SS-VTCN is designed to capture thenormal patterns of the IoT traffic data based on the distribution whether it is labeled or not by learning their representations with key techniques such as Variational Autoencoders and Temporal Convolutional Network . This network can use the encode data to predict preliminary result, and reconstruct input datato determine anomalies by the representations . This is more suitable than supervised and unsupervised method with better performance when compared to other state-of-art semi-supervised methods, says the authors of the paper . They say it is better suited than supervised methods with better results when compared with other state of-art methods such as unsupervisory methods . The author of the article also suggests that the network can be used to detect multiple anomalies in a real consumer smart home data. For more information, please contact the author of this article by email: http://www.mailonline.com/news/news

Author(s) : Yan Xu, Yongliang Cheng

Links : PDF - Abstract

Code :

https://github.com/oktantod/RoboND-DeepLearning-Project


Coursera

Keywords : methods - supervised - network - data - art -

Leave a Reply

Your email address will not be published. Required fields are marked *