Autoencoder neural network-based abnormal data detection in edge computing enabled large-scale IoT systems

Tianqi YU; Yongxu ZHU; Xianbin WANG

doi:10.11959/j.issn.2096-3750.2018.00076

您当前的位置：

首页 >

文章列表页 >

Autoencoder neural network-based abnormal data detection in edge computing enabled large-scale IoT systems

Theory and Technology | 更新时间：2024-06-05

- Autoencoder neural network-based abnormal data detection in edge computing enabled large-scale IoT systems
- Chinese Journal on Internet of Things Vol. 2, Issue 4, Pages: 14-21(2018)
- 作者机构：
  
  1. 西安大略大学电气与计算机工程学院，安大略伦敦N6A 5B9
  2. 拉夫堡大学沃尔夫森机械、电气与制造工程学院，拉夫伯勒LE11 3TU
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.2096-3750.2018.00076
  CLC： TP319
- Published：30 December 2018，
  
  Published Online：2018-12，
- 稿件说明：
移动端阅览
TIANQI YU, YONGXU ZHU, XIANBIN WANG. Autoencoder neural network-based abnormal data detection in edge computing enabled large-scale IoT systems. [J]. Chinese journal on internet of things, 2018, 2(4): 14-21.
DOI：

TIANQI YU, YONGXU ZHU, XIANBIN WANG. Autoencoder neural network-based abnormal data detection in edge computing enabled large-scale IoT systems. [J]. Chinese journal on internet of things, 2018, 2(4): 14-21. DOI： 10.11959/j.issn.2096-3750.2018.00076.

摘要

物联网以其便于搭建及成本低廉等优点，被广泛地应用于环境监测中。在大规模物联网监测系统中，云平台一直被用作远程的数据和控制中心，然而系统中大量的数据上传和处理给云平台的带宽负载和实时性反馈等方面带来了巨大挑战。因此，提出了基于边缘计算的物联网监测系统框架。边缘计算作为该系统的中间层，能够为终端设备提供实时的本地服务，同时能够通过初步分析分流云平台的计算任务进而降低数据上传量。在此基础上，进一步提出了一种利用自编码神经网络实现的异常检测方法。采用实地采集的海洋气候监测数据进行仿真分析，仿真结果表明，本文提出的基于自编码神经网络的异常检测方法能够充分利用采集数据的空间相关性并准确地检测出异常数据。

Abstract

Given the advantages of low cost and easy deployment

large-scale Internet of things (IoT) has been deployed for environment monitoring pervasively.Within such systems

cloud platform is typically utilized as a remote data and control center.However

tremendous amount of data uploading and processing induce huge challenges on bandwidth load and real-time data gathering.In order to overcome these challenges

edge computing enabled IoT system architecture was proposed for environmental monitoring.As the intermediate layer

local processing could be supported for end devices with low latency and assist with preliminary analysis to offload computational tasks from cloud and the amount of data uploading could be reduced.Based on this system architecture

an autoencoder neural network-based abnormal data detection scheme was developed newly.Performance evaluation has been conducted based on the practical oceanic atmospheric data.Simulation results indicate that the proposed scheme can accurately detect the abnormal data by fully exploiting the spatial data correlation.

关键词

自编码神经网络异常检测边缘计算物联网

Keywords

autoencoder neural networkabnormal data detectionedge computingIoT

references

SHI W, CAO J, ZHANG Q ,et al. Edge computing:vision and challenges[J]. IEEE Internet of Things Journal, 2016,3(5): 637-646.

杨旸, 李凯, 徐海东 ,等. 雾计算赋能机器人同步定位与地图构建[J]. 物联网学报, 2018,2(2): 33-40.

YANG Y, LI K, XU H D ,et al. Fog computing-enabled robot simultaneous localization and mapping[J]. Chinese Journal on Internet of Things, 2018,2(2): 33-40.

ZHANG Y, MERATNIA N, HAVINGA P J M . Outlier detection techniques for wireless sensor networks:a survey[J]. IEEE Communications Surveys and Tutorials, 2010,12(2): 159-170.

BHATIA S K, . Adaptive K-means clustering[C]// AAAI Flairs Conference Menlo Park,CA,USA. 2004: 695-699.

MAHDAVINEJAD M S, REZVAN M, BAREKATAIN M ,et al. Machine learning for Internet of things data analysis:a survey[J]. Digital Communications Networks, 2018,4(3): 161-175.

SEZER O B, DOGDU E, OZBAYOGLU A M . Context-aware computing,learning and big data in Internet of things:a survey[J]. IEEE Internet of Things Journal, 2018,5(1): 1-27.

ZHU Q, SHI B, YANG F ,et al. Task offloading decision in fog computing system[J]. China Communications, 2017,14(11): 59-68.

NOVO O . Blockchain meets IoT:an architecture for scalable access management in IoT[J]. IEEE Internet of Things Journal, 2018,5(2): 1184-1195.

FRUSTACI M, PACE P, ALOI G ,et al. Evaluating critical security issues of the IoT world:present and future challenges[J]. IEEE Internet of Things Journal, 2018,5(4): 2483-2495.

Views

1766

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Construction and optimization of a smart classroom system for emotional computing

Collaborative offloading computing scheme based on energy harvesting technology

Edge server deployment decision based on improved NSGA-Ⅱ in the Internet of vehicles edge computing scenario

Design and implementation of low-cost hardware architecture for authentication encryption algorithm SM4-GCM

Research on agricultural IoT pest and disease image recognition algorithm based on STM32

Related Author

HUANG Lijuan

CHENG Zhengyi

YANG Ziyan

WANG Jun

ZHAO Haodong

Sifeng ZHU

Yu WANG

Hao CHEN

Related Institution

Northeast Normal University

University of Electronic Science and Technology of China

Sichuan Tianfu New Area Chengdu Hamilton Luxelakes Primary School

Nanjing University of Posts and Telecommunications

School of Computer, Henan University of Engineering

⁰