基于多传感器信息融合的用户认证方法

发布时间：2018-06-28 09:44

本文选题：测量 + 传感器　；参考：《激光与光电子学进展》2017年07期

【摘要】：为了保证智能手机的信息安全,提出一种多传感器信息融合的手机用户身份认证方法。首先从手机用户操作手势的姿态角变化、运动幅度以及旋转程度等方面提取信号特征,然后分别以三类单特征的动态时间规整识别结果作为独立证据构造基本概率分配函数,进而采用Dempster/Shafer证据理论对其进行融合。为缓解证据间出现的冲突,避免其影响融合效果,引入加权证据方法。通过计算各证据之间的相似性来衡量证据间的冲突程度进而确定各证据的可信度,并且对各证据进行加权修正以降低可信度小的证据对融合结果的影响,最后根据融合结果做出决策。仿真结果表明,该算法性能优于对比算法,能有效对手机用户进行身份识别。
[Abstract]:In order to ensure the information security of smart phone, a mobile phone user identity authentication method based on multi-sensor information fusion is proposed. Firstly, the signal features are extracted from the change of attitude angle, the amplitude of motion and the degree of rotation of the mobile phone user's gesture, and then the dynamic time warping recognition results of three kinds of single features are used as independent evidence to construct the basic probability distribution function. Then Dempster / Shafer evidence theory is used to fuse it. In order to alleviate the conflict between the evidence and avoid its influence on the fusion effect, the weighted evidence method is introduced. The degree of conflict between evidence is measured by calculating the similarity of each evidence, and the credibility of each evidence is determined, and the weight of each evidence is revised to reduce the impact of the evidence with less credibility on the fusion result. Finally, the decision is made according to the fusion result. Simulation results show that the performance of the algorithm is better than the contrast algorithm, and it can effectively identify mobile phone users.
【作者单位】：江南大学物联网技术应用教育部工程研究中心;
【基金】：中央高校基本科研业务费用专项资金(JUSRP51510)
【分类号】：TP202;TP212;TP309

【相似文献】