论文标题
援引深度学习以估算室内LIFI用户位置和方向
Invoking Deep Learning for Joint Estimation of Indoor LiFi User Position and Orientation
论文作者
论文摘要
光照（LIFI）是一种完整的双向光学无线通信（OWC），被认为是高速室内连通性的有前途的解决方案。与常规射频无线系统不同，OWC通道不是各向同性的，这意味着设备方向会显着影响通道的增益。但是，由于缺乏LIFI系统的适当渠道模型，许多研究认为接收器是垂直向上的，并且随机位于覆盖区域内，从实际的角度来看，这不是现实的假设。在本文中，提出了针对室内LIFI系统的新型现实和基于测量的通道模型。确切地说，对于随机定向的固定和移动LIFI接收器的情况，渠道增益的统计数据是得出的。对于固定用户，提出了两个通道模型，即修改后的截短拉普拉斯（MTL）模型和修改后的β（MB）模型。对于LIFI用户，提出了两个通道模型，即修改后的高斯（SMTG）模型的总和和修改后的beta（SMB）模型的总和。根据派生模型，研究了LIFI用户的随机取向和空间分布的影响，我们表明上述因素可以强烈影响渠道增益和系统性能。
Light-fidelity (LiFi) is a fully-networked bidirectional optical wireless communication (OWC) that is considered a promising solution for high-speed indoor connectivity. Unlike in conventional radio frequency wireless systems, the OWC channel is not isotropic, meaning that the device orientation affects the channel gain significantly. However, due to the lack of proper channel models for LiFi systems, many studies have assumed that the receiver is vertically upward and randomly located within the coverage area, which is not a realistic assumption from a practical point of view. In this paper, novel realistic and measurement-based channel models for indoor LiFi systems are proposed. Precisely, the statistics of the channel gain are derived for the case of randomly oriented stationary and mobile LiFi receivers. For stationary users, two channel models are proposed, namely, the modified truncated Laplace (MTL) model and the modified Beta (MB) model. For LiFi users, two channel models are proposed, namely, the sum of modified truncated Gaussian (SMTG) model and the sum of modified Beta (SMB) model. Based on the derived models, the impact of random orientation and spatial distribution of LiFi users is investigated, where we show that the aforementioned factors can strongly affect the channel gain and system performance.
