The ability to predict the arrival and residence time of mobile users at a particular place is essential for the development of a wealth of new applications and services, such as smart heating control, transportation planning or urban navigation. Previous techniques based on probabilistic models have not been able to perform such prediction accurately. In this paper, we present two linear mobility models, namely Linear Regression, and Auto-Regression, to predict the temporal behavior, particularly the residence time, of individual users. We run performance evaluation experiments on two different WiFi mobility traces datasets made available through the CRAWDAD project. Our results show that using linear regression-based learning algorithms significantly improve the residence time prediction accuracy compared to state-of-the-art methods, and achieve prediction errors in the order of seconds and minutes for a large number of users.

预测移动用户在特定位置到达和停留时间的能力对于开发大量新应用和服务（例如智能供暖控制，交通规划或城市导航）至关重要。基于概率模型的先前技术无法准确地执行这种预测。在本文中，我们提出了两个线性移动性模型，即线性回归和自回归，以预测各个用户的时间行为，尤其是停留时间。我们对通过CRAWDAD项目提供的两个不同的WiFi移动轨迹数据集进行了性能评估实验。我们的结果表明，与最先进的方法相比，使用基于线性回归的学习算法可显着提高停留时间的预测准确性，