College of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, China.
Gansu Province Internet of Things Engineering Research Center, Lanzhou 730070, China.
Sensors (Basel). 2020 Aug 17;20(16):4607. doi: 10.3390/s20164607.
Human identity recognition has a wide range of application scenarios and a large number of application requirements. In recent years, the technology of collecting human biometrics through sensors for identification has become mature, but this kind of method needs additional equipment as assistance, which cannot be well applied to some scenarios. Using Wi-Fi for identity recognition has many advantages, such as no additional equipment as assistance, not affected by temperature, humidity, weather, light, and so on, so it has become a hot topic of research. The methods of individual identity recognition have been more mature; for example, gait information can be extracted as features. However, it is difficult to identify small-scale (2-5) group personnel at one time, and the tasks of fingerprint storage and classification are complex. In order to solve this problem, this paper proposed a method of using the random forest as a fingerprint database classifier. The method is divided into two stages: the offline stage trains the random forest classifier through the collected training data set. In the online phase, the real-time data collected are input into the classifier to get the results. When extracting channel state information (CSI) features, multiple people are regarded as a whole to reduce the difficulty of feature selection. The use of random forest classifier in classification can give full play to the advantages of random forest, which can deal with a large number of multi-dimensional data and is easy to generalize. Experiments showed that WiGId has good recognition performance in both LOS (line of sight) and N LOS (None line of sight) environments.
人类身份识别具有广泛的应用场景和大量的应用需求。近年来，通过传感器采集人体生物特征进行识别的技术已经成熟，但这种方法需要额外的设备作为辅助，无法很好地应用于某些场景。利用 Wi-Fi 进行身份识别具有许多优势，例如无需额外的设备作为辅助，不受温度、湿度、天气、光线等因素的影响，因此成为研究的热点。个体身份识别的方法已经比较成熟；例如，可以提取步态信息作为特征。但是，同时识别小规模（2-5 人）群体人员比较困难，并且指纹的存储和分类任务复杂。为了解决这个问题，本文提出了一种使用随机森林作为指纹数据库分类器的方法。该方法分为两个阶段：离线阶段通过收集的训练数据集训练随机森林分类器。在线阶段，将实时采集到的实际数据输入到分类器中，以获得结果。在提取信道状态信息 (CSI) 特征时，将多个人视为一个整体，以降低特征选择的难度。在分类中使用随机森林分类器可以充分发挥随机森林的优势，可以处理大量多维数据，并且易于推广。实验表明，WiGId 在 LOS（视距）和 N LOS（非视距）环境下均具有良好的识别性能。
