Optical fiber perimeter security intrusion event identification model construction method and security system

The invention discloses an optical fiber perimeter security intrusion event identification model construction method and a security system, and the optical fiber perimeter security intrusion event identification model construction method comprises the steps: enabling a multimode optical fiber to be wound on a perimeter fence to form a sensing unit so as to detect an external intrusion event; enabling the detected intrusion event to be user for filtering of a filter bank and decomposed into four different frequency bands, and carrying out feature extraction in the four different frequency bandsby adopting a combination vector of a singular value and a kurtosis value; and finally, inputting the extracted combined feature vectors into an improved probabilistic neural network optimized by a salp swarm algorithm for training and obtaining an optimal smoothing factor, thereby effectively reducing the false alarm rate of artificial intrusion events and non-artificial intrusion events. 一种光纤周界安防入侵事件识别模型构建方法和安防系统，将多模光纤