GBDT算法在无线非接触式人体行为识别中的应用研究

Application of GBDT algorithm in wireless contactless human behavior recognition

无线非接触式人体行为感知是指利用无线信号的传播特征反推人体行为的过程。由于非接触式感知具有造价低,无需额外设备,可以实现非视距感知等特点,现已成为国内外的研究热点。但是现有的人体行为感知算法需要利用复杂的特征提取技术,使其在嵌入式设备上运行困难。本文针对这一问题,提出了基于GBDT的人体行为感知算法,在不需要复杂的特征提取的基础上实现精准的人体行为感知。试验结果表明,基于GBDT的技术在rRuler数据集上的识别准确度可以达到98%左右,并有利于部署在实际嵌入式设备上。

Wireless device-free human behavior sensing refers to the process of using the propagation characteristics of wireless signals to deduce human behavior. Due to the characteristics of low cost, no additional equipment and non-line-of-sight perception, device-free sensing has become a research hotspot at home and abroad. However, the existing human behavior sensing algorithms need to use complex feature extraction technology, so it is difficult to run on embedded devices. To solve this problem, this paper proposes a human behavior sensing algorithm based on GBDT, which realizes accurate human behavior sensing without complex feature extraction. The experimental results show that the recognition accuracy of the technology based on GBDT on the rRuler data set can reach about 98%, and it is conducive to the deployment on the actual embedded equipment.