Coupled IGMM-GANs with Applications to Anomaly Detection in Human Mobility Data
Coupled IGMM-GANs with Applications to Anomaly Detection in Human Mobility Data
复制标题
DOI：
10.1145/3385809
复制
发表时间：
2020-06
期刊：
影响因子：
--
通讯作者：
Daniel Smolyak;Kathryn Gray;Sarkhan Badirli;G. Mohler
中科院分区：
文献类型：
--
作者：
Daniel Smolyak;Kathryn Gray;Sarkhan Badirli;G. Mohler
检测人员移动数据中的异常活动具有多种应用，包括道路危险感知、基于远程信息处理的保险以及出租车服务和乘车共享中的欺诈检测。在本文中，我们解决了异常人类轨迹研究中出现的两个挑战：（1）缺乏关于异常定义的地面实况数据；（2）现有方法对重要预处理和特征工程的依赖。尽管生成对抗网络 (GAN) 似乎非常适合解决这些挑战，但我们发现现有的基于 GAN 的异常检测算法由于无法处理多模态模式而表现不佳。为此，我们引入了与（双向）GAN 相结合的无限高斯混合模型（IGMM-GAN），该模型能够生成合成且真实的人体移动数据，同时促进多模态异常检测。通过估计人类轨迹空间上的生成概率密度，我们能够生成真实的合成数据集，可用于对现有异常检测方法进行基准测试。估计的多模态密度还允许我们用于检测异常轨迹的异常值的自然定义。我们展示了我们的方法及其对几个人体移动数据集以及 MNIST 上现有 GAN 异常检测的改进。
Detecting anomalous activity in human mobility data has a number of applications, including road hazard sensing, telematics-based insurance, and fraud detection in taxi services and ride sharing. In this article, we address two challenges that arise in the study of anomalous human trajectories: (1) a lack of ground truth data on what defines an anomaly and (2) the dependence of existing methods on significant pre-processing and feature engineering. Although generative adversarial networks (GANs) seem like a natural fit for addressing these challenges, we find that existing GAN-based anomaly detection algorithms perform poorly due to their inability to handle multimodal patterns. For this purpose, we introduce an infinite Gaussian mixture model coupled with (bidirectional) GANs—IGMM-GAN—that is able to generate synthetic, yet realistic, human mobility data and simultaneously facilitates multimodal anomaly detection. Through the estimation of a generative probability density on the space of human trajectories, we are able to generate realistic synthetic datasets that can be used to benchmark existing anomaly detection methods. The estimated multimodal density also allows for a natural definition of outlier that we use for detecting anomalous trajectories. We illustrate our methodology and its improvement over existing GAN anomaly detection on several human mobility datasets, along with MNIST.