Data Stream Classification by Using Stacked CARU Networks

研究成果: Conference contribution同行評審

4 引文 斯高帕斯(Scopus)

摘要

RNN based networks have been widely used in various applications to obtain impressive performance, and CARU has more advantages in NLP tasks. However, the RNN exerts a great pressure on the CARU unit when a single layer is used. In this work, we propose to implement a multi-layer design, which can gradually extract the main features through multiple CARU units. The advantage of this is that it can consider part of speech and content. It allows each layer to perform its work clearly while alleviating long-term dependencies. Using seven popular data streams, the performance of multi-layer CARU is compared and evaluated with many state-of-the-art technologies. Experiments show that our design can improve the classification performance of various data sets. In addition, the design and implementation can be easily deployed in RNN based systems.

原文English
主出版物標題Proceedings - 2022 IEEE International Conference on Big Data and Smart Computing, BigComp 2022
編輯Herwig Unger, Young-Kuk Kim, Eenjun Hwang, Sung-Bae Cho, Stephan Pareigis, Kyamakya Kyandoghere, Young-Guk Ha, Jinho Kim, Atsuyuki Morishima, Christian Wagner, Hyuk-Yoon Kwon, Yang-Sae Moon, Carson Leung
發行者Institute of Electrical and Electronics Engineers Inc.
頁面385-390
頁數6
ISBN(電子)9781665421973
DOIs
出版狀態Published - 2022
事件2022 IEEE International Conference on Big Data and Smart Computing, BigComp 2022 - Daegu, Korea, Republic of
持續時間: 17 1月 202220 1月 2022

出版系列

名字Proceedings - 2022 IEEE International Conference on Big Data and Smart Computing, BigComp 2022

Conference

Conference2022 IEEE International Conference on Big Data and Smart Computing, BigComp 2022
國家/地區Korea, Republic of
城市Daegu
期間17/01/2220/01/22

指紋

深入研究「Data Stream Classification by Using Stacked CARU Networks」主題。共同形成了獨特的指紋。

引用此