Cascading artificial neural networks optimized by genetic algorithms and integrated with global navigation satellite system to offer accurate ubiquitous positioning in urban environment

► A GA-optimized cascading ANN based indoor positioning system (IPS) is developed. ► The IPS is integrated with GNSS to provide a ubiquitous positioning in urban environment. ► Optimization using GA increases the cascading ANN’s accuracy and precision. ► The proposed IPS offers better accuracy and precision when compared to other well documented IPSs. ► Ubiquitous positioning system displayed a mean distance error of 3.29m when tested in different environments. Location-based services (LBSs) have long been identified as an important component of emerging mobile services. While outdoor positioning has become strongly established, systems dealing with indoor positioning in urban environment are still under development. The upcoming LBSs require positioning systems (PSs) that are available ubiquitously, which requires the integration of the PS available in an outdoor environment with the PS available in indoor environment. Global navigation satellite systems (GNSSs) such as GPS, GLONASS, Galileo, and QZSS are some of the prominent systems that provide outdoor positioning. Indoor positioning systems (IPSs), however, are undergoing rapid development, and these systems can be supplied using short-range wireless technologies such as Wi-Fi, Bluetooth, RFID, and Infrared. Among these technologies, intense research is being conducted into Wi-Fi-based positioning systems due to their ubiquitous presence. This paper presents a model and results for a ubiquitous positioning system (UPS) that integrates a novel WLAN-based IPS and GNSS. The IPS is developed using cascading artificial neural networks, which are further optimized using genetic algorithms. The systems were thoroughly investigated on an actual Wi-Fi network at Asian Institute of Technology, Thailand. The IPS demonstrated a mean accuracy of 2.10m and the UPS demonstrated a mean accuracy of 3.26m, with 89% of the distance error within the range of 0–3.5m.