold learning [15], and neural network learning [16,17] can be employed to obtain precise estimate of the location. However, all these methods require a large amount of the labeled training data for high accuracy.…”

Section: Introductionmentioning

confidence: 99%

Semisupervised Location Awareness in Wireless Sensor Networks Using Laplacian Support Vector Regression

Yoo

Kim

2014

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

Supervised machine learning has been widely used in context-aware wireless sensor networks (WSNs) to discover context descriptions from sensor data. However, collecting a lot of labeled training data in order to guarantee good performance requires much cost and time. For this reason, the semisupervised learning has been recently developed due to its superior performance despite using only a small amount of the labeled data. In this paper, we extend the standard support vector regression (SVR) to the semisupervised SVR by employing manifold regularization, which we call Laplacian SVR (LapSVR). The LapSVR is compared with the standard SVR and the semisupervised least square algorithm that is another recently developed semisupervised regression algorithm. The algorithms are evaluated for location awareness of multiple mobile robots in a WSN. The experimental results show that the proposed algorithm yields more accurate location estimates than the other algorithms.

show abstract

“…Subject to the power map obtained through the field measurements (Morwlli et al, 2006), the position of a moving user can be estimated and tracked by using the particle filtering that implemented an irregular sampling of a posterior probability space for lower computational power required. An artificial neural network based work with the supervised learning strategy to reduce the localization error caused by the interference, reflection and other unexpected interruption is presented in (Battiti et al, 2002;Ocana et al, 2005;Ahmad et al, 2006;Ivan & Branka, 2005). During the offline phase, RSSI and the corresponding location coordinates are adopted as the inputs and the targets for the training purpose.…”

Section: Introductionmentioning

confidence: 99%