M2NN: Rare Event Inference through Multi-variate Multi-scale Attention

Manjusha Ravindranath, K. Selcuk Candan, Maria Luisa Sapino

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

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.

Original languageEnglish (US)
Title of host publicationProceedings - 2020 IEEE International Conference on Smart Data Services, SMDS 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages53-62
Number of pages10
ISBN (Electronic)9781728187778
DOIs
StatePublished - Oct 2020
Event2020 IEEE International Conference on Smart Data Services, SMDS 2020 - Virtual, Beijing, China
Duration: Oct 18 2020Oct 24 2020

Publication series

NameProceedings - 2020 IEEE International Conference on Smart Data Services, SMDS 2020

Conference

Conference2020 IEEE International Conference on Smart Data Services, SMDS 2020
Country/TerritoryChina
CityVirtual, Beijing
Period10/18/2010/24/20

Keywords

  • Brain EEG analysis
  • Multi-scale attention
  • Multivariate time series
  • Rare event inference

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Information Systems
  • Information Systems and Management

Fingerprint

Dive into the research topics of 'M2NN: Rare Event Inference through Multi-variate Multi-scale Attention'. Together they form a unique fingerprint.

Cite this