A Fast and Resource Efficient Method for Indoor Positioning Using Received Signal Strength
IEEE Transactions on Vehicular Technology
Indoor localization, received signal strength, support vector machines (SVMs), undersampling, wireless local area network (WLAN)
This paper proposes an indoor localization method using online independent support vector machine (OISVM) classification method and undersampling techniques. The system is based on the received signal strength indicator (RSSI) of Wi-Fi signals. A new undersampling algorithm is developed to address the imbalanced data problem associated with the OISVM, and a kernel function parameter selection algorithm is introduced for the training process. The time complexity of both the training process and the prediction process are significantly decreased. Comparative experimental results indicate that the training speed and the prediction speed are improved by at least ten and five times, respectively. Furthermore, through online learning, the estimation error is decreased by 0.8 m. Such an improvement makes the proposed method an ideal indoor positioning solution for portable devices for which the processing power and the memory are limited.
Wu, Zheng; Fu, Kechang; Jedari, Esrafil; Shuvra, Shaeera Rabbanee; Rashidzadeh, Rashid; and Saif, Mehrdad. (2016). A Fast and Resource Efficient Method for Indoor Positioning Using Received Signal Strength. IEEE Transactions on Vehicular Technology, 65 (12), 9747-9758.