M2NN: Rare Event Inference through Multi-variate Multi-scale Attention
M2NN: Rare Event Inference through Multi-variate Multi-scale Attention
复制标题
DOI：
10.1109/smds49396.2020.00014
复制
发表时间：
2020-10
期刊：
影响因子：
--
通讯作者：
Manjusha Ravindranath;K. Candan;M. Sapino
中科院分区：
文献类型：
--
作者：
Manjusha Ravindranath;K. Candan;M. Sapino
随着传感数据的可用性越来越高，推断观测中相关事件的存在正成为依赖此类数据源的应用程序中智能数据服务交付的关键任务。然而，当被推断的事件是罕见的时，例如当试图在脑电图（EEG）数据中推断癫痫发作事件时，现有的解决方案往往失败。在本文中，我们注意到，多变量时间序列通常具有鲁棒的局部多变量时间特征，至少在理论上可以帮助识别这些事件;然而，缺乏足够的数据来训练这些事件使得神经架构无法识别和利用这些特征。为了应对这一挑战，我们提出了一个基于LSTM的神经架构，M2 N N，与注意力机制，利用强大的多变量时间特征，提取先验和输入到NN作为边信息。特别地，通过在多个尺度上同时考虑时间序列的时间特征沿着外部知识（包括先验已知的变量关系）来提取多变量时间特征。然后，我们证明了利用这些多尺度、多变量特征的具有双层注意力的单层LSTM在EEG数据的罕见癫痫发作检测中提供了显着的收益。此外，为了说明M2 N N更广泛的适用性（和可重复性），我们还在其他公开的罕见事件检测任务中对其进行了评估，例如制造业中的异常检测。我们进一步表明，建议的M2 N N技术是有益的，在解决更传统的推理问题，如旅行时间预测，罕见的事故事件可能会导致事故。
With the increasing availability of sensory data, inferring the existence of relevant events in the observations is becoming a critical task for smart data service delivery in applications that rely on such data sources. Yet, existing solutions tend to fail when the events that are being inferred are rare, for instance when one attempts to infer seizure events in electroencephalogram (EEG) data. In this paper, we note that multi-variate time series often carry robust localized multi-variate temporal features that could, at least in theory, help identify these events; however, the lack of sufficient data to train for these events make it impossible for neural architectures to identify and make use of these features. To tackle this challenge, we propose an LSTM-based neural architecture, M2N N, with an attention mechanism that leverages robust multivariate temporal features that are extracted a priori and fed into the NN as a side information. In particular, multi-variate temporal features are extracted by simultaneously considering, at multiple scales, temporal characteristics of the time series along with external knowledge, including variate relationships that are known a priori. We then show that a single layer LSTM with dual-layer attention that leverages these multi-scale, multi-variate features provides significant gains in rare seizure detection on EEG data. In addition, in order to illustrate the broader applicability (and reproducibility) of M2N N, we also evaluate it in other publicly available rare event detection tasks, such as anomaly detection in manufacturing. We further show that the proposed M2N N technique is beneficial in tackling more traditional inference problems, such as travel-time prediction, where rare accident events can cause congestions.