TY - JOUR A2 - Zhao, Liang AU - Liu, Desheng AU - Zhen, Hang AU - Kong, Dequan AU - Chen, Xiaowei AU - Zhang, Lei AU - Yuan, Mingrun AU - Wang, Hui PY - 2021 DA - 2021/01/31 TI - Sensors Anomaly Detection of Industrial Internet of Things Based on Isolated Forest Algorithm and Data Compression SP - 6699313 VL - 2021 AB - Aiming at solving network delay caused by large chunks of data in industrial Internet of Things, a data compression algorithm based on edge computing is creatively put forward in this paper.传感器收集的数据需要预处理,然后用不同单包量K和差错阈e处理多组比较实验,这将大大降低数据传输量,前提是确保数据瞬时性有效基于压缩处理,提议基于隔离林的异常检测算法,可精确识别渐进变化和突发变化引起的异常值并控制并调整设备动作,以便满足控制需求实验模拟显示,隔离森林算法基于分区偏差框图和K值集群算法基于异常检测距离验证前者在数据压缩和检测精度方面的可行性和长处SN-1058-9244UR-https://doi.org/101155/2021/669313DO-10.1155/2021/669313JF-科学编程PB-HindawiKW-ER