@inproceedings{47c43c3133b548ecbab33e6069fc1c64,
title = "Generative adversarial networks for increasing the veracity of big data",
abstract = "This work describes how automated data generation integrates in a big data pipeline. A lack of veracity in big data can cause models that are inaccurate, or biased by trends in the training data. This can lead to issues as a pipeline matures that are difficult to overcome. This work describes the use of a Generative Adversarial Network to generate sketch data, such as those that might be used in a human verification task. These generated sketches are verified as recognizable using a crowd-sourcing methodology, and finds that the generated sketches were correctly recognized 43.8\% of the time, in contrast to human drawn sketches which were 87.7\% accurate. This method is scalable and can be used to generate realistic data in many domains and bootstrap a dataset used for training a model prior to deployment.",
author = "Dering, \{Matthew L.\} and Tucker, \{Conrad S.\}",
year = "2017",
month = jul,
day = "1",
doi = "10.1109/BigData.2017.8258219",
language = "English (US)",
series = "Proceedings - 2017 IEEE International Conference on Big Data, Big Data 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "2595--2602",
editor = "Jian-Yun Nie and Zoran Obradovic and Toyotaro Suzumura and Rumi Ghosh and Raghunath Nambiar and Chonggang Wang and Hui Zang and Ricardo Baeza-Yates and Ricardo Baeza-Yates and Xiaohua Hu and Jeremy Kepner and Alfredo Cuzzocrea and Jian Tang and Masashi Toyoda",
booktitle = "Proceedings - 2017 IEEE International Conference on Big Data, Big Data 2017",
address = "United States",
note = "5th IEEE International Conference on Big Data, Big Data 2017 ; Conference date: 11-12-2017 Through 14-12-2017",
}