Milos Borenovic

Positioning in WLAN environment by use of artificial neural networks and space partitioning

Short range wireless technologies such as wireless local area network (WLAN), Bluetooth, radio frequency identification, ultrasound and Infrared Data Association can be used to supply position information in indoor environments where their infrastructure is deployed. Due to the ubiquitous presence of WLAN networks, positioning techniques in these environments are the scope of intense research. In this paper, the position determination by the use of artificial neural networks (ANNs) is explored. The single ANN multilayer feedforward structure and a novel positioning technique based on cascade-connected ANNs and space partitioning are presented. The proposed techniques are thoroughly investigated on a real WLAN network. Also, an in-depth comparison with other well-known techniques is shown. Positioning with a single ANN has shown good results. Moreover, when utilising space partitioning with the cascade-connected ANNs, the median error is further reduced for as much as 28%.

Space partitioning strategies for indoor WLAN positioning with cascade-connected ANN structures

Position information in indoor environments can be procured using diverse approaches. Due to the ubiquitous presence of WLAN networks, positioning techniques in these environments are the scope of intense research. This paper explores two strategies for space partitioning when utilizing cascade-connected Artificial Neural Networks (ANNs) structures for indoor WLAN positioning. A set of cascade-connected ANN structures with different space partitioning strategies are compared mutually and to the single ANN structure. The benefits of using cascade-connected ANNs structures are shown and discussed in terms of the size of the environment, number of subspaces and partitioning strategy. The optimal cascade-connected ANN structures with space partitioning show up to 50% decrease in median error and up to 12% decrease in the average error with respect to the single ANN model. Finally, the single ANN and the optimal cascade-connected ANN model are compared against other well-known positioning techniques.

Utilizing artificial neural networks for WLAN positioning

Short range wireless technologies such as WLAN, Bluetooth, RFID, ultrasound and IrDA can be used to supply location information in indoor areas in which their coverage is assured. With respect to outdoor techniques, these technologies are more accurate but with smaller covering areas. In this paper, we present the comparison of the existing location techniques in WLAN networks and a novel approach of utilizing artificial neural networks for positioning purposes. In addition to estimating WLAN clients position, neural networks have been employed to estimate the room and type of the room the client resides in. Extensive measurements were conducted to evaluate these approaches and the obtained results indicate performances sufficient for real case use.

Multi-system-multi-operator localization in PLMN using neural networks

Providing the localization algorithm for context-aware services is the focus of many studies. This paper explores the properties of positioning models based on received signal strength (RSS) in PLMN (Public Land Mobile Network) networks. The effects of using the RSS at a mobile terminal from various systems, such as GSM and UMTS, as well as from multiple operators, have been investigated and discussed. Twenty-two models, based on artificial neural networks, have been developed and verified using the data from an immense measurement campaign. The obtained results show that augmenting the model with additional RSS data, even from systems with poor radio-visibility, may improve the positioning accuracy to as much as a 35thinspacem median distance error in a light urban environment. The degradation of accuracy in indoor environments and the complexity and latency of the models were also scrutinized. Copyright

Vehicle Positioning Using GSM and Cascade-Connected ANN Structures

Procuring location information for intelligent transportation systems is a popular topic among researchers. This paper investigates the vehicle location algorithm based on the received signal strength (RSS) from available Global System for Mobile Communications (GSM) networks. The performances of positioning models, which consisted of cascade-connected (C-C) artificial neural network (ANN) multilayer feedforward structures employing the space-partitioning principle, are compared with the single-ANN multilayer feedforward model in terms of accuracy, the number of subspaces, and other positioning relevant parameters. C-C ANN structures make use of the fact that a vehicle can be found only in a subspace of the entire environment (roads) to improve the positioning accuracy. The best-performing C-C ANN structure achieved an average error of 26 m and a median error of less than 5 m, which is accurate enough for most of the vehicle location services. Using the same RSS database obtained by measurements, it was shown that the proposed model outperforms kNN and extended Kalman filter (EKF)-trained ANN positioning algorithms. Moreover, the presented ANN structures replace not only the positioning algorithms but the overloaded map-matching process as well.

Comparative analysis of RSSI, SNR and Noise level parameters applicability for WLAN positioning purposes

In this paper, the extensive experimental analysis of RSSI, SNR and Noise level parameters usefulness for WLAN positioning purposes was conducted. Four positioning models, based on artificial neural networks, with RSSI, SNR, Noise level and both RSSI and SNR as networks inputs, were created, trained and verified. The obtained results have shown that, contrary to the common knowledge, SNR parameter is equally suitable for WLAN positioning purposes as RSSI parameter. In addition, the obtained results pointed out that the space distribution of the noise level parameter contains less location dependant information than RSSI or SNR.

Positioning in Indoor Mobile Systems

At present times people travel far greater distances on daily bases than our not so distanced ancestors had travelled in their lifetimes. Technological revolution had brought human race in an excited state and steered it towards globalization. Nevertheless, the process of globalization is not all about new and faster means of transportation or about people covering superior distances. Immense amount of information, ubiquitous and easily accessible, formulate the essence of this process. Consequently, ways through which the information flows are getting too saturated for free usage so, for example, frequency spectrum had become a vital natural resource with a price tagged on its lease. However, the price of not having the information is usually much higher. By employing various wireless technologies we are trying to make the most efficient use of frequency spectrum. These new technologies have brought along the inherent habit of users to be able to exchange information regardless of their whereabouts. Higher uncertainty of the user’s position has produced increase in the amount of information contained in its position. As a result, services built on the location awareness capabilities of the mobile devices and/or networks, usually referred to as Location Based Services (LBS, also referred to as LoCation Services – LCS), have been created. Example of services using the mobile location can be: location of emergency calls, mobile yellow pages, tracking and monitoring, location sensitive billing, commercials, etc. With the development of these services, more efforts are being pushed into producing the maximum of location-dependent information from a wireless technology. Simply, greater the amount of information available – more accurate the location estimate is. Whereas in outdoor environment the satellite-based positioning techniques, such as the Global Positioning System (GPS), have considerable advantages in terms of accuracy, the problem of position determination in an indoor environment is much farther from having a unique solution. Cellular-based, Computer vision, IrDA (Infrared Data Association), ultrasound, satellite-based (Indoor GPS) and RF (Radio Frequency) systems can be used to

Cascade-connected ANN structures for indoor WLAN positioning

Various radio systems can be used to obtain the position information in indoor environments. Due to the ubiquitous presence of WLAN networks, positioning techniques in these environments are the scope of intense research. This paper explores the properties of cascade-connected Artificial Neural Networks (ANNs) structures. Several cascade-connected ANN structures with space partitioning are compared to the single ANN multilayer feedforward structure. The benefits of using cascade-connected ANNs structures are shown and discussed in terms of the size of the environment and subspaces. The optimal cascade-connected ANN structure with space partitioning shows a 41% decrease in median error with respect to the single ANN model.

ANN based models for positioning in indoor WLAN environments

Position information in indoor environments can be procured using diverse approaches. Due to the ubiquitous presence of WLAN networks, positioning techniques in these environments are the scope of intense research. This paper explores models based on Artificial Neural Networks (ANNs): single ANN positioning models using RSSI, SNR and N values as inputs, and a range of cascade-connected ANN positioning models, utilizing various space-partitioning patterns. The benefits from using cascade-connected ANN structures are shown and discussed. The optimal cascade-connected ANN structure with space partitioning shows 41% decrease in median error and 12% decrease in the average error with respect to the best-performing single ANN model.

Impact of varying reference points density on performances of fingerprinting based GSM positioning system

Procuring the location information using mobile radio systems is a popular topic amongst researchers. This paper investigates the impact of reference points density on performances of fingerprinting based GSM positioning system. The neural networks based model, was trained with a varying volume of the training set. Having in mind the accuracy and the time consumption for model generation, it was shown that, for optimal performances, the adjacent reference points ought to be 4m to 6m apart.