Fiber optic perimeter detection based on principal component analysis

It is a key requirement for any perimeter intrusion detection system to distinguish the intrusion from environmental events without reducing the efficiency. We implement and demonstrate a fiber optic perimeter detection system, which screens the event signal by its features in frequency domain. These features are extracted by method of principal component analysis (PCA) and then identified by support vector machine (SVM). Experimental results show that the combination of PCA and SVM improve evidently the anti-disturbance ability.