A deep learning approach for predicting critical events using event logs
A deep learning approach for predicting critical events using event logs
复制标题
使用事件日志预测关键事件的深度学习方法
DOI：
10.1002/qre.2853
复制
发表时间：
2021-02
影响因子：
2.3
通讯作者：
Congfang Huang;Akash Deep;Shiyu Zhou;D. Veeramani
中科院分区：
文献类型：
--
作者：
Congfang Huang;Akash Deep;Shiyu Zhou;D. Veeramani
事件日志包括关于不同类型的事件的发生和相关联的时间的数据，通常在现代工业机器和系统的操作期间收集。人们普遍认为，事件日志中嵌入的丰富信息可以用来预测关键事件的发生。在本文中，我们提出了一个递归神经网络模型，它使用来自事件日志的时间到事件数据，不仅可以预测感兴趣的目标事件的发生时间，还可以从训练的模型中解释导致目标事件的重要事件。为了提高模型的性能，本文采用了抽样技术和删失数据处理方法。该模型在模拟数据和真实的世界数据集上进行了测试。通过这些比较研究，我们表明，深度学习方法通常可以实现比传统统计模型（如考克斯比例风险模型）更好的预测性能。真实的世界的案例研究也表明，在这项工作中提出的模型解释算法可以揭示事件之间的潜在物理关系。
Event logs, comprising data on the occurrence of different types of events and associated times, are commonly collected during the operation of modern industrial machines and systems. It is widely believed that the rich information embedded in event logs can be used to predict the occurrence of critical events. In this paper, we propose a recurrent neural network model using time‐to‐event data from event logs not only to predict the time of the occurrence of a target event of interest, but also to interpret, from the trained model, significant events leading to the target event. To improve the performance of our model, sampling techniques and methods dealing with the censored data are utilized. The proposed model is tested on both simulated data and real‐world datasets. Through these comparison studies, we show that the deep learning approach can often achieve better prediction performance than the traditional statistical model, such as, the Cox proportional hazard model. The real‐world case study also shows that the model interpretation algorithm proposed in this work can reveal the underlying physical relationship among events.