【摘要】：針對目前室內(nèi)指紋定位算法存在實時性差、對動態(tài)環(huán)境適應性不足的問題,提出一種新的基于半監(jiān)督極限學習機的定位算法。該算法首先通過半監(jiān)督極限學習機建立初始化位置估計模型,然后利用新增的半標記數(shù)據(jù)對原定位模型進行動態(tài)調(diào)整,最后為新增訓練數(shù)據(jù)分配合適懲罰權重,使模型具有時效機制。仿真結果表明,該定位算法在保證定位實時性的同時提高了對動態(tài)環(huán)境的適應性。
[Abstract]:A new localization algorithm based on semi-supervised extreme learning machine is proposed to solve the problem that the indoor fingerprint localization algorithm is poor in real time and adaptability to the dynamic environment. The algorithm first establishes the initialization position estimation model by semi-supervised extreme learning machine, then dynamically adjusts the original location model by using the newly added half-mark data, and finally assigns appropriate penalty weight to the new training data. The model has a time-effect mechanism. The simulation results show that the algorithm not only ensures the real time of location, but also improves the adaptability to dynamic environment.
【作者單位】： 江南大學物聯(lián)網(wǎng)工程學院;
【基金】：江蘇省產(chǎn)學研聯(lián)合創(chuàng)新資金前瞻性聯(lián)合研究項目(BY2014023-31) 江蘇省“六大人才高峰”項目(WLW-007)
【分類號】：TN929.5;TP181;TP212.9

【相似文獻】

相關會議論文 前1條

1 單莘;;一種網(wǎng)絡告警的增量式情景規(guī)則挖掘方法[A];中國通信學會第五屆學術年會論文集[C];2008年

，

本文編號：2380151