We illustrate our methodology and its improvement over existing GAN anomaly detection on the MNIST dataset. Published in: 2018 IEEE International Conference on ...

Abstract—Detecting anomalies and outliers in data has a number of applications including hazard sensing, fraud detection, and systems management.

For this purpose we introduce an infinite Gaussian mixture model coupled with (bi-directional) generative adversarial networks, IGMM-GAN, that facilitates ...

An infinite Gaussian mixture model coupled with (bi-directional) generative adversarial networks, IGMM-GAN, that facilitates multimodal anomaly detection ...

Previous studies on anomaly detection in GPS trajectory data have focused both on the detection of city-wide traffic events and determining abnormal driving ...

Gray, Kathryn, Smolyak, Daniel, Badirli, Sarkhan, and Mohler, George. "Coupled IGMM-GANs for improved generative adversarial anomaly detection". 2018 IEEE ...

Sep 8, 2018 · We illustrate our methodology and its improvement over existing GAN anomaly detection on several human mobility datasets, along with MNIST.

... These methods aim to learn patterns and detect outlier trajectories without the demands for pre-labeled data. Gray et al. [19] proposed a GAN-based model to ...

Jun 3, 2020 · Coupled IGMM-GANs for improved generative adversarial anomaly detection. In Proceedings of the 2018 IEEE International Conference on Big ...

Kathryn Gray, Daniel Smolyak, Sarkhan Badirli, George O. Mohler: Coupled IGMM-GANs for improved generative adversarial anomaly detection.