It is difficult to accurately identify the intrusion detection method of wireless sensor network nodes,which leads to the problem of low risk detection rate.A detection method based on big data mining is proposed.Through node classification,abnormal feature extraction and AdaBoost algorithm,the accurate classification of intrusion data is realized.Using the cluster network structure fusion data,after feature selection and normalization processing,a detection model is built based on data reduction and logistic regression.By processing the reduced data and calculating the feature weights,the judgment matrix is constructed to realize accurate and efficient intrusion risk detection.The experimental results show that the proposed method effectively handles the network complexity and significantly improves the risk detection rate.The experiment proves that it can efficiently and accurately detect the intrusion risk,and provides a solid guarantee for the safe and stable operation of the wireless sensor network.
big data miningwireless sensor networknetwork nodenode invasionintrusion risk detection
维普
万方数据
