Sichuan University National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University, Chengdu 610064, China.
College of Electrical Engineering, Sichuan University, Chengdu 610065, China.
Sensors (Basel). 2023 Apr 19;23(8):4094. doi: 10.3390/s23084094.
Deep learning anomaly detection is important in distributed optical fiber acoustic sensing (DAS). However, anomaly detection is more challenging than traditional learning tasks, due to the scarcity of true-positive data and the vast imbalance and irregularity within datasets. Furthermore, it is impossible to catalog all types of anomalies, therefore, the direct application of supervised learning is deficient. To overcome these problems, an unsupervised deep learning method that only learns the normal data features from ordinary events is proposed. First, a convolutional autoencoder is used to extract DAS signal features. A clustering algorithm then locates the feature center of the normal data, and the distance to the new signal is used to determine whether it is an anomaly. The efficacy of the proposed method was evaluated in a real high-speed rail intrusion scenario, and considered all behaviors that may threaten the normal operation of high-speed trains as abnormal. The results show that the threat detection rate of this method reaches 91.5%, which is 5.9% higher than that of the state-of-the-art supervised network and, at 7.2%, the false alarm rate is 0.8% lower than the supervised network. Moreover, using a shallow autoencoder reduces the parameters to 1.34 K, which is significantly lower than the 79.55 K of the state-of-the-art supervised network.
深度学习异常检测在分布式光纤声学传感（DAS）中很重要。然而，异常检测比传统的学习任务更具挑战性，因为真阳性数据的稀缺性以及数据集中的巨大不平衡和不规则性。此外，不可能对所有类型的异常进行分类，因此，监督学习的直接应用是不足的。为了克服这些问题，提出了一种仅从普通事件中学习正常数据特征的无监督深度学习方法。首先，使用卷积自动编码器提取 DAS 信号特征。然后，聚类算法定位正常数据的特征中心，并用新信号与特征中心的距离来确定是否异常。在真实的高铁入侵场景中评估了所提出方法的性能，并将可能威胁高铁正常运行的所有行为都视为异常。结果表明，该方法的威胁检测率达到 91.5%，比最先进的监督网络高出 5.9%，而误报率则比监督网络低 0.8%。此外，使用浅层自动编码器将参数减少到 1.34K，明显低于最先进的监督网络的 79.55K。
