Indoor Floor Localization Based on Multi-Intelligent Sensors

Abstract

With the continuous expansion of the market of indoor localization, the requirements of indoor localization technology are becoming higher and higher. Existing indoor floor localization (IFL) systems based on Wi-Fi signal and barometer data are susceptible to external environment changes, resulting in large errors. A method for indoor floor localization using multiple intelligent sensors (MIS-IFL) is proposed to decrease the localization errors, which consists of a fingerprint database construction phase and a floor localization phase. In the fingerprint database construction phase, data acquisition is performed using magnetometer sensor, accelerator sensor and gyro sensor in the smartphone. In the floor localization phase, an active pattern recognition is performed through the collaborative work of multiple intelligent sensors and machine learning classifiers. Then floor localization is performed using magnetic data mapping, Euclidean closest approximation and majority principle. Finally, the inter-floor detection link based on machine learning is added to improve the overall localization accuracy of MIS-IFL. The experimental results show that the performance of the proposed method is superior to the existing IFL.

A Survey of Indoor Localization Systems in Multi-Floor Environments

“…Thus, IMUs are commonly used alongside other technology that can provide absolute localization. IMUs have been widely used in indoor localization in multi-floor environments to provide real-time location estimates as the user moves [180], [181], [199]- [201].…”

“…Due to the natural existence of magnetic fields everywhere and the growing availability of magnetometers in the form of MEMS sensors incorporated in smartphones, magnetic field signals can be used for indoor localization. Magnetism has been used in conjunction with other technologies for indoor localization in multi-floor environments to improve the localization performance [128], [199], [201].…”

“…Furthermore, in the common case of using smartphones in PDR, the sensors' readings might change depending on the user's activity. For instance, actions like making a phone call, phone shaking while walking, and holding the phone with different orientations affect the readings [201]. This is especially apparent in estimating the walking direction as it depends on how the user carries his phone.…”

“…Yu et al [199] proposed fusing BLE as an absolute localization method with PDR based on smartphone IMUs sensors and barometers for altitude information to obtain the 3D location, where the integration is through an adaptive unscented Kalman filter. Zhao et al [201] fused magnetic fingerprinting and IMUs sensor readings for floor localization. Where activity recognition is done using the sensors, then based on the activity, the real-time magnetic data is mapped to the fingerprint, where matching is done using a KNN method.…”