Location Determination in Indoor Environment based on RSS Fingerprinting and Artificial Neural Network

Stella, Maja; Russo, Mladen; Begušić, Dinko

doi:10.1109/contel.2007.381886

Cited by 42 publications

(26 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast to the more common fingerprint applications for User Equipment (UE) positioning (e.g. [9], [10], [11], [12], [13], [14], [15] and [16]), this paper focuses on the identification of cell areas. The cell fingerprints are solely based on the Received Signal Strength (RSS) of the neighbor cells as measured by the UE.…”

Section: Introductionmentioning

confidence: 99%

Cell Identification based on Received Signal Strength Fingerprints: Concept and Application towards Energy Saving in Cellular Networks

Roth-Mandutz¹,

Mwanje²,

Mitschele‐Thiel³

2014

ICST Trans Mobile Comm Appl

View full text Add to dashboard Cite

The increasing deployment of small cells aimed at off-loading data traffic from macrocells in heterogeneous networks has resulted in a drastic increase in energy consumption in cellular networks. Energy consumption can be optimized in a selforganized way by adapting the number of active cells in response to the current traffic demand. In this paper we concentrate on the complex problem of how to identify small cells to be reactivated in situations where multiple cells are concurrently inactive. Solely based on the received signal strength, we present cell-specific patterns for the generation of unique cell fingerprints. The cell fingerprints of the deactivated cells are matched with measurements from a high data rate demanding mobile device to identify the most appropriate candidate. Our scheme results in a matching success rate of up to 100% to identify the best cell depending on the number of cells to be activated.

show abstract

Section: Introductionmentioning

confidence: 99%

Cell Identification based on Received Signal Strength Fingerprints: Concept and Application towards Energy Saving in Cellular Networks

Roth-Mandutz¹,

Mwanje²,

Mitschele‐Thiel³

2014

ICST Trans Mobile Comm Appl

View full text Add to dashboard Cite

show abstract

“…Nowadays Artificial Neural Networks has gained attention as a fast, flexible, efficient and accurate tool in the areas of simulation, design, modeling and optimization. Input-output relationship is developed between the RSSI and LQI parameters as the inputs to the Artificial Neural Networks and location coordinates of the sensors as outputs to predict the location of a mobile sensor in an indoor environment [2,16,22].…”

Section: Introductionmentioning

confidence: 99%

Neural-based approach for localization of sensors in indoor environment

et al. 2009

View full text Add to dashboard Cite

Location of wireless sensor nodes is an important piece of information for many applications. There are many algorithms present in literature based on Received Signal Strength (RSSI) to estimate the location. However the radio signal propagation is easily influenced by diffraction, reflection and scattering. Therefore algorithms purely based on RSSI may not accurately predict the position of the node.In the present work, an algorithm for estimating the position of mobile nodes is proposed which is based on a combination of Received Signal Strength (RSSI) and Link Quality Indicator (LQI). Artificial Neural Networks are used to establish the relationship between the location of the mobile node and the experimentally obtained values of RSSI and LQI. Two different algorithms namely, Bayesian Regularization and Gradient Descent are used to develop the neural network model. Proposed algorithms improve the localization accuracy and perform better than other state-of-the-art algorithms.

show abstract

“…In reality, the value of can be slightly different depending on which data point is used in (17). Averaging over all obtained from support vectors may improve robustness.…”

Section: Complete Formulationmentioning

confidence: 99%

“…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

Location Determination in Indoor Environment based on RSS Fingerprinting and Artificial Neural Network

Cited by 42 publications

References 10 publications

Cell Identification based on Received Signal Strength Fingerprints: Concept and Application towards Energy Saving in Cellular Networks

Cell Identification based on Received Signal Strength Fingerprints: Concept and Application towards Energy Saving in Cellular Networks

Neural-based approach for localization of sensors in indoor environment

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

Contact Info

Product

Resources

About