计算机科学
铰链损耗
离群值
异常检测
有界函数
支持向量机
稳健性(进化)
特征向量
数据挖掘
算法
人工智能
机器学习
模式识别(心理学)
数学
生物化学
基因
数学分析
化学
作者
Imran Razzak,Khurram Zafar,Muhammad Imran,Guandong Xu
标识
DOI:10.1016/j.future.2020.05.045
摘要
Exponential growth of large scale data industrial internet of things is evident due to the enormous deployment of IoT data acquisition devices. Detection of unusual patterns from large scale IoT data is important though challenging task. Recently, one-class support vector machines is extensively being used for anomaly detection. It tries to find an optimal hyperplane in high dimensional data that best separates the data from anomalies with maximum margin. However, the hinge loss of traditional one-class support vector machines is unbounded, which results in larger loss caused by outliers affecting its performance for anomaly detection. Furthermore, existing methods are computationally complex for larger data. In this paper, we present novel anomaly detection for large scale data by using randomized nonlinear features in support vector machines with bounded loss function rather than finding optimized support vectors with unbounded loss function. Extensive experimental evaluation on ten benchmark datasets shows the robustness of the proposed approach against outliers such as 0.8239, 0.7921 , 0.7501, 0.6711 , 0.6692, 0.4789 , 0.6462 , 0.6812 , 0.7271 and 0.7873 accuracy for Gas Sensor Array, Human Activity Recognition, Parkinson’s, Hepatitis, Breast Cancer, Blood Transfusion , Heart, ILPD and Wholesale Customers datasets respectively. In addition to this, introduction of randomized nonlinear feature helps to considerably decrease the computational complexity and space complexity from O(N3) to O(Bkn) and O(N2) to O(Bkn). Thus, very attractive for larger datasets.
科研通智能强力驱动
Strongly Powered by AbleSci AI