The widespread of the 802.11-based wireless LAN technology brings a good opportunity for the development of the indoor positioning system based on 802.11. In this paper, a 802.11-based indoor positioning method using support vector regression (SVR) is presented. The method consists of two periods: offline training period and online location period. The accurate position prediction model is achieved in the offline training period by SVR, and the exact position is determined in the online location period according to the received signal strength (RSS) of the mobile devices. Due to the complex indoor environment, wireless channel congestion, obstructions and limitation of node communication range, the RSS is vulnerable and changeable. To address the above issues, corresponding data filtering rules obtained through statistical analysis are applied in offline training period to improve the quality of training sample, and thus improve the quality of prediction model. In the online location period, k-times continuous measurement is utilized to obtain the high quality input of the received signal strength, which guarantees the consistency with the training samples and improves the position accuracy of mobile devices. Performance evaluation and comprehensive analysis are done through intensive experiments, and the results show that the presented method has a higher positioning accuracy when compared with the probability positioning method and neutral network positioning method, and its demand for the storage capacity and computing power of the mobile devices is also low at the same time.