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.