Open AccessFilling Algorithm for the Missing Value of Network Stability Monitoring Results Based on Big Data
Author(s) -
Pinpin Lyu
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1673/1/012011
Subject(s) - missing data , stability (learning theory) , computer science , value (mathematics) , big data , field (mathematics) , algorithm , data mining , mode (computer interface) , set (abstract data type) , data set , mathematics , artificial intelligence , machine learning , pure mathematics , programming language , operating system
In the research field of network stability monitoring based on big data, there are some disadvantages. For example, the processing method of the missing value of results influences execution effect, interfere the final filling effect and can only be applied in small data set. Therefore, a missing value filling algorithm for network stability monitoring results based on big data is proposed. The evaluation index of network stability monitoring based on big data is selected, and data missing mode and missing value filling mechanism are analyzed. The filling algorithm for the missing value of results based on big data is designed, the missing value filling parameter framework is constructed, the missing value filling parameters are processed, and the filling of the missing value of network stability detection results is completed. Compared with the traditional algorithm, the experimental results show that the efficiency of the designed missing value filling algorithm is 70.3% higher than that of the traditional filling algorithm, and the accuracy rate is far higher than the traditional method.