Knowledge Commons of Institute of Automation,CAS
An Online Anomaly Learning and Forecasting Model for Large-Scale Service of Internet of Thing | |
Wang JP(王军平); JUNPING WANG | |
2014-10 | |
会议名称 | International Conference on Identification, Information & Knowledge in the Internet of Things |
会议录名称 | International Conference on Identification, Information & Knowledge in the Internet of Things |
会议日期 | 2014-10-17 |
会议地点 | BEIJING |
摘要 | The online anomaly detection has been propounded as the key idea of monitoring fault of large-scale sensor nodes in Internet of Things. Now the exciting progresses of research have been made in online anomaly detection area. However, the highly dynamic distributing character of Internet of Things makes the anomaly detection scheme difficult to be used in online manner. This paper presents a new online anomaly learning and detection mechanism for large-scale service of Internet of Thing. Firstly, our model uses the reversible-jump MCMC learning to online learn anomaly-free of dynamics network and service data. Next, we perform a structural analysis of IoT-based service topology by Network Utility Maximization (NUM) theory. The results of experiment demonstrate the method accuracy in forecasting dynamics network and service structures from synthetic data. |
关键词 | Internet Of Things Service Delivery Online Anomaly Learning And Detection |
收录类别 | EI |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/12343 |
专题 | 多模态人工智能系统全国重点实验室_人工智能与机器学习(杨雪冰)-技术团队 |
通讯作者 | JUNPING WANG |
推荐引用方式 GB/T 7714 | Wang JP,JUNPING WANG. An Online Anomaly Learning and Forecasting Model for Large-Scale Service of Internet of Thing[C],2014. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
An Online Anomaly Le(220KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
个性服务 |
推荐该条目 |
保存到收藏夹 |
查看访问统计 |
导出为Endnote文件 |
谷歌学术 |
谷歌学术中相似的文章 |
[Wang JP(王军平)]的文章 |
[JUNPING WANG]的文章 |
百度学术 |
百度学术中相似的文章 |
[Wang JP(王军平)]的文章 |
[JUNPING WANG]的文章 |
必应学术 |
必应学术中相似的文章 |
[Wang JP(王军平)]的文章 |
[JUNPING WANG]的文章 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论