This is the experimental code for PENG Neng-song,Anomaly detection method for wireless sensor networks based on time series data and is compared with the literature 《Cao Dong-lei A Fault-Tolerant Algorithm for Event Region Detection in Wireless Sensor Network》
In view of the large difference of sampling value between sensors in the harsh environment of sensor networks, and with the increase of fault nodes in wireless sensor networks and inaccurate event detection, a new detection method based on sensor network time series is proposed. Using the median of the K normal data of the sensor to establish the pivot quantity and construct the confidence interval, a method is proposed to calculate the variance of the data interval to judge the source of the anomaly. The experimental results show that the detection rate of abnormal data in the sensor is more than 98%, and the false positives rate remains below 0.5%, which has certain practicability.
This is my personal website. Share some java and big data technologies. Welcome to visit.