Affiliation:
1. School of Software, South China Normal University, Foshan , 528225, China
Abstract
Abstract
At present, in the fault diagnosis database of submarine optical fiber network, the attribute selection of large data is completed by detecting the attributes of the data, the accuracy of large data attribute selection cannot be guaranteed. In this paper, a large data attribute selection method based on support vector machines (SVM) for fault diagnosis database of submarine optical fiber network is proposed. Mining large data in the database of optical fiber network fault diagnosis, and calculate its attribute weight, attribute classification is completed according to attribute weight, so as to complete attribute selection of large data. Experimental results prove that ,the proposed method can improve the accuracy of large data attribute selection in fault diagnosis database of submarine optical fiber network, and has high use value.
Subject
Mechanical Engineering,Ocean Engineering
Reference24 articles.
1. 1. Karabadji N E I, Seridi H, Khelf I, et al. Improved decision tree construction based on attribute selection and data sampling for fault diagnosis in rotating machines. Engineering Applications of Artificial Intelligence, 2014, 35(35):71-83.
2. 2. Zhang Q H, Qin A, Shu L, et al. Vibration sensor based intelligent fault diagnosis system for large machine unit in petrochemical industry. International Journal of Distributed Sensor Networks, 2015, 2015(3):1376-1381.
3. 3. Jin S, Cui W, Jin Z, et al. AF-DHNN: Fuzzy Clustering and Inference-Based Node Fault Diagnosis Method for Fire Detection.. Sensors, 2015, 15(7):17366-17396.
4. 4. Panda M, Khilar P M. Distributed self fault diagnosis algorithm for large scale wireless sensor networks using modified three sigma edit test. Ad Hoc Networks, 2015, 25(PA):170-184.
5. 5. Zhang Q H, Hu Q, Sun G, et al. Concurrent Fault Diagnosis for Rotating Machinery Based on Vibration Sensors. International Journal of Distributed Sensor Networks, 2015, 2013(1):59-72.
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献